github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9782] "Error: llama runner process has terminated: CUDA error: out of memory" while having some idling GPUs #52908

New Issue
Closed
opened 2026-04-29 01:20:20 -05:00 by GiteaMirror · 20 comments
GiteaMirror commented 2026-04-29 01:20:20 -05:00
Owner
Copy Link

Originally created by @AlbertoSinigaglia on GitHub (Mar 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9782

What is the issue?

This is the model I'm trying to load:

ollama list
NAME                                                          ID              SIZE      MODIFIED     
cas/nous-hermes-2-mistral-7b-dpo:latest                       1591668a22eb    4.4 GB    3 weeks ago

Which is pretty small, however, I'm getting:

ollama run cas/nous-hermes-2-mistral-7b-dpo:latest
Error: llama runner process has terminated: CUDA error: out of memory
  current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898
  cudaMemGetInfo(free, total)
//ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error

Which would be fine, if only I didn't have 80Gb of VRAM free (running nvitop):

Image

The first 2 GPUs are pretty much free. Ollama is not restricted to any of these GPUs, indeed usually it also manages to shard the big models across these three GPUs. At this point, I'm thinking that it wants to allocate the model in the only GPU that is already occupied...

Side notes:

  • this does not depend on the specific model I try to load, anyone I try to load get's the same error.
  • in GPU:1 there occupied memory is Phi4 (which is always loaded in memory)

OS

Ubuntu 22.04

GPU

3x NVIDIA RTX A6000 48Gb

CPU

AMD Ryzen Threadripper PRO 5995WX 64-Cores

Ollama version

ollama version is 0.5.13

Originally created by @AlbertoSinigaglia on GitHub (Mar 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9782 ### What is the issue? This is the model I'm trying to load: ``` ollama list NAME ID SIZE MODIFIED cas/nous-hermes-2-mistral-7b-dpo:latest 1591668a22eb 4.4 GB 3 weeks ago ``` Which is pretty small, however, I'm getting: ``` ollama run cas/nous-hermes-2-mistral-7b-dpo:latest Error: llama runner process has terminated: CUDA error: out of memory current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898 cudaMemGetInfo(free, total) //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error ``` Which would be fine, if only I didn't have 80Gb of VRAM free (running `nvitop`): <img width="1203" alt="Image" src="https://github.com/user-attachments/assets/4e377236-59b8-4cdb-a4b5-9b138af5542f" /> The first 2 GPUs are pretty much free. Ollama is not restricted to any of these GPUs, indeed usually it also manages to shard the big models across these three GPUs. At this point, I'm thinking that it wants to allocate the model in the only GPU that is already occupied... Side notes: - this does not depend on the specific model I try to load, anyone I try to load get's the same error. - in GPU:1 there occupied memory is Phi4 (which is always loaded in memory) ### OS Ubuntu 22.04 ### GPU 3x `NVIDIA RTX A6000 48Gb` ### CPU `AMD Ryzen Threadripper PRO 5995WX 64-Cores` ### Ollama version `ollama version is 0.5.13`
GiteaMirror added the bug label 2026-04-29 01:20:20 -05:00
GiteaMirror commented 2026-04-29 01:20:22 -05:00
Author
Owner
Copy Link

@AlbertoSinigaglia commented on GitHub (Mar 15, 2025):

I've updated to the new 0.6.0, which solved the issue, though also 0.5.13 was running fine until this morning, so I feel that it's not quite a "static" bug, but more of a "Running" bug... let you know if that happens again

<!-- gh-comment-id:2726440249 --> @AlbertoSinigaglia commented on GitHub (Mar 15, 2025): I've updated to the new 0.6.0, which solved the issue, though also 0.5.13 was running fine until this morning, so I feel that it's not quite a "static" bug, but more of a "Running" bug... let you know if that happens again
GiteaMirror commented 2026-04-29 01:20:23 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 16, 2025):

If you still have the log, could you include some of the lines from before the crash? It might give some insight into what it was doing when the alloc failed.

<!-- gh-comment-id:2727458572 --> @rick-github commented on GitHub (Mar 16, 2025): If you still have the log, could you include some of the lines from before the crash? It might give some insight into what it was doing when the alloc failed.
GiteaMirror commented 2026-04-29 01:20:24 -05:00
Author
Owner
Copy Link

@demiurger commented on GitHub (Mar 16, 2025):

Have the same issue: model starts, if prompt is short it works, if promt is like few sentence ollama crashes with OOM.
Have 2 1080Ti 11GB. Same results with 0.6.0

app.log
server.log

<!-- gh-comment-id:2727469987 --> @demiurger commented on GitHub (Mar 16, 2025): Have the same issue: model starts, if prompt is short it works, if promt is like few sentence ollama crashes with OOM. Have 2 1080Ti 11GB. Same results with 0.6.0 [app.log](https://github.com/user-attachments/files/19272486/app.log) [server.log](https://github.com/user-attachments/files/19272487/server.log)
GiteaMirror commented 2026-04-29 01:20:25 -05:00
Author
Owner
Copy Link

@AlbertoSinigaglia commented on GitHub (Mar 16, 2025):

If you still have the log, could you include some of the lines from before the crash? It might give some insight into what it was doing when the alloc failed.

Mmm not sure, what should i run to get them? (Or in which folder are they stored?)

<!-- gh-comment-id:2727476367 --> @AlbertoSinigaglia commented on GitHub (Mar 16, 2025): > If you still have the log, could you include some of the lines from before the crash? It might give some insight into what it was doing when the alloc failed. Mmm not sure, what should i run to get them? (Or in which folder are they stored?)
GiteaMirror commented 2026-04-29 01:20:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 16, 2025):

Where ever you found the Error: llama runner process has terminated: CUDA error: out of memory line. A few lines above that will either show GIN lines, or hopefully some lines starting with ggml which may give insight into what was happening. either that or just include the output of sudo journalctl -u ollama --no-pager --since=yesterday

<!-- gh-comment-id:2727480926 --> @rick-github commented on GitHub (Mar 16, 2025): Where ever you found the `Error: llama runner process has terminated: CUDA error: out of memory` line. A few lines above that will either show `GIN` lines, or hopefully some lines starting with `ggml` which may give insight into what was happening. either that or just include the output of `sudo journalctl -u ollama --no-pager --since=yesterday`
GiteaMirror commented 2026-04-29 01:20:26 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 16, 2025):

@demiurger Something strange is happening.

time=2025-03-15T20:51:29.821Z level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=63
 layers.offload=49 layers.split=24,25 memory.available="[10.0 GiB 8.6 GiB]" memory.gpu_overhead="0 B"
 memory.required.full="22.9 GiB" memory.required.partial="18.4 GiB" memory.required.kv="992.0 MiB"
 memory.required.allocations="[10.0 GiB 8.4 GiB]" memory.weights.total="14.3 GiB" memory.weights.repeating="14.3 GiB"
 memory.weights.nonrepeating="1.1 GiB" memory.graph.full="1.6 GiB" memory.graph.partial="1.6 GiB"
 projector.weights="795.9 MiB" projector.graph="1.0 GiB"

ollama needs 23G to host the model. You don't have enough VRAM to hold it all, so ollama allocates 18.4G of the available 18.6G of VRAM and offloads 49 of 63 layers to the GPU.

time=2025-03-15T20:51:50.333Z level=INFO source=server.go:624 msg="llama runner started in 20.37 seconds"
[GIN] 2025/03/15 - 20:51:50 | 200 |   20.7185226s |       127.0.0.1 | POST     "/api/generate"

It successfully loads the model and completes a generate inference.

ggml_backend_cuda_buffer_type_alloc_buffer: allocating 13130.09 MiB on device 0: cudaMalloc failed: out of memory
ggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 13767896576

But then decides it suddenly needs another 13G of VRAM. It's like some allocator deep in ollama/llama.cpp got MB and GB mixed up. Do you recall what the query was that caused the OOM?

<!-- gh-comment-id:2727484953 --> @rick-github commented on GitHub (Mar 16, 2025): @demiurger Something strange is happening. ``` time=2025-03-15T20:51:29.821Z level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=63 layers.offload=49 layers.split=24,25 memory.available="[10.0 GiB 8.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="22.9 GiB" memory.required.partial="18.4 GiB" memory.required.kv="992.0 MiB" memory.required.allocations="[10.0 GiB 8.4 GiB]" memory.weights.total="14.3 GiB" memory.weights.repeating="14.3 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="1.6 GiB" memory.graph.partial="1.6 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" ``` ollama needs 23G to host the model. You don't have enough VRAM to hold it all, so ollama allocates 18.4G of the available 18.6G of VRAM and offloads 49 of 63 layers to the GPU. ``` time=2025-03-15T20:51:50.333Z level=INFO source=server.go:624 msg="llama runner started in 20.37 seconds" [GIN] 2025/03/15 - 20:51:50 | 200 | 20.7185226s | 127.0.0.1 | POST "/api/generate" ``` It successfully loads the model and completes a `generate` inference. ``` ggml_backend_cuda_buffer_type_alloc_buffer: allocating 13130.09 MiB on device 0: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 13767896576 ``` But then decides it suddenly needs another 13G of VRAM. It's like some allocator deep in ollama/llama.cpp got MB and GB mixed up. Do you recall what the query was that caused the OOM?
GiteaMirror commented 2026-04-29 01:20:28 -05:00
Author
Owner
Copy Link

@AlbertoSinigaglia commented on GitHub (Mar 16, 2025):

@rick-github here's one of the logs

logs from ollama 
mar 15 11:39:07 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:07.109+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.136+01:00 level=INFO source=sched.go:508 msg="updated VRAM based on existing loaded models" gpu=GPU-a1c88671-c53c-a240-0fe5-5e9bd6b67d6e library=cuda total="47.5 GiB" available="38.6 GiB"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=INFO source=sched.go:508 msg="updated VRAM based on existing loaded models" gpu=GPU-8d08743b-a730-6035-e5ed-9d2a4bb7d987 library=cuda total="47.5 GiB" available="36.1 GiB"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=INFO source=sched.go:508 msg="updated VRAM based on existing loaded models" gpu=GPU-f80f1c32-b9ea-b671-ee24-8ed809aed7d1 library=cuda total="47.5 GiB" available="47.2 GiB"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.key_length default=128
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.value_length default=128
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48 gpu=GPU-f80f1c32-b9ea-b671-ee24-8ed809aed7d1 parallel=4 available=50671386624 required="35.3 GiB"
mar 15 11:39:07 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:07.407+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:97 msg="system memory" total="503.5 GiB" free="431.4 GiB" free_swap="61.3 GiB"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.key_length default=128
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.value_length default=128
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:130 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[47.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="35.3 GiB" memory.required.partial="35.3 GiB" memory.required.kv="2.0 GiB" memory.required.allocations="[35.3 GiB]" memory.weights.total="32.9 GiB" memory.weights.repeating="32.1 GiB" memory.weights.nonrepeating="788.9 MiB" memory.graph.full="676.0 MiB" memory.graph.partial="916.1 MiB"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48 --ctx-size 8192 --batch-size 512 --n-gpu-layers 65 --threads 64 --parallel 4 --port 34775"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.408+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=2
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.408+01:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.408+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.423+01:00 level=INFO source=runner.go:931 msg="starting go runner"
mar 15 11:39:07 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
mar 15 11:39:07 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
mar 15 11:39:07 acquario3 ollama[87551]: ggml_cuda_init: found 1 CUDA devices:
mar 15 11:39:07 acquario3 ollama[87551]:   Device 0: NVIDIA RTX A6000, compute capability 8.6, VMM: yes
mar 15 11:39:07 acquario3 ollama[87551]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
mar 15 11:39:07 acquario3 ollama[87551]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 500,600,610,700,750,800,860,870,890,900,1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=64
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:992 msg="Server listening on 127.0.0.1:34775"
mar 15 11:39:07 acquario3 ollama[87551]: CUDA error: out of memory
mar 15 11:39:07 acquario3 ollama[87551]:   current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898
mar 15 11:39:07 acquario3 ollama[87551]:   cudaMemGetInfo(free, total)
mar 15 11:39:07 acquario3 ollama[87551]: //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.660+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
mar 15 11:39:07 acquario3 ollama[87551]: Could not attach to process.  If your uid matches the uid of the target
mar 15 11:39:07 acquario3 ollama[87551]: process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
mar 15 11:39:07 acquario3 ollama[87551]: again as the root user.  For more details, see /etc/sysctl.d/10-ptrace.conf
mar 15 11:39:07 acquario3 ollama[87551]: ptrace: Inappropriate ioctl for device.
mar 15 11:39:07 acquario3 ollama[87551]: No stack.
mar 15 11:39:07 acquario3 ollama[87551]: The program is not being run.
mar 15 11:39:07 acquario3 ollama[87551]: SIGABRT: abort
mar 15 11:39:07 acquario3 ollama[87551]: PC=0x7e77300969fc m=0 sigcode=18446744073709551610
mar 15 11:39:07 acquario3 ollama[87551]: signal arrived during cgo execution
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 149 gp=0xc000511500 m=0 mp=0x64c82640e7a0 [syscall]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.cgocall(0x64c82555ac30, 0xc00019cc00)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/cgocall.go:167 +0x4b fp=0xc00019cbd8 sp=0xc00019cba0 pc=0x64c82490858b
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama._Cfunc_llama_model_load_from_file(0x64c828253680, {0x0, 0x41, 0x1, 0x0, 0x0, 0x64c82555a510, 0xc0005fffd0, 0x0, 0x0, ...})
mar 15 11:39:07 acquario3 ollama[87551]:         _cgo_gotypes.go:754 +0x4b fp=0xc00019cc00 sp=0xc00019cbd8 pc=0x64c824c8ef6b
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama.LoadModelFromFile.func1(...)
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/llama/llama.go:265
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama.LoadModelFromFile({0x7ffc0a89ebf0, 0x6e}, {0x41, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc0006468b0, ...})
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/llama/llama.go:265 +0x36b fp=0xc00019cdc8 sp=0xc00019cc00 pc=0x64c824c91aeb
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0003d26c0, {0x41, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc0006468b0, 0x0}, ...)
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/llamarunner/runner.go:849 +0x9b fp=0xc00019cf10 sp=0xc00019cdc8 pc=0x64c824cacddb
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/llamarunner/runner.go:966 +0xda fp=0xc00019cfe0 sp=0xc00019cf10 pc=0x64c824cae69a
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00019cfe8 sp=0xc00019cfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/llamarunner/runner.go:966 +0xcb7
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 1 gp=0xc000002380 m=nil [IO wait]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0002735b8 sp=0xc000273598 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.netpollblock(0xc000273608?, 0x248a51a6?, 0xc8?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/netpoll.go:575 +0xf7 fp=0xc0002735f0 sp=0xc0002735b8 pc=0x64c8248d0677
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.runtime_pollWait(0x7e77302a4e70, 0x72)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/netpoll.go:351 +0x85 fp=0xc000273610 sp=0xc0002735f0 pc=0x64c82490aa85
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).wait(0xc00051a000?, 0x900000036?, 0x0)
mar 15 11:39:07 acquario3 ollama[87551]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000273638 sp=0xc000273610 pc=0x64c824991f07
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).waitRead(...)
mar 15 11:39:07 acquario3 ollama[87551]:         internal/poll/fd_poll_runtime.go:89
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*FD).Accept(0xc00051a000)
mar 15 11:39:07 acquario3 ollama[87551]:         internal/poll/fd_unix.go:620 +0x295 fp=0xc0002736e0 sp=0xc000273638 pc=0x64c8249972d5
mar 15 11:39:07 acquario3 ollama[87551]: net.(*netFD).accept(0xc00051a000)
mar 15 11:39:07 acquario3 ollama[87551]:         net/fd_unix.go:172 +0x29 fp=0xc000273798 sp=0xc0002736e0 pc=0x64c824a09749
mar 15 11:39:07 acquario3 ollama[87551]: net.(*TCPListener).accept(0xc00052e000)
mar 15 11:39:07 acquario3 ollama[87551]:         net/tcpsock_posix.go:159 +0x1b fp=0xc0002737e8 sp=0xc000273798 pc=0x64c824a1f0fb
mar 15 11:39:07 acquario3 ollama[87551]: net.(*TCPListener).Accept(0xc00052e000)
mar 15 11:39:07 acquario3 ollama[87551]:         net/tcpsock.go:380 +0x30 fp=0xc000273818 sp=0xc0002737e8 pc=0x64c824a1dfb0
mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*onceCloseListener).Accept(0xc0003d2750?)
mar 15 11:39:07 acquario3 ollama[87551]:         <autogenerated>:1 +0x24 fp=0xc000273830 sp=0xc000273818 pc=0x64c824c34e64
mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*Server).Serve(0xc00053a000, {0x64c825bb9528, 0xc00052e000})
mar 15 11:39:07 acquario3 ollama[87551]:         net/http/server.go:3424 +0x30c fp=0xc000273960 sp=0xc000273830 pc=0x64c824c0c72c
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034120, 0xe, 0xe})
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/llamarunner/runner.go:993 +0x116a fp=0xc000273d08 sp=0xc000273960 pc=0x64c824cae2ca
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner.Execute({0xc000034110?, 0x0?, 0x0?})
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000273d30 sp=0xc000273d08 pc=0x64c824ed89b4
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000035b00?, {0x64c825738055?, 0x4?, 0x64c825738059?})
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/cmd/cmd.go:1281 +0x45 fp=0xc000273d58 sp=0xc000273d30 pc=0x64c8254ede45
mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).execute(0xc00064ef08, {0xc0005e15e0, 0xe, 0xe})
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000273e78 sp=0xc000273d58 pc=0x64c824a829dc
mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).ExecuteC(0xc00061c908)
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000273f30 sp=0xc000273e78 pc=0x64c824a83225
mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).Execute(...)
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/spf13/cobra@v1.7.0/command.go:992
mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/spf13/cobra@v1.7.0/command.go:985
mar 15 11:39:07 acquario3 ollama[87551]: main.main()
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000273f50 sp=0xc000273f30 pc=0x64c8254ee1ad
mar 15 11:39:07 acquario3 ollama[87551]: runtime.main()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:283 +0x29d fp=0xc000273fe0 sp=0xc000273f50 pc=0x64c8248d7c7d
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000273fe8 sp=0xc000273fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018cfa8 sp=0xc00018cf88 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:441
mar 15 11:39:07 acquario3 ollama[87551]: runtime.forcegchelper()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:348 +0xb8 fp=0xc00018cfe0 sp=0xc00018cfa8 pc=0x64c8248d7fb8
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018cfe8 sp=0xc00018cfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.init.7 in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:336 +0x1a
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018d780 sp=0xc00018d760 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:441
mar 15 11:39:07 acquario3 ollama[87551]: runtime.bgsweep(0xc000186080)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgcsweep.go:316 +0xdf fp=0xc00018d7c8 sp=0xc00018d780 pc=0x64c8248c27df
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcenable.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:204 +0x25 fp=0xc00018d7e0 sp=0xc00018d7c8 pc=0x64c8248b6bc5
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018d7e8 sp=0xc00018d7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcenable in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:204 +0x66
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x10000?, 0x64c8258ea9d8?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018df78 sp=0xc00018df58 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:441
mar 15 11:39:07 acquario3 ollama[87551]: runtime.(*scavengerState).park(0x64c82640b980)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc00018dfa8 sp=0xc00018df78 pc=0x64c8248c0229
mar 15 11:39:07 acquario3 ollama[87551]: runtime.bgscavenge(0xc000186080)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc00018dfc8 sp=0xc00018dfa8 pc=0x64c8248c07b9
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcenable.gowrap2()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:205 +0x25 fp=0xc00018dfe0 sp=0xc00018dfc8 pc=0x64c8248b6b65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018dfe8 sp=0xc00018dfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcenable in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:205 +0xa5
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc00018c688?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018c630 sp=0xc00018c610 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.runfinq()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mfinal.go:196 +0x107 fp=0xc00018c7e0 sp=0xc00018c630 pc=0x64c8248b5b87
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018c7e8 sp=0xc00018c7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.createfing in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mfinal.go:166 +0x3d
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 6 gp=0xc0002ec8c0 m=nil [chan receive]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0xc00033d5e0?, 0xc00023c018?, 0x60?, 0xe7?, 0x64c8249f0488?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018e718 sp=0xc00018e6f8 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.chanrecv(0xc0000403f0, 0x0, 0x1)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/chan.go:664 +0x445 fp=0xc00018e790 sp=0xc00018e718 pc=0x64c8248a7d85
mar 15 11:39:07 acquario3 ollama[87551]: runtime.chanrecv1(0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/chan.go:506 +0x12 fp=0xc00018e7b8 sp=0xc00018e790 pc=0x64c8248a7912
mar 15 11:39:07 acquario3 ollama[87551]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1796
mar 15 11:39:07 acquario3 ollama[87551]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1799 +0x2f fp=0xc00018e7e0 sp=0xc00018e7b8 pc=0x64c8248b9d6f
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018e7e8 sp=0xc00018e7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1794 +0x85
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 7 gp=0xc0002eca80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018ef38 sp=0xc00018ef18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00018efc8 sp=0xc00018ef38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00018efe0 sp=0xc00018efc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018efe8 sp=0xc00018efe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 8 gp=0xc0002ecc40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018f738 sp=0xc00018f718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00018f7c8 sp=0xc00018f738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00018f7e0 sp=0xc00018f7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018f7e8 sp=0xc00018f7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 9 gp=0xc0002ece00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018ff38 sp=0xc00018ff18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00018ffc8 sp=0xc00018ff38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00018ffe0 sp=0xc00018ffc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018ffe8 sp=0xc00018ffe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 10 gp=0xc0002ecfc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000188738 sp=0xc000188718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0001887c8 sp=0xc000188738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0001887e0 sp=0xc0001887c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0001887e8 sp=0xc0001887e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 11 gp=0xc0002ed180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000188f38 sp=0xc000188f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000188fc8 sp=0xc000188f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000188fe0 sp=0xc000188fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000188fe8 sp=0xc000188fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 12 gp=0xc0002ed340 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000189738 sp=0xc000189718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0001897c8 sp=0xc000189738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0001897e0 sp=0xc0001897c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0001897e8 sp=0xc0001897e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 13 gp=0xc0002ed500 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000189f38 sp=0xc000189f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000189fc8 sp=0xc000189f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000189fe0 sp=0xc000189fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000189fe8 sp=0xc000189fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 14 gp=0xc0002ed6c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018a738 sp=0xc00018a718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00018a7c8 sp=0xc00018a738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00018a7e0 sp=0xc00018a7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018a7e8 sp=0xc00018a7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 15 gp=0xc0002ed880 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018af38 sp=0xc00018af18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00018afc8 sp=0xc00018af38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00018afe0 sp=0xc00018afc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018afe8 sp=0xc00018afe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 16 gp=0xc0002eda40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018b738 sp=0xc00018b718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00018b7c8 sp=0xc00018b738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00018b7e0 sp=0xc00018b7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018b7e8 sp=0xc00018b7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 18 gp=0xc0002edc00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00018bf38 sp=0xc00018bf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00018bfc8 sp=0xc00018bf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00018bfe0 sp=0xc00018bfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00018bfe8 sp=0xc00018bfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 19 gp=0xc0002eddc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049a738 sp=0xc00049a718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049a7c8 sp=0xc00049a738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049a7e0 sp=0xc00049a7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049a7e8 sp=0xc00049a7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 20 gp=0xc00049e000 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049af38 sp=0xc00049af18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049afc8 sp=0xc00049af38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049afe0 sp=0xc00049afc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049afe8 sp=0xc00049afe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 21 gp=0xc00049e1c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049b738 sp=0xc00049b718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049b7c8 sp=0xc00049b738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049b7e0 sp=0xc00049b7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049b7e8 sp=0xc00049b7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 22 gp=0xc00049e380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049bf38 sp=0xc00049bf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049bfc8 sp=0xc00049bf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049bfe0 sp=0xc00049bfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049bfe8 sp=0xc00049bfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 23 gp=0xc00049e540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049c738 sp=0xc00049c718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049c7c8 sp=0xc00049c738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049c7e0 sp=0xc00049c7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049c7e8 sp=0xc00049c7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 24 gp=0xc00049e700 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049cf38 sp=0xc00049cf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049cfc8 sp=0xc00049cf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049cfe0 sp=0xc00049cfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049cfe8 sp=0xc00049cfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 34 gp=0xc000202380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000496738 sp=0xc000496718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004967c8 sp=0xc000496738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004967e0 sp=0xc0004967c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004967e8 sp=0xc0004967e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 50 gp=0xc000504000 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 51 gp=0xc0005041c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 52 gp=0xc000504380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 53 gp=0xc000504540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 54 gp=0xc000504700 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 55 gp=0xc0005048c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050cf38 sp=0xc00050cf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050cfc8 sp=0xc00050cf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050cfe0 sp=0xc00050cfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050cfe8 sp=0xc00050cfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 56 gp=0xc000504a80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050d738 sp=0xc00050d718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050d7c8 sp=0xc00050d738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050d7e0 sp=0xc00050d7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050d7e8 sp=0xc00050d7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 57 gp=0xc000504c40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00050df38 sp=0xc00050df18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050dfc8 sp=0xc00050df38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00050dfe0 sp=0xc00050dfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050dfe8 sp=0xc00050dfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 58 gp=0xc000504e00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 59 gp=0xc000504fc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000506f38 sp=0xc000506f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000506fc8 sp=0xc000506f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000506fe0 sp=0xc000506fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000506fe8 sp=0xc000506fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 60 gp=0xc000505180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000507738 sp=0xc000507718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005077c8 sp=0xc000507738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0005077e0 sp=0xc0005077c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005077e8 sp=0xc0005077e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 25 gp=0xc00049e8c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049d738 sp=0xc00049d718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049d7c8 sp=0xc00049d738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049d7e0 sp=0xc00049d7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049d7e8 sp=0xc00049d7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 35 gp=0xc000202540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000496f38 sp=0xc000496f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000496fc8 sp=0xc000496f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000496fe0 sp=0xc000496fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000496fe8 sp=0xc000496fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 36 gp=0xc000202700 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000497738 sp=0xc000497718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004977c8 sp=0xc000497738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004977e0 sp=0xc0004977c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004977e8 sp=0xc0004977e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 26 gp=0xc00049ea80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00049df38 sp=0xc00049df18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00049dfc8 sp=0xc00049df38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00049dfe0 sp=0xc00049dfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00049dfe8 sp=0xc00049dfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 61 gp=0xc000505340 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000507f38 sp=0xc000507f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000507fc8 sp=0xc000507f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000507fe0 sp=0xc000507fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000507fe8 sp=0xc000507fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 37 gp=0xc0002028c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000497f38 sp=0xc000497f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000497fc8 sp=0xc000497f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000497fe0 sp=0xc000497fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000497fe8 sp=0xc000497fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 38 gp=0xc000202a80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000498738 sp=0xc000498718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004987c8 sp=0xc000498738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004987e0 sp=0xc0004987c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004987e8 sp=0xc0004987e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 27 gp=0xc00049ec40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a4738 sp=0xc0004a4718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a47c8 sp=0xc0004a4738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a47e0 sp=0xc0004a47c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a47e8 sp=0xc0004a47e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 28 gp=0xc00049ee00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a4f38 sp=0xc0004a4f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a4fc8 sp=0xc0004a4f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a4fe0 sp=0xc0004a4fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a4fe8 sp=0xc0004a4fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 29 gp=0xc00049efc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a5738 sp=0xc0004a5718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a57c8 sp=0xc0004a5738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a57e0 sp=0xc0004a57c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a57e8 sp=0xc0004a57e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 30 gp=0xc00049f180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a5f38 sp=0xc0004a5f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a5fc8 sp=0xc0004a5f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a5fe0 sp=0xc0004a5fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a5fe8 sp=0xc0004a5fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 31 gp=0xc00049f340 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a6738 sp=0xc0004a6718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a67c8 sp=0xc0004a6738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a67e0 sp=0xc0004a67c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a67e8 sp=0xc0004a67e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 32 gp=0xc00049f500 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a6f38 sp=0xc0004a6f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a6fc8 sp=0xc0004a6f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a6fe0 sp=0xc0004a6fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a6fe8 sp=0xc0004a6fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 39 gp=0xc000202c40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000498f38 sp=0xc000498f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000498fc8 sp=0xc000498f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000498fe0 sp=0xc000498fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000498fe8 sp=0xc000498fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 62 gp=0xc000505500 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000508738 sp=0xc000508718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005087c8 sp=0xc000508738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0005087e0 sp=0xc0005087c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005087e8 sp=0xc0005087e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 63 gp=0xc0005056c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000508f38 sp=0xc000508f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000508fc8 sp=0xc000508f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000508fe0 sp=0xc000508fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000508fe8 sp=0xc000508fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 64 gp=0xc000505880 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000509738 sp=0xc000509718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005097c8 sp=0xc000509738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0005097e0 sp=0xc0005097c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005097e8 sp=0xc0005097e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 65 gp=0xc000505a40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000509f38 sp=0xc000509f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000509fc8 sp=0xc000509f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000509fe0 sp=0xc000509fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000509fe8 sp=0xc000509fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 33 gp=0xc00049f6c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a7738 sp=0xc0004a7718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a77c8 sp=0xc0004a7738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a77e0 sp=0xc0004a77c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a77e8 sp=0xc0004a77e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 40 gp=0xc000202e00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000499738 sp=0xc000499718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004997c8 sp=0xc000499738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004997e0 sp=0xc0004997c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004997e8 sp=0xc0004997e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 41 gp=0xc000202fc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000499f38 sp=0xc000499f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000499fc8 sp=0xc000499f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000499fe0 sp=0xc000499fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000499fe8 sp=0xc000499fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 42 gp=0xc000203180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a0738 sp=0xc0004a0718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a07c8 sp=0xc0004a0738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a07e0 sp=0xc0004a07c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a07e8 sp=0xc0004a07e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 43 gp=0xc000203340 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a0f38 sp=0xc0004a0f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a0fc8 sp=0xc0004a0f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a0fe0 sp=0xc0004a0fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a0fe8 sp=0xc0004a0fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 44 gp=0xc000203500 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a1738 sp=0xc0004a1718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a17c8 sp=0xc0004a1738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a17e0 sp=0xc0004a17c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a17e8 sp=0xc0004a17e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 45 gp=0xc0002036c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a1f38 sp=0xc0004a1f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a1fc8 sp=0xc0004a1f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a1fe0 sp=0xc0004a1fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a1fe8 sp=0xc0004a1fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 46 gp=0xc000203880 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a2738 sp=0xc0004a2718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a27c8 sp=0xc0004a2738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a27e0 sp=0xc0004a27c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a27e8 sp=0xc0004a27e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 47 gp=0xc000203a40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a2f38 sp=0xc0004a2f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a2fc8 sp=0xc0004a2f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a2fe0 sp=0xc0004a2fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a2fe8 sp=0xc0004a2fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 48 gp=0xc000203c00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a3738 sp=0xc0004a3718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a37c8 sp=0xc0004a3738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a37e0 sp=0xc0004a37c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a37e8 sp=0xc0004a37e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 49 gp=0xc000203dc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a3f38 sp=0xc0004a3f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a3fc8 sp=0xc0004a3f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a3fe0 sp=0xc0004a3fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a3fe8 sp=0xc0004a3fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 66 gp=0xc000218000 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021e738 sp=0xc00021e718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021e7c8 sp=0xc00021e738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021e7e0 sp=0xc00021e7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021e7e8 sp=0xc00021e7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 67 gp=0xc0002181c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021ef38 sp=0xc00021ef18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021efc8 sp=0xc00021ef38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021efe0 sp=0xc00021efc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021efe8 sp=0xc00021efe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 68 gp=0xc000218380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021f738 sp=0xc00021f718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021f7c8 sp=0xc00021f738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021f7e0 sp=0xc00021f7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021f7e8 sp=0xc00021f7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 69 gp=0xc000218540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021ff38 sp=0xc00021ff18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021ffc8 sp=0xc00021ff38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021ffe0 sp=0xc00021ffc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021ffe8 sp=0xc00021ffe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 70 gp=0xc000218700 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000220738 sp=0xc000220718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0002207c8 sp=0xc000220738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0002207e0 sp=0xc0002207c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0002207e8 sp=0xc0002207e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 82 gp=0xc000505c00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021a738 sp=0xc00021a718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021a7c8 sp=0xc00021a738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021a7e0 sp=0xc00021a7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021a7e8 sp=0xc00021a7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 98 gp=0xc00049f880 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a7f38 sp=0xc0004a7f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a7fc8 sp=0xc0004a7f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a7fe0 sp=0xc0004a7fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a7fe8 sp=0xc0004a7fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 71 gp=0xc0002188c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000220f38 sp=0xc000220f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000220fc8 sp=0xc000220f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000220fe0 sp=0xc000220fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000220fe8 sp=0xc000220fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 99 gp=0xc00049fa40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004ac738 sp=0xc0004ac718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004ac7c8 sp=0xc0004ac738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004ac7e0 sp=0xc0004ac7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ac7e8 sp=0xc0004ac7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 100 gp=0xc00049fc00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004acf38 sp=0xc0004acf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004acfc8 sp=0xc0004acf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004acfe0 sp=0xc0004acfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004acfe8 sp=0xc0004acfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 101 gp=0xc00049fdc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004ad738 sp=0xc0004ad718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004ad7c8 sp=0xc0004ad738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004ad7e0 sp=0xc0004ad7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ad7e8 sp=0xc0004ad7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 83 gp=0xc000505dc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021af38 sp=0xc00021af18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021afc8 sp=0xc00021af38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021afe0 sp=0xc00021afc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021afe8 sp=0xc00021afe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 102 gp=0xc0004b0000 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004adf38 sp=0xc0004adf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004adfc8 sp=0xc0004adf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004adfe0 sp=0xc0004adfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004adfe8 sp=0xc0004adfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 103 gp=0xc0004b01c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004ae738 sp=0xc0004ae718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004ae7c8 sp=0xc0004ae738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004ae7e0 sp=0xc0004ae7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ae7e8 sp=0xc0004ae7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 104 gp=0xc0004b0380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004aef38 sp=0xc0004aef18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004aefc8 sp=0xc0004aef38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004aefe0 sp=0xc0004aefc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aefe8 sp=0xc0004aefe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 105 gp=0xc0004b0540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004af738 sp=0xc0004af718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004af7c8 sp=0xc0004af738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004af7e0 sp=0xc0004af7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004af7e8 sp=0xc0004af7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 106 gp=0xc0004b0700 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004aff38 sp=0xc0004aff18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004affc8 sp=0xc0004aff38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004affe0 sp=0xc0004affc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004affe8 sp=0xc0004affe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 107 gp=0xc0004b08c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a8738 sp=0xc0004a8718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a87c8 sp=0xc0004a8738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a87e0 sp=0xc0004a87c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a87e8 sp=0xc0004a87e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 108 gp=0xc0004b0a80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a8f38 sp=0xc0004a8f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a8fc8 sp=0xc0004a8f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a8fe0 sp=0xc0004a8fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a8fe8 sp=0xc0004a8fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 109 gp=0xc0004b0c40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a9738 sp=0xc0004a9718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a97c8 sp=0xc0004a9738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a97e0 sp=0xc0004a97c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a97e8 sp=0xc0004a97e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 110 gp=0xc0004b0e00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004a9f38 sp=0xc0004a9f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004a9fc8 sp=0xc0004a9f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004a9fe0 sp=0xc0004a9fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a9fe8 sp=0xc0004a9fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 111 gp=0xc0004b0fc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004aa738 sp=0xc0004aa718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004aa7c8 sp=0xc0004aa738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004aa7e0 sp=0xc0004aa7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aa7e8 sp=0xc0004aa7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 112 gp=0xc0004b1180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004aaf38 sp=0xc0004aaf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004aafc8 sp=0xc0004aaf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004aafe0 sp=0xc0004aafc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aafe8 sp=0xc0004aafe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 113 gp=0xc0004b1340 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004ab738 sp=0xc0004ab718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004ab7c8 sp=0xc0004ab738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004ab7e0 sp=0xc0004ab7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ab7e8 sp=0xc0004ab7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 114 gp=0xc0004b1500 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004abf38 sp=0xc0004abf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004abfc8 sp=0xc0004abf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004abfe0 sp=0xc0004abfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004abfe8 sp=0xc0004abfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 115 gp=0xc0004b16c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b6738 sp=0xc0004b6718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b67c8 sp=0xc0004b6738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b67e0 sp=0xc0004b67c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b67e8 sp=0xc0004b67e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 116 gp=0xc0004b1880 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b6f38 sp=0xc0004b6f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b6fc8 sp=0xc0004b6f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b6fe0 sp=0xc0004b6fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b6fe8 sp=0xc0004b6fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 117 gp=0xc0004b1a40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b7738 sp=0xc0004b7718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b77c8 sp=0xc0004b7738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b77e0 sp=0xc0004b77c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b77e8 sp=0xc0004b77e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 118 gp=0xc0004b1c00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b7f38 sp=0xc0004b7f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b7fc8 sp=0xc0004b7f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b7fe0 sp=0xc0004b7fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b7fe8 sp=0xc0004b7fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 119 gp=0xc0004b1dc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b8738 sp=0xc0004b8718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b87c8 sp=0xc0004b8738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b87e0 sp=0xc0004b87c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b87e8 sp=0xc0004b87e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 120 gp=0xc0004ba000 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b8f38 sp=0xc0004b8f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b8fc8 sp=0xc0004b8f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b8fe0 sp=0xc0004b8fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b8fe8 sp=0xc0004b8fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 121 gp=0xc0004ba1c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b9738 sp=0xc0004b9718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b97c8 sp=0xc0004b9738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b97e0 sp=0xc0004b97c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b97e8 sp=0xc0004b97e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 122 gp=0xc0004ba380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b9f38 sp=0xc0004b9f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b9fc8 sp=0xc0004b9f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b9fe0 sp=0xc0004b9fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b9fe8 sp=0xc0004b9fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 123 gp=0xc0004ba540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b2738 sp=0xc0004b2718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b27c8 sp=0xc0004b2738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b27e0 sp=0xc0004b27c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b27e8 sp=0xc0004b27e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 124 gp=0xc0004ba700 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b2f38 sp=0xc0004b2f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b2fc8 sp=0xc0004b2f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b2fe0 sp=0xc0004b2fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b2fe8 sp=0xc0004b2fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 125 gp=0xc0004ba8c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b3738 sp=0xc0004b3718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b37c8 sp=0xc0004b3738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b37e0 sp=0xc0004b37c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b37e8 sp=0xc0004b37e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 126 gp=0xc0004baa80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b3f38 sp=0xc0004b3f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b3fc8 sp=0xc0004b3f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b3fe0 sp=0xc0004b3fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b3fe8 sp=0xc0004b3fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 127 gp=0xc0004bac40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b4738 sp=0xc0004b4718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b47c8 sp=0xc0004b4738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b47e0 sp=0xc0004b47c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b47e8 sp=0xc0004b47e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 128 gp=0xc0004bae00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b4f38 sp=0xc0004b4f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b4fc8 sp=0xc0004b4f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b4fe0 sp=0xc0004b4fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b4fe8 sp=0xc0004b4fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 129 gp=0xc0004bafc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b5738 sp=0xc0004b5718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b57c8 sp=0xc0004b5738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b57e0 sp=0xc0004b57c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b57e8 sp=0xc0004b57e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 130 gp=0xc0004bb180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004b5f38 sp=0xc0004b5f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004b5fc8 sp=0xc0004b5f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004b5fe0 sp=0xc0004b5fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b5fe8 sp=0xc0004b5fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 131 gp=0xc0004bb340 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c0738 sp=0xc0004c0718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c07c8 sp=0xc0004c0738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c07e0 sp=0xc0004c07c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c07e8 sp=0xc0004c07e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 132 gp=0xc0004bb500 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c0f38 sp=0xc0004c0f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c0fc8 sp=0xc0004c0f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c0fe0 sp=0xc0004c0fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c0fe8 sp=0xc0004c0fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 133 gp=0xc0004bb6c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c1738 sp=0xc0004c1718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c17c8 sp=0xc0004c1738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c17e0 sp=0xc0004c17c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c17e8 sp=0xc0004c17e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 134 gp=0xc0004bb880 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c1f38 sp=0xc0004c1f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c1fc8 sp=0xc0004c1f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c1fe0 sp=0xc0004c1fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c1fe8 sp=0xc0004c1fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 135 gp=0xc0004bba40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c2738 sp=0xc0004c2718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c27c8 sp=0xc0004c2738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c27e0 sp=0xc0004c27c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c27e8 sp=0xc0004c27e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 136 gp=0xc0004bbc00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c2f38 sp=0xc0004c2f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c2fc8 sp=0xc0004c2f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c2fe0 sp=0xc0004c2fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c2fe8 sp=0xc0004c2fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 137 gp=0xc0004bbdc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c3738 sp=0xc0004c3718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c37c8 sp=0xc0004c3738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c37e0 sp=0xc0004c37c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c37e8 sp=0xc0004c37e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 138 gp=0xc0004c4000 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c3f38 sp=0xc0004c3f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c3fc8 sp=0xc0004c3f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c3fe0 sp=0xc0004c3fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c3fe8 sp=0xc0004c3fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 139 gp=0xc0004c41c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004bc738 sp=0xc0004bc718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004bc7c8 sp=0xc0004bc738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004bc7e0 sp=0xc0004bc7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bc7e8 sp=0xc0004bc7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 140 gp=0xc0004c4380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004bcf38 sp=0xc0004bcf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004bcfc8 sp=0xc0004bcf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004bcfe0 sp=0xc0004bcfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bcfe8 sp=0xc0004bcfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 141 gp=0xc0004c4540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004bd738 sp=0xc0004bd718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004bd7c8 sp=0xc0004bd738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004bd7e0 sp=0xc0004bd7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bd7e8 sp=0xc0004bd7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 142 gp=0xc0004c4700 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004bdf38 sp=0xc0004bdf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004bdfc8 sp=0xc0004bdf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004bdfe0 sp=0xc0004bdfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bdfe8 sp=0xc0004bdfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 143 gp=0xc0004c48c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004be738 sp=0xc0004be718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004be7c8 sp=0xc0004be738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004be7e0 sp=0xc0004be7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004be7e8 sp=0xc0004be7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 144 gp=0xc0004c4a80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004bef38 sp=0xc0004bef18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004befc8 sp=0xc0004bef38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004befe0 sp=0xc0004befc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004befe8 sp=0xc0004befe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 145 gp=0xc0004c4c40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004bf738 sp=0xc0004bf718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004bf7c8 sp=0xc0004bf738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004bf7e0 sp=0xc0004bf7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bf7e8 sp=0xc0004bf7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 146 gp=0xc0004c4e00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004bff38 sp=0xc0004bff18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004bffc8 sp=0xc0004bff38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004bffe0 sp=0xc0004bffc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bffe8 sp=0xc0004bffe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 147 gp=0xc0004c4fc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004ca738 sp=0xc0004ca718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004ca7c8 sp=0xc0004ca738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004ca7e0 sp=0xc0004ca7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ca7e8 sp=0xc0004ca7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 148 gp=0xc0004c5180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004caf38 sp=0xc0004caf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004cafc8 sp=0xc0004caf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004cafe0 sp=0xc0004cafc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004cafe8 sp=0xc0004cafe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 72 gp=0xc000218a80 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000221738 sp=0xc000221718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0002217c8 sp=0xc000221738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0002217e0 sp=0xc0002217c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0002217e8 sp=0xc0002217e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 73 gp=0xc000218c40 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc000221f38 sp=0xc000221f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc000221fc8 sp=0xc000221f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc000221fe0 sp=0xc000221fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000221fe8 sp=0xc000221fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 84 gp=0xc000510000 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021b738 sp=0xc00021b718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021b7c8 sp=0xc00021b738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021b7e0 sp=0xc00021b7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021b7e8 sp=0xc00021b7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 85 gp=0xc0005101c0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021bf38 sp=0xc00021bf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021bfc8 sp=0xc00021bf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021bfe0 sp=0xc00021bfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021bfe8 sp=0xc00021bfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 86 gp=0xc000510380 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021c738 sp=0xc00021c718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021c7c8 sp=0xc00021c738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021c7e0 sp=0xc00021c7c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021c7e8 sp=0xc00021c7e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 87 gp=0xc000510540 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609cd4dd?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00021cf38 sp=0xc00021cf18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc00021cfc8 sp=0xc00021cf38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc00021cfe0 sp=0xc00021cfc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00021cfe8 sp=0xc00021cfe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 74 gp=0xc000218e00 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609b974f?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c6738 sp=0xc0004c6718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c67c8 sp=0xc0004c6738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c67e0 sp=0xc0004c67c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c67e8 sp=0xc0004c67e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 75 gp=0xc000218fc0 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x64c8264ba100?, 0x1?, 0xff?, 0x30?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c6f38 sp=0xc0004c6f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c6fc8 sp=0xc0004c6f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c6fe0 sp=0xc0004c6fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c6fe8 sp=0xc0004c6fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 76 gp=0xc000219180 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x64c8264ba100?, 0x1?, 0xda?, 0x8d?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c7738 sp=0xc0004c7718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c77c8 sp=0xc0004c7738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c77e0 sp=0xc0004c77c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c77e8 sp=0xc0004c77e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 77 gp=0xc000219340 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609beabf?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c7f38 sp=0xc0004c7f18 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c7fc8 sp=0xc0004c7f38 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c7fe0 sp=0xc0004c7fc8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c7fe8 sp=0xc0004c7fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 78 gp=0xc000219500 m=nil [GC worker (idle)]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609b3c5a?, 0x0?, 0x0?, 0x0?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c8738 sp=0xc0004c8718 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1423 +0xe9 fp=0xc0004c87c8 sp=0xc0004c8738 pc=0x64c8248b9089
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1()
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x25 fp=0xc0004c87e0 sp=0xc0004c87c8 pc=0x64c8248b8f65
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c87e8 sp=0xc0004c87e0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/mgc.go:1339 +0x105
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 150 gp=0xc0005116c0 m=nil [sync.WaitGroup.Wait]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0xa0?, 0x5?, 0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc0004c9e18 sp=0xc0004c9df8 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:441
mar 15 11:39:07 acquario3 ollama[87551]: runtime.semacquire1(0xc0003d26c8, 0x0, 0x1, 0x0, 0x18)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/sema.go:188 +0x229 fp=0xc0004c9e80 sp=0xc0004c9e18 pc=0x64c8248eb249
mar 15 11:39:07 acquario3 ollama[87551]: sync.runtime_SemacquireWaitGroup(0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/sema.go:110 +0x25 fp=0xc0004c9eb8 sp=0xc0004c9e80 pc=0x64c82490d285
mar 15 11:39:07 acquario3 ollama[87551]: sync.(*WaitGroup).Wait(0x0?)
mar 15 11:39:07 acquario3 ollama[87551]:         sync/waitgroup.go:118 +0x48 fp=0xc0004c9ee0 sp=0xc0004c9eb8 pc=0x64c82491ea08
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0003d26c0, {0x64c825bbb7a0, 0xc000616d20})
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/llamarunner/runner.go:316 +0x47 fp=0xc0004c9fb8 sp=0xc0004c9ee0 pc=0x64c824ca9a67
mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2()
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0x28 fp=0xc0004c9fe0 sp=0xc0004c9fb8 pc=0x64c824cae588
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c9fe8 sp=0xc0004c9fe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0xd97
mar 15 11:39:07 acquario3 ollama[87551]: goroutine 151 gp=0xc000511880 m=nil [IO wait]:
mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x64c824995505?, 0xc000619900?, 0x40?, 0xfa?, 0xb?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/proc.go:435 +0xce fp=0xc00029f948 sp=0xc00029f928 pc=0x64c82490b86e
mar 15 11:39:07 acquario3 ollama[87551]: runtime.netpollblock(0x64c82492ecf8?, 0x248a51a6?, 0xc8?)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/netpoll.go:575 +0xf7 fp=0xc00029f980 sp=0xc00029f948 pc=0x64c8248d0677
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.runtime_pollWait(0x7e77302a4d58, 0x72)
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/netpoll.go:351 +0x85 fp=0xc00029f9a0 sp=0xc00029f980 pc=0x64c82490aa85
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).wait(0xc000619900?, 0xc00035f000?, 0x0)
mar 15 11:39:07 acquario3 ollama[87551]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00029f9c8 sp=0xc00029f9a0 pc=0x64c824991f07
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).waitRead(...)
mar 15 11:39:07 acquario3 ollama[87551]:         internal/poll/fd_poll_runtime.go:89
mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*FD).Read(0xc000619900, {0xc00035f000, 0x1000, 0x1000})
mar 15 11:39:07 acquario3 ollama[87551]:         internal/poll/fd_unix.go:165 +0x27a fp=0xc00029fa60 sp=0xc00029f9c8 pc=0x64c8249931fa
mar 15 11:39:07 acquario3 ollama[87551]: net.(*netFD).Read(0xc000619900, {0xc00035f000?, 0xc00029fad0?, 0x64c8249923c5?})
mar 15 11:39:07 acquario3 ollama[87551]:         net/fd_posix.go:55 +0x25 fp=0xc00029faa8 sp=0xc00029fa60 pc=0x64c824a077a5
mar 15 11:39:07 acquario3 ollama[87551]: net.(*conn).Read(0xc000232720, {0xc00035f000?, 0x0?, 0x0?})
mar 15 11:39:07 acquario3 ollama[87551]:         net/net.go:194 +0x45 fp=0xc00029faf0 sp=0xc00029faa8 pc=0x64c824a15b65
mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*connReader).Read(0xc00064aff0, {0xc00035f000, 0x1000, 0x1000})
mar 15 11:39:07 acquario3 ollama[87551]:         net/http/server.go:798 +0x159 fp=0xc00029fb40 sp=0xc00029faf0 pc=0x64c824c015d9
mar 15 11:39:07 acquario3 ollama[87551]: bufio.(*Reader).fill(0xc000210600)
mar 15 11:39:07 acquario3 ollama[87551]:         bufio/bufio.go:113 +0x103 fp=0xc00029fb78 sp=0xc00029fb40 pc=0x64c824a2d303
mar 15 11:39:07 acquario3 ollama[87551]: bufio.(*Reader).Peek(0xc000210600, 0x4)
mar 15 11:39:07 acquario3 ollama[87551]:         bufio/bufio.go:152 +0x53 fp=0xc00029fb98 sp=0xc00029fb78 pc=0x64c824a2d433
mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*conn).serve(0xc0003d2750, {0x64c825bbb768, 0xc000514360})
mar 15 11:39:07 acquario3 ollama[87551]:         net/http/server.go:2137 +0x785 fp=0xc00029ffb8 sp=0xc00029fb98 pc=0x64c824c073c5
mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*Server).Serve.gowrap3()
mar 15 11:39:07 acquario3 ollama[87551]:         net/http/server.go:3454 +0x28 fp=0xc00029ffe0 sp=0xc00029ffb8 pc=0x64c824c0cb28
mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({})
mar 15 11:39:07 acquario3 ollama[87551]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00029ffe8 sp=0xc00029ffe0 pc=0x64c824912fa1
mar 15 11:39:07 acquario3 ollama[87551]: created by net/http.(*Server).Serve in goroutine 1
mar 15 11:39:07 acquario3 ollama[87551]:         net/http/server.go:3454 +0x485
mar 15 11:39:07 acquario3 ollama[87551]: rax    0x0
mar 15 11:39:07 acquario3 ollama[87551]: rbx    0x7e7730677400
mar 15 11:39:07 acquario3 ollama[87551]: rcx    0x7e77300969fc
mar 15 11:39:07 acquario3 ollama[87551]: rdx    0x6
mar 15 11:39:07 acquario3 ollama[87551]: rdi    0x521b1
mar 15 11:39:07 acquario3 ollama[87551]: rsi    0x521b1
mar 15 11:39:07 acquario3 ollama[87551]: rbp    0x521b1
mar 15 11:39:07 acquario3 ollama[87551]: rsp    0x7ffc0a89c730
mar 15 11:39:07 acquario3 ollama[87551]: r8     0x7ffc0a89c800
mar 15 11:39:07 acquario3 ollama[87551]: r9     0x7ffc0a89c7d0
mar 15 11:39:07 acquario3 ollama[87551]: r10    0x8
mar 15 11:39:07 acquario3 ollama[87551]: r11    0x246
mar 15 11:39:07 acquario3 ollama[87551]: r12    0x6
mar 15 11:39:07 acquario3 ollama[87551]: r13    0x16
mar 15 11:39:07 acquario3 ollama[87551]: r14    0x7e76e049242e
mar 15 11:39:07 acquario3 ollama[87551]: r15    0x64c82825cbc8
mar 15 11:39:07 acquario3 ollama[87551]: rip    0x7e77300969fc
mar 15 11:39:07 acquario3 ollama[87551]: rflags 0x246
mar 15 11:39:07 acquario3 ollama[87551]: cs     0x33
mar 15 11:39:07 acquario3 ollama[87551]: fs     0x0
mar 15 11:39:07 acquario3 ollama[87551]: gs     0x0
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.733+01:00 level=ERROR source=server.go:421 msg="llama runner terminated" error="exit status 2"
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.910+01:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: CUDA error: out of memory\n  current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898\n  cudaMemGetInfo(free, total)\n//ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error"
mar 15 11:39:07 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:07 | 500 |  1.086408297s |      172.19.0.5 | POST     "/api/chat"
mar 15 11:39:08 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:08.173+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:08 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:08.694+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:08 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:08.957+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.212+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.466+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.726+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.985+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:10 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:10.246+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:10 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:10.503+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:10 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:10.756+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.014+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.269+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.524+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.777+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.030+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.285+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.541+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.804+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:13 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:13.060+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:13 acquario3 ollama[87551]: time=2025-03-15T11:39:13.060+01:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.149805431 model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48
mar 15 11:39:13 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:13.322+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:13 acquario3 ollama[87551]: time=2025-03-15T11:39:13.322+01:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.411542305 model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48
mar 15 11:39:13 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:13.586+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:13 acquario3 ollama[87551]: time=2025-03-15T11:39:13.586+01:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.675742087 model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48
mar 15 11:39:22 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:22.578+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:23 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:23.142+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:23 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:23.422+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.439+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.key_length default=128
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.439+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.value_length default=128
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.439+01:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 gpu=GPU-8d08743b-a730-6035-e5ed-9d2a4bb7d987 parallel=4 available=50749964288 required="11.5 GiB"
mar 15 11:39:23 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:23.724+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory"
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.724+01:00 level=INFO source=server.go:97 msg="system memory" total="503.5 GiB" free="431.6 GiB" free_swap="61.3 GiB"
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.key_length default=128
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.value_length default=128
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=server.go:130 msg=offload library=cuda layers.requested=-1 layers.model=41 layers.offload=41 layers.split="" memory.available="[47.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.5 GiB" memory.required.partial="11.5 GiB" memory.required.kv="1.6 GiB" memory.required.allocations="[11.5 GiB]" memory.weights.total="9.3 GiB" memory.weights.repeating="8.9 GiB" memory.weights.nonrepeating="402.0 MiB" memory.graph.full="1.0 GiB" memory.graph.partial="1.0 GiB"
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 --ctx-size 8192 --batch-size 512 --n-gpu-layers 41 --threads 64 --parallel 4 --port 35965"
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=1
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.726+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.742+01:00 level=INFO source=runner.go:931 msg="starting go runner"
mar 15 11:39:23 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
mar 15 11:39:23 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
mar 15 11:39:23 acquario3 ollama[87551]: ggml_cuda_init: found 1 CUDA devices:
mar 15 11:39:23 acquario3 ollama[87551]:   Device 0: NVIDIA RTX A6000, compute capability 8.6, VMM: yes
mar 15 11:39:23 acquario3 ollama[87551]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
mar 15 11:39:23 acquario3 ollama[87551]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.806+01:00 level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 500,600,610,700,750,800,860,870,890,900,1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=64
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.806+01:00 level=INFO source=runner.go:992 msg="Server listening on 127.0.0.1:35965"
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA RTX A6000) - 48398 MiB free
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: loaded meta data with 33 key-value pairs and 243 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 (version GGUF V3 (latest))
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   0:                       general.architecture str              = phi3
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   1:                               general.type str              = model
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   2:                               general.name str              = Phi 4
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   3:                            general.version str              = 4
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   4:                       general.organization str              = Microsoft
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   5:                           general.basename str              = phi
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   6:                         general.size_label str              = 15B
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   7:                            general.license str              = mit
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   8:                       general.license.link str              = https://huggingface.co/microsoft/phi-...
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv   9:                               general.tags arr[str,7]       = ["phi", "nlp", "math", "code", "chat"...
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  10:                          general.languages arr[str,1]       = ["en"]
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  11:                        phi3.context_length u32              = 16384
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  12:  phi3.rope.scaling.original_context_length u32              = 16384
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  13:                      phi3.embedding_length u32              = 5120
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  14:                   phi3.feed_forward_length u32              = 17920
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  15:                           phi3.block_count u32              = 40
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  16:                  phi3.attention.head_count u32              = 40
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  17:               phi3.attention.head_count_kv u32              = 10
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  18:      phi3.attention.layer_norm_rms_epsilon f32              = 0.000010
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  19:                  phi3.rope.dimension_count u32              = 128
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  20:                        phi3.rope.freq_base f32              = 250000.000000
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  21:                          general.file_type u32              = 15
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  22:              phi3.attention.sliding_window u32              = 131072
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = dbrx
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,100352]  = ["!", "\"", "#", "$", "%", "&", "'", ...
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,100352]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,100000]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 100257
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 100257
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  30:            tokenizer.ggml.padding_token_id u32              = 100257
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  31:                    tokenizer.chat_template str              = {% for message in messages %}{% if (m...
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv  32:               general.quantization_version u32              = 2
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type  f32:   81 tensors
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type q4_K:  101 tensors
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type q5_K:   40 tensors
mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type q6_K:   21 tensors
mar 15 11:39:23 acquario3 ollama[87551]: print_info: file format = GGUF V3 (latest)
mar 15 11:39:23 acquario3 ollama[87551]: print_info: file type   = Q4_K - Medium
mar 15 11:39:23 acquario3 ollama[87551]: print_info: file size   = 8.43 GiB (4.94 BPW)
mar 15 11:39:23 acquario3 ollama[87551]: load: special tokens cache size = 96
mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.978+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
mar 15 11:39:23 acquario3 ollama[87551]: load: token to piece cache size = 0.6151 MB
mar 15 11:39:23 acquario3 ollama[87551]: print_info: arch             = phi3
mar 15 11:39:23 acquario3 ollama[87551]: print_info: vocab_only       = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_ctx_train      = 16384
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd           = 5120
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_layer          = 40
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_head           = 40
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_head_kv        = 10
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_rot            = 128
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_swa            = 131072
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_head_k    = 128
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_head_v    = 128
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_gqa            = 4
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_k_gqa     = 1280
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_v_gqa     = 1280
mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_norm_eps       = 0.0e+00
mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_norm_rms_eps   = 1.0e-05
mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_clamp_kqv      = 0.0e+00
mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_max_alibi_bias = 0.0e+00
mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_logit_scale    = 0.0e+00
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_ff             = 17920
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_expert         = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_expert_used    = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: causal attn      = 1
mar 15 11:39:23 acquario3 ollama[87551]: print_info: pooling type     = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: rope type        = 2
mar 15 11:39:23 acquario3 ollama[87551]: print_info: rope scaling     = linear
mar 15 11:39:23 acquario3 ollama[87551]: print_info: freq_base_train  = 250000.0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: freq_scale_train = 1
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_ctx_orig_yarn  = 16384
mar 15 11:39:23 acquario3 ollama[87551]: print_info: rope_finetuned   = unknown
mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_d_conv       = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_d_inner      = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_d_state      = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_dt_rank      = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_dt_b_c_rms   = 0
mar 15 11:39:23 acquario3 ollama[87551]: print_info: model type       = 14B
mar 15 11:39:23 acquario3 ollama[87551]: print_info: model params     = 14.66 B
mar 15 11:39:23 acquario3 ollama[87551]: print_info: general.name     = Phi 4
mar 15 11:39:23 acquario3 ollama[87551]: print_info: vocab type       = BPE
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_vocab          = 100352
mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_merges         = 100000
mar 15 11:39:23 acquario3 ollama[87551]: print_info: BOS token        = 100257 '<|endoftext|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOS token        = 100257 '<|endoftext|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOT token        = 100265 '<|im_end|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: PAD token        = 100257 '<|endoftext|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: LF token         = 198 'Ċ'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: FIM PRE token    = 100258 '<|fim_prefix|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: FIM SUF token    = 100260 '<|fim_suffix|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: FIM MID token    = 100259 '<|fim_middle|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOG token        = 100257 '<|endoftext|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOG token        = 100265 '<|im_end|>'
mar 15 11:39:23 acquario3 ollama[87551]: print_info: max token length = 256
mar 15 11:39:23 acquario3 ollama[87551]: load_tensors: loading model tensors, this can take a while... (mmap = true)
mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: offloading 40 repeating layers to GPU
mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: offloading output layer to GPU
mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: offloaded 41/41 layers to GPU
mar 15 11:39:24 acquario3 ollama[87551]: load_tensors:        CUDA0 model buffer size =  8354.71 MiB
mar 15 11:39:24 acquario3 ollama[87551]: load_tensors:   CPU_Mapped model buffer size =   275.62 MiB
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_seq_max     = 4
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ctx         = 8192
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ctx_per_seq = 2048
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_batch       = 2048
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ubatch      = 512
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: flash_attn    = 0
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: freq_base     = 250000.0
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: freq_scale    = 1
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (16384) -- the full capacity of the model will not be utilized
mar 15 11:39:25 acquario3 ollama[87551]: llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 40, can_shift = 1
mar 15 11:39:25 acquario3 ollama[87551]: llama_kv_cache_init:      CUDA0 KV buffer size =  1600.00 MiB
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: KV self size  = 1600.00 MiB, K (f16):  800.00 MiB, V (f16):  800.00 MiB
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model:  CUDA_Host  output buffer size =     1.61 MiB
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model:      CUDA0 compute buffer size =   701.00 MiB
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model:  CUDA_Host compute buffer size =    26.01 MiB
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: graph nodes  = 1606
mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: graph splits = 2
mar 15 11:39:25 acquario3 ollama[87551]: time=2025-03-15T11:39:25.484+01:00 level=INFO source=server.go:596 msg="llama runner started in 1.76 seconds"
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: loaded meta data with 33 key-value pairs and 243 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 (version GGUF V3 (latest))
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   0:                       general.architecture str              = phi3
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   1:                               general.type str              = model
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   2:                               general.name str              = Phi 4
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   3:                            general.version str              = 4
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   4:                       general.organization str              = Microsoft
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   5:                           general.basename str              = phi
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   6:                         general.size_label str              = 15B
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   7:                            general.license str              = mit
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   8:                       general.license.link str              = https://huggingface.co/microsoft/phi-...
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv   9:                               general.tags arr[str,7]       = ["phi", "nlp", "math", "code", "chat"...
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  10:                          general.languages arr[str,1]       = ["en"]
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  11:                        phi3.context_length u32              = 16384
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  12:  phi3.rope.scaling.original_context_length u32              = 16384
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  13:                      phi3.embedding_length u32              = 5120
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  14:                   phi3.feed_forward_length u32              = 17920
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  15:                           phi3.block_count u32              = 40
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  16:                  phi3.attention.head_count u32              = 40
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  17:               phi3.attention.head_count_kv u32              = 10
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  18:      phi3.attention.layer_norm_rms_epsilon f32              = 0.000010
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  19:                  phi3.rope.dimension_count u32              = 128
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  20:                        phi3.rope.freq_base f32              = 250000.000000
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  21:                          general.file_type u32              = 15
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  22:              phi3.attention.sliding_window u32              = 131072
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = dbrx
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,100352]  = ["!", "\"", "#", "$", "%", "&", "'", ...
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,100352]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,100000]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 100257
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 100257
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  30:            tokenizer.ggml.padding_token_id u32              = 100257
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  31:                    tokenizer.chat_template str              = {% for message in messages %}{% if (m...
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv  32:               general.quantization_version u32              = 2
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type  f32:   81 tensors
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type q4_K:  101 tensors
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type q5_K:   40 tensors
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type q6_K:   21 tensors
mar 15 11:39:25 acquario3 ollama[87551]: print_info: file format = GGUF V3 (latest)
mar 15 11:39:25 acquario3 ollama[87551]: print_info: file type   = Q4_K - Medium
mar 15 11:39:25 acquario3 ollama[87551]: print_info: file size   = 8.43 GiB (4.94 BPW)
mar 15 11:39:25 acquario3 ollama[87551]: load: special tokens cache size = 96
mar 15 11:39:25 acquario3 ollama[87551]: load: token to piece cache size = 0.6151 MB
mar 15 11:39:25 acquario3 ollama[87551]: print_info: arch             = phi3
mar 15 11:39:25 acquario3 ollama[87551]: print_info: vocab_only       = 1
mar 15 11:39:25 acquario3 ollama[87551]: print_info: model type       = ?B
mar 15 11:39:25 acquario3 ollama[87551]: print_info: model params     = 14.66 B
mar 15 11:39:25 acquario3 ollama[87551]: print_info: general.name     = Phi 4
mar 15 11:39:25 acquario3 ollama[87551]: print_info: vocab type       = BPE
mar 15 11:39:25 acquario3 ollama[87551]: print_info: n_vocab          = 100352
mar 15 11:39:25 acquario3 ollama[87551]: print_info: n_merges         = 100000
mar 15 11:39:25 acquario3 ollama[87551]: print_info: BOS token        = 100257 '<|endoftext|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOS token        = 100257 '<|endoftext|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOT token        = 100265 '<|im_end|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: PAD token        = 100257 '<|endoftext|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: LF token         = 198 'Ċ'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: FIM PRE token    = 100258 '<|fim_prefix|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: FIM SUF token    = 100260 '<|fim_suffix|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: FIM MID token    = 100259 '<|fim_middle|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOG token        = 100257 '<|endoftext|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOG token        = 100265 '<|im_end|>'
mar 15 11:39:25 acquario3 ollama[87551]: print_info: max token length = 256
mar 15 11:39:25 acquario3 ollama[87551]: llama_model_load: vocab only - skipping tensors
mar 15 11:39:26 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:26 | 200 |  4.106908544s |      172.19.0.5 | POST     "/api/chat"
mar 15 11:39:28 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:28 | 200 |  1.580520467s |      172.19.0.5 | POST     "/api/chat"
mar 15 11:39:31 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:31 | 200 |  3.688297873s |      172.19.0.5 | POST     "/api/chat"
<!-- gh-comment-id:2727521637 --> @AlbertoSinigaglia commented on GitHub (Mar 16, 2025): @rick-github here's one of the logs <details> <summary> logs from ollama </summary> ``` mar 15 11:39:07 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:07.109+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.136+01:00 level=INFO source=sched.go:508 msg="updated VRAM based on existing loaded models" gpu=GPU-a1c88671-c53c-a240-0fe5-5e9bd6b67d6e library=cuda total="47.5 GiB" available="38.6 GiB" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=INFO source=sched.go:508 msg="updated VRAM based on existing loaded models" gpu=GPU-8d08743b-a730-6035-e5ed-9d2a4bb7d987 library=cuda total="47.5 GiB" available="36.1 GiB" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=INFO source=sched.go:508 msg="updated VRAM based on existing loaded models" gpu=GPU-f80f1c32-b9ea-b671-ee24-8ed809aed7d1 library=cuda total="47.5 GiB" available="47.2 GiB" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.key_length default=128 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.value_length default=128 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.137+01:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48 gpu=GPU-f80f1c32-b9ea-b671-ee24-8ed809aed7d1 parallel=4 available=50671386624 required="35.3 GiB" mar 15 11:39:07 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:07.407+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:97 msg="system memory" total="503.5 GiB" free="431.4 GiB" free_swap="61.3 GiB" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.key_length default=128 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=WARN source=ggml.go:136 msg="key not found" key=qwen2.attention.value_length default=128 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:130 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[47.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="35.3 GiB" memory.required.partial="35.3 GiB" memory.required.kv="2.0 GiB" memory.required.allocations="[35.3 GiB]" memory.weights.total="32.9 GiB" memory.weights.repeating="32.1 GiB" memory.weights.nonrepeating="788.9 MiB" memory.graph.full="676.0 MiB" memory.graph.partial="916.1 MiB" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48 --ctx-size 8192 --batch-size 512 --n-gpu-layers 65 --threads 64 --parallel 4 --port 34775" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.408+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=2 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.408+01:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.408+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.423+01:00 level=INFO source=runner.go:931 msg="starting go runner" mar 15 11:39:07 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no mar 15 11:39:07 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no mar 15 11:39:07 acquario3 ollama[87551]: ggml_cuda_init: found 1 CUDA devices: mar 15 11:39:07 acquario3 ollama[87551]: Device 0: NVIDIA RTX A6000, compute capability 8.6, VMM: yes mar 15 11:39:07 acquario3 ollama[87551]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so mar 15 11:39:07 acquario3 ollama[87551]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 500,600,610,700,750,800,860,870,890,900,1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=64 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:992 msg="Server listening on 127.0.0.1:34775" mar 15 11:39:07 acquario3 ollama[87551]: CUDA error: out of memory mar 15 11:39:07 acquario3 ollama[87551]: current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898 mar 15 11:39:07 acquario3 ollama[87551]: cudaMemGetInfo(free, total) mar 15 11:39:07 acquario3 ollama[87551]: //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.660+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" mar 15 11:39:07 acquario3 ollama[87551]: Could not attach to process. If your uid matches the uid of the target mar 15 11:39:07 acquario3 ollama[87551]: process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try mar 15 11:39:07 acquario3 ollama[87551]: again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf mar 15 11:39:07 acquario3 ollama[87551]: ptrace: Inappropriate ioctl for device. mar 15 11:39:07 acquario3 ollama[87551]: No stack. mar 15 11:39:07 acquario3 ollama[87551]: The program is not being run. mar 15 11:39:07 acquario3 ollama[87551]: SIGABRT: abort mar 15 11:39:07 acquario3 ollama[87551]: PC=0x7e77300969fc m=0 sigcode=18446744073709551610 mar 15 11:39:07 acquario3 ollama[87551]: signal arrived during cgo execution mar 15 11:39:07 acquario3 ollama[87551]: goroutine 149 gp=0xc000511500 m=0 mp=0x64c82640e7a0 [syscall]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.cgocall(0x64c82555ac30, 0xc00019cc00) mar 15 11:39:07 acquario3 ollama[87551]: runtime/cgocall.go:167 +0x4b fp=0xc00019cbd8 sp=0xc00019cba0 pc=0x64c82490858b mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama._Cfunc_llama_model_load_from_file(0x64c828253680, {0x0, 0x41, 0x1, 0x0, 0x0, 0x64c82555a510, 0xc0005fffd0, 0x0, 0x0, ...}) mar 15 11:39:07 acquario3 ollama[87551]: _cgo_gotypes.go:754 +0x4b fp=0xc00019cc00 sp=0xc00019cbd8 pc=0x64c824c8ef6b mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama.LoadModelFromFile.func1(...) mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama/llama.go:265 mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama.LoadModelFromFile({0x7ffc0a89ebf0, 0x6e}, {0x41, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc0006468b0, ...}) mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/llama/llama.go:265 +0x36b fp=0xc00019cdc8 sp=0xc00019cc00 pc=0x64c824c91aeb mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0003d26c0, {0x41, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc0006468b0, 0x0}, ...) mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner/runner.go:849 +0x9b fp=0xc00019cf10 sp=0xc00019cdc8 pc=0x64c824cacddb mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner/runner.go:966 +0xda fp=0xc00019cfe0 sp=0xc00019cf10 pc=0x64c824cae69a mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00019cfe8 sp=0xc00019cfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner/runner.go:966 +0xcb7 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 1 gp=0xc000002380 m=nil [IO wait]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0002735b8 sp=0xc000273598 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.netpollblock(0xc000273608?, 0x248a51a6?, 0xc8?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/netpoll.go:575 +0xf7 fp=0xc0002735f0 sp=0xc0002735b8 pc=0x64c8248d0677 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.runtime_pollWait(0x7e77302a4e70, 0x72) mar 15 11:39:07 acquario3 ollama[87551]: runtime/netpoll.go:351 +0x85 fp=0xc000273610 sp=0xc0002735f0 pc=0x64c82490aa85 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).wait(0xc00051a000?, 0x900000036?, 0x0) mar 15 11:39:07 acquario3 ollama[87551]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000273638 sp=0xc000273610 pc=0x64c824991f07 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).waitRead(...) mar 15 11:39:07 acquario3 ollama[87551]: internal/poll/fd_poll_runtime.go:89 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*FD).Accept(0xc00051a000) mar 15 11:39:07 acquario3 ollama[87551]: internal/poll/fd_unix.go:620 +0x295 fp=0xc0002736e0 sp=0xc000273638 pc=0x64c8249972d5 mar 15 11:39:07 acquario3 ollama[87551]: net.(*netFD).accept(0xc00051a000) mar 15 11:39:07 acquario3 ollama[87551]: net/fd_unix.go:172 +0x29 fp=0xc000273798 sp=0xc0002736e0 pc=0x64c824a09749 mar 15 11:39:07 acquario3 ollama[87551]: net.(*TCPListener).accept(0xc00052e000) mar 15 11:39:07 acquario3 ollama[87551]: net/tcpsock_posix.go:159 +0x1b fp=0xc0002737e8 sp=0xc000273798 pc=0x64c824a1f0fb mar 15 11:39:07 acquario3 ollama[87551]: net.(*TCPListener).Accept(0xc00052e000) mar 15 11:39:07 acquario3 ollama[87551]: net/tcpsock.go:380 +0x30 fp=0xc000273818 sp=0xc0002737e8 pc=0x64c824a1dfb0 mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*onceCloseListener).Accept(0xc0003d2750?) mar 15 11:39:07 acquario3 ollama[87551]: <autogenerated>:1 +0x24 fp=0xc000273830 sp=0xc000273818 pc=0x64c824c34e64 mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*Server).Serve(0xc00053a000, {0x64c825bb9528, 0xc00052e000}) mar 15 11:39:07 acquario3 ollama[87551]: net/http/server.go:3424 +0x30c fp=0xc000273960 sp=0xc000273830 pc=0x64c824c0c72c mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034120, 0xe, 0xe}) mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner/runner.go:993 +0x116a fp=0xc000273d08 sp=0xc000273960 pc=0x64c824cae2ca mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner.Execute({0xc000034110?, 0x0?, 0x0?}) mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000273d30 sp=0xc000273d08 pc=0x64c824ed89b4 mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000035b00?, {0x64c825738055?, 0x4?, 0x64c825738059?}) mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/cmd/cmd.go:1281 +0x45 fp=0xc000273d58 sp=0xc000273d30 pc=0x64c8254ede45 mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).execute(0xc00064ef08, {0xc0005e15e0, 0xe, 0xe}) mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000273e78 sp=0xc000273d58 pc=0x64c824a829dc mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).ExecuteC(0xc00061c908) mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000273f30 sp=0xc000273e78 pc=0x64c824a83225 mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).Execute(...) mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra@v1.7.0/command.go:992 mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra.(*Command).ExecuteContext(...) mar 15 11:39:07 acquario3 ollama[87551]: github.com/spf13/cobra@v1.7.0/command.go:985 mar 15 11:39:07 acquario3 ollama[87551]: main.main() mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000273f50 sp=0xc000273f30 pc=0x64c8254ee1ad mar 15 11:39:07 acquario3 ollama[87551]: runtime.main() mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:283 +0x29d fp=0xc000273fe0 sp=0xc000273f50 pc=0x64c8248d7c7d mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000273fe8 sp=0xc000273fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018cfa8 sp=0xc00018cf88 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:441 mar 15 11:39:07 acquario3 ollama[87551]: runtime.forcegchelper() mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:348 +0xb8 fp=0xc00018cfe0 sp=0xc00018cfa8 pc=0x64c8248d7fb8 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018cfe8 sp=0xc00018cfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.init.7 in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:336 +0x1a mar 15 11:39:07 acquario3 ollama[87551]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018d780 sp=0xc00018d760 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:441 mar 15 11:39:07 acquario3 ollama[87551]: runtime.bgsweep(0xc000186080) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgcsweep.go:316 +0xdf fp=0xc00018d7c8 sp=0xc00018d780 pc=0x64c8248c27df mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcenable.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:204 +0x25 fp=0xc00018d7e0 sp=0xc00018d7c8 pc=0x64c8248b6bc5 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018d7e8 sp=0xc00018d7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcenable in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:204 +0x66 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x10000?, 0x64c8258ea9d8?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018df78 sp=0xc00018df58 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:441 mar 15 11:39:07 acquario3 ollama[87551]: runtime.(*scavengerState).park(0x64c82640b980) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgcscavenge.go:425 +0x49 fp=0xc00018dfa8 sp=0xc00018df78 pc=0x64c8248c0229 mar 15 11:39:07 acquario3 ollama[87551]: runtime.bgscavenge(0xc000186080) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgcscavenge.go:658 +0x59 fp=0xc00018dfc8 sp=0xc00018dfa8 pc=0x64c8248c07b9 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcenable.gowrap2() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:205 +0x25 fp=0xc00018dfe0 sp=0xc00018dfc8 pc=0x64c8248b6b65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018dfe8 sp=0xc00018dfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcenable in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:205 +0xa5 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc00018c688?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018c630 sp=0xc00018c610 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.runfinq() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mfinal.go:196 +0x107 fp=0xc00018c7e0 sp=0xc00018c630 pc=0x64c8248b5b87 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018c7e8 sp=0xc00018c7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.createfing in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mfinal.go:166 +0x3d mar 15 11:39:07 acquario3 ollama[87551]: goroutine 6 gp=0xc0002ec8c0 m=nil [chan receive]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0xc00033d5e0?, 0xc00023c018?, 0x60?, 0xe7?, 0x64c8249f0488?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018e718 sp=0xc00018e6f8 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.chanrecv(0xc0000403f0, 0x0, 0x1) mar 15 11:39:07 acquario3 ollama[87551]: runtime/chan.go:664 +0x445 fp=0xc00018e790 sp=0xc00018e718 pc=0x64c8248a7d85 mar 15 11:39:07 acquario3 ollama[87551]: runtime.chanrecv1(0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/chan.go:506 +0x12 fp=0xc00018e7b8 sp=0xc00018e790 pc=0x64c8248a7912 mar 15 11:39:07 acquario3 ollama[87551]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1796 mar 15 11:39:07 acquario3 ollama[87551]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1799 +0x2f fp=0xc00018e7e0 sp=0xc00018e7b8 pc=0x64c8248b9d6f mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018e7e8 sp=0xc00018e7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1794 +0x85 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 7 gp=0xc0002eca80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018ef38 sp=0xc00018ef18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00018efc8 sp=0xc00018ef38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00018efe0 sp=0xc00018efc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018efe8 sp=0xc00018efe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 8 gp=0xc0002ecc40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018f738 sp=0xc00018f718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00018f7c8 sp=0xc00018f738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00018f7e0 sp=0xc00018f7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018f7e8 sp=0xc00018f7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 9 gp=0xc0002ece00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018ff38 sp=0xc00018ff18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00018ffc8 sp=0xc00018ff38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00018ffe0 sp=0xc00018ffc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018ffe8 sp=0xc00018ffe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 10 gp=0xc0002ecfc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000188738 sp=0xc000188718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0001887c8 sp=0xc000188738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0001887e0 sp=0xc0001887c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0001887e8 sp=0xc0001887e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 11 gp=0xc0002ed180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000188f38 sp=0xc000188f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000188fc8 sp=0xc000188f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000188fe0 sp=0xc000188fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000188fe8 sp=0xc000188fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 12 gp=0xc0002ed340 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000189738 sp=0xc000189718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0001897c8 sp=0xc000189738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0001897e0 sp=0xc0001897c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0001897e8 sp=0xc0001897e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 13 gp=0xc0002ed500 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000189f38 sp=0xc000189f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000189fc8 sp=0xc000189f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000189fe0 sp=0xc000189fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000189fe8 sp=0xc000189fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 14 gp=0xc0002ed6c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018a738 sp=0xc00018a718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00018a7c8 sp=0xc00018a738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00018a7e0 sp=0xc00018a7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018a7e8 sp=0xc00018a7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 15 gp=0xc0002ed880 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018af38 sp=0xc00018af18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00018afc8 sp=0xc00018af38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00018afe0 sp=0xc00018afc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018afe8 sp=0xc00018afe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 16 gp=0xc0002eda40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018b738 sp=0xc00018b718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00018b7c8 sp=0xc00018b738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00018b7e0 sp=0xc00018b7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018b7e8 sp=0xc00018b7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 18 gp=0xc0002edc00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00018bf38 sp=0xc00018bf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00018bfc8 sp=0xc00018bf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00018bfe0 sp=0xc00018bfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00018bfe8 sp=0xc00018bfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 19 gp=0xc0002eddc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049a738 sp=0xc00049a718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049a7c8 sp=0xc00049a738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049a7e0 sp=0xc00049a7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049a7e8 sp=0xc00049a7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 20 gp=0xc00049e000 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049af38 sp=0xc00049af18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049afc8 sp=0xc00049af38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049afe0 sp=0xc00049afc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049afe8 sp=0xc00049afe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 21 gp=0xc00049e1c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049b738 sp=0xc00049b718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049b7c8 sp=0xc00049b738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049b7e0 sp=0xc00049b7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049b7e8 sp=0xc00049b7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 22 gp=0xc00049e380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049bf38 sp=0xc00049bf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049bfc8 sp=0xc00049bf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049bfe0 sp=0xc00049bfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049bfe8 sp=0xc00049bfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 23 gp=0xc00049e540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049c738 sp=0xc00049c718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049c7c8 sp=0xc00049c738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049c7e0 sp=0xc00049c7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049c7e8 sp=0xc00049c7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 24 gp=0xc00049e700 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049cf38 sp=0xc00049cf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049cfc8 sp=0xc00049cf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049cfe0 sp=0xc00049cfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049cfe8 sp=0xc00049cfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 34 gp=0xc000202380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000496738 sp=0xc000496718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004967c8 sp=0xc000496738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004967e0 sp=0xc0004967c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004967e8 sp=0xc0004967e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 50 gp=0xc000504000 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 51 gp=0xc0005041c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 52 gp=0xc000504380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 53 gp=0xc000504540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 54 gp=0xc000504700 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 55 gp=0xc0005048c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050cf38 sp=0xc00050cf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050cfc8 sp=0xc00050cf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050cfe0 sp=0xc00050cfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050cfe8 sp=0xc00050cfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 56 gp=0xc000504a80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050d738 sp=0xc00050d718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050d7c8 sp=0xc00050d738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050d7e0 sp=0xc00050d7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050d7e8 sp=0xc00050d7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 57 gp=0xc000504c40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00050df38 sp=0xc00050df18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00050dfc8 sp=0xc00050df38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00050dfe0 sp=0xc00050dfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050dfe8 sp=0xc00050dfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 58 gp=0xc000504e00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 59 gp=0xc000504fc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000506f38 sp=0xc000506f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000506fc8 sp=0xc000506f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000506fe0 sp=0xc000506fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000506fe8 sp=0xc000506fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 60 gp=0xc000505180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000507738 sp=0xc000507718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0005077c8 sp=0xc000507738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0005077e0 sp=0xc0005077c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0005077e8 sp=0xc0005077e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 25 gp=0xc00049e8c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049d738 sp=0xc00049d718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049d7c8 sp=0xc00049d738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049d7e0 sp=0xc00049d7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049d7e8 sp=0xc00049d7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 35 gp=0xc000202540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000496f38 sp=0xc000496f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000496fc8 sp=0xc000496f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000496fe0 sp=0xc000496fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000496fe8 sp=0xc000496fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 36 gp=0xc000202700 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000497738 sp=0xc000497718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004977c8 sp=0xc000497738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004977e0 sp=0xc0004977c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004977e8 sp=0xc0004977e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 26 gp=0xc00049ea80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00049df38 sp=0xc00049df18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00049dfc8 sp=0xc00049df38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00049dfe0 sp=0xc00049dfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00049dfe8 sp=0xc00049dfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 61 gp=0xc000505340 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000507f38 sp=0xc000507f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000507fc8 sp=0xc000507f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000507fe0 sp=0xc000507fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000507fe8 sp=0xc000507fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 37 gp=0xc0002028c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000497f38 sp=0xc000497f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000497fc8 sp=0xc000497f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000497fe0 sp=0xc000497fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000497fe8 sp=0xc000497fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 38 gp=0xc000202a80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000498738 sp=0xc000498718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004987c8 sp=0xc000498738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004987e0 sp=0xc0004987c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004987e8 sp=0xc0004987e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 27 gp=0xc00049ec40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a4738 sp=0xc0004a4718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a47c8 sp=0xc0004a4738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a47e0 sp=0xc0004a47c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a47e8 sp=0xc0004a47e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 28 gp=0xc00049ee00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a4f38 sp=0xc0004a4f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a4fc8 sp=0xc0004a4f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a4fe0 sp=0xc0004a4fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a4fe8 sp=0xc0004a4fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 29 gp=0xc00049efc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a5738 sp=0xc0004a5718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a57c8 sp=0xc0004a5738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a57e0 sp=0xc0004a57c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a57e8 sp=0xc0004a57e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 30 gp=0xc00049f180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a5f38 sp=0xc0004a5f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a5fc8 sp=0xc0004a5f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a5fe0 sp=0xc0004a5fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a5fe8 sp=0xc0004a5fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 31 gp=0xc00049f340 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a6738 sp=0xc0004a6718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a67c8 sp=0xc0004a6738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a67e0 sp=0xc0004a67c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a67e8 sp=0xc0004a67e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 32 gp=0xc00049f500 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a6f38 sp=0xc0004a6f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a6fc8 sp=0xc0004a6f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a6fe0 sp=0xc0004a6fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a6fe8 sp=0xc0004a6fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 39 gp=0xc000202c40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000498f38 sp=0xc000498f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000498fc8 sp=0xc000498f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000498fe0 sp=0xc000498fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000498fe8 sp=0xc000498fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 62 gp=0xc000505500 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000508738 sp=0xc000508718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0005087c8 sp=0xc000508738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0005087e0 sp=0xc0005087c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0005087e8 sp=0xc0005087e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 63 gp=0xc0005056c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000508f38 sp=0xc000508f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000508fc8 sp=0xc000508f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000508fe0 sp=0xc000508fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000508fe8 sp=0xc000508fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 64 gp=0xc000505880 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000509738 sp=0xc000509718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0005097c8 sp=0xc000509738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0005097e0 sp=0xc0005097c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0005097e8 sp=0xc0005097e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 65 gp=0xc000505a40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000509f38 sp=0xc000509f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000509fc8 sp=0xc000509f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000509fe0 sp=0xc000509fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000509fe8 sp=0xc000509fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 33 gp=0xc00049f6c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a7738 sp=0xc0004a7718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a77c8 sp=0xc0004a7738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a77e0 sp=0xc0004a77c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a77e8 sp=0xc0004a77e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 40 gp=0xc000202e00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000499738 sp=0xc000499718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004997c8 sp=0xc000499738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004997e0 sp=0xc0004997c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004997e8 sp=0xc0004997e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 41 gp=0xc000202fc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000499f38 sp=0xc000499f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000499fc8 sp=0xc000499f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000499fe0 sp=0xc000499fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000499fe8 sp=0xc000499fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 42 gp=0xc000203180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a0738 sp=0xc0004a0718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a07c8 sp=0xc0004a0738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a07e0 sp=0xc0004a07c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a07e8 sp=0xc0004a07e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 43 gp=0xc000203340 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a0f38 sp=0xc0004a0f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a0fc8 sp=0xc0004a0f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a0fe0 sp=0xc0004a0fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a0fe8 sp=0xc0004a0fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 44 gp=0xc000203500 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a1738 sp=0xc0004a1718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a17c8 sp=0xc0004a1738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a17e0 sp=0xc0004a17c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a17e8 sp=0xc0004a17e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 45 gp=0xc0002036c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a1f38 sp=0xc0004a1f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a1fc8 sp=0xc0004a1f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a1fe0 sp=0xc0004a1fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a1fe8 sp=0xc0004a1fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 46 gp=0xc000203880 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a2738 sp=0xc0004a2718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a27c8 sp=0xc0004a2738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a27e0 sp=0xc0004a27c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a27e8 sp=0xc0004a27e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 47 gp=0xc000203a40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a2f38 sp=0xc0004a2f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a2fc8 sp=0xc0004a2f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a2fe0 sp=0xc0004a2fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a2fe8 sp=0xc0004a2fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 48 gp=0xc000203c00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a3738 sp=0xc0004a3718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a37c8 sp=0xc0004a3738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a37e0 sp=0xc0004a37c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a37e8 sp=0xc0004a37e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 49 gp=0xc000203dc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a3f38 sp=0xc0004a3f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a3fc8 sp=0xc0004a3f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a3fe0 sp=0xc0004a3fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a3fe8 sp=0xc0004a3fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 66 gp=0xc000218000 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021e738 sp=0xc00021e718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021e7c8 sp=0xc00021e738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021e7e0 sp=0xc00021e7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021e7e8 sp=0xc00021e7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 67 gp=0xc0002181c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021ef38 sp=0xc00021ef18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021efc8 sp=0xc00021ef38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021efe0 sp=0xc00021efc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021efe8 sp=0xc00021efe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 68 gp=0xc000218380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021f738 sp=0xc00021f718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021f7c8 sp=0xc00021f738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021f7e0 sp=0xc00021f7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021f7e8 sp=0xc00021f7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 69 gp=0xc000218540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021ff38 sp=0xc00021ff18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021ffc8 sp=0xc00021ff38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021ffe0 sp=0xc00021ffc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021ffe8 sp=0xc00021ffe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 70 gp=0xc000218700 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000220738 sp=0xc000220718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0002207c8 sp=0xc000220738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0002207e0 sp=0xc0002207c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0002207e8 sp=0xc0002207e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 82 gp=0xc000505c00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021a738 sp=0xc00021a718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021a7c8 sp=0xc00021a738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021a7e0 sp=0xc00021a7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021a7e8 sp=0xc00021a7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 98 gp=0xc00049f880 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a7f38 sp=0xc0004a7f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a7fc8 sp=0xc0004a7f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a7fe0 sp=0xc0004a7fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a7fe8 sp=0xc0004a7fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 71 gp=0xc0002188c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000220f38 sp=0xc000220f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000220fc8 sp=0xc000220f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000220fe0 sp=0xc000220fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000220fe8 sp=0xc000220fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 99 gp=0xc00049fa40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004ac738 sp=0xc0004ac718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004ac7c8 sp=0xc0004ac738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004ac7e0 sp=0xc0004ac7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ac7e8 sp=0xc0004ac7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 100 gp=0xc00049fc00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004acf38 sp=0xc0004acf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004acfc8 sp=0xc0004acf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004acfe0 sp=0xc0004acfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004acfe8 sp=0xc0004acfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 101 gp=0xc00049fdc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004ad738 sp=0xc0004ad718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004ad7c8 sp=0xc0004ad738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004ad7e0 sp=0xc0004ad7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ad7e8 sp=0xc0004ad7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 83 gp=0xc000505dc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021af38 sp=0xc00021af18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021afc8 sp=0xc00021af38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021afe0 sp=0xc00021afc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021afe8 sp=0xc00021afe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 102 gp=0xc0004b0000 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004adf38 sp=0xc0004adf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004adfc8 sp=0xc0004adf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004adfe0 sp=0xc0004adfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004adfe8 sp=0xc0004adfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 103 gp=0xc0004b01c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004ae738 sp=0xc0004ae718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004ae7c8 sp=0xc0004ae738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004ae7e0 sp=0xc0004ae7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ae7e8 sp=0xc0004ae7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 104 gp=0xc0004b0380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004aef38 sp=0xc0004aef18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004aefc8 sp=0xc0004aef38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004aefe0 sp=0xc0004aefc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aefe8 sp=0xc0004aefe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 105 gp=0xc0004b0540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004af738 sp=0xc0004af718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004af7c8 sp=0xc0004af738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004af7e0 sp=0xc0004af7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004af7e8 sp=0xc0004af7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 106 gp=0xc0004b0700 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004aff38 sp=0xc0004aff18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004affc8 sp=0xc0004aff38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004affe0 sp=0xc0004affc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004affe8 sp=0xc0004affe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 107 gp=0xc0004b08c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a8738 sp=0xc0004a8718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a87c8 sp=0xc0004a8738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a87e0 sp=0xc0004a87c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a87e8 sp=0xc0004a87e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 108 gp=0xc0004b0a80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a8f38 sp=0xc0004a8f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a8fc8 sp=0xc0004a8f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a8fe0 sp=0xc0004a8fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a8fe8 sp=0xc0004a8fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 109 gp=0xc0004b0c40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a9738 sp=0xc0004a9718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a97c8 sp=0xc0004a9738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a97e0 sp=0xc0004a97c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a97e8 sp=0xc0004a97e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 110 gp=0xc0004b0e00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004a9f38 sp=0xc0004a9f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004a9fc8 sp=0xc0004a9f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004a9fe0 sp=0xc0004a9fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a9fe8 sp=0xc0004a9fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 111 gp=0xc0004b0fc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004aa738 sp=0xc0004aa718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004aa7c8 sp=0xc0004aa738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004aa7e0 sp=0xc0004aa7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aa7e8 sp=0xc0004aa7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 112 gp=0xc0004b1180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004aaf38 sp=0xc0004aaf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004aafc8 sp=0xc0004aaf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004aafe0 sp=0xc0004aafc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aafe8 sp=0xc0004aafe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 113 gp=0xc0004b1340 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004ab738 sp=0xc0004ab718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004ab7c8 sp=0xc0004ab738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004ab7e0 sp=0xc0004ab7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ab7e8 sp=0xc0004ab7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 114 gp=0xc0004b1500 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004abf38 sp=0xc0004abf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004abfc8 sp=0xc0004abf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004abfe0 sp=0xc0004abfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004abfe8 sp=0xc0004abfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 115 gp=0xc0004b16c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b6738 sp=0xc0004b6718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b67c8 sp=0xc0004b6738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b67e0 sp=0xc0004b67c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b67e8 sp=0xc0004b67e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 116 gp=0xc0004b1880 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b6f38 sp=0xc0004b6f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b6fc8 sp=0xc0004b6f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b6fe0 sp=0xc0004b6fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b6fe8 sp=0xc0004b6fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 117 gp=0xc0004b1a40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b7738 sp=0xc0004b7718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b77c8 sp=0xc0004b7738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b77e0 sp=0xc0004b77c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b77e8 sp=0xc0004b77e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 118 gp=0xc0004b1c00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b7f38 sp=0xc0004b7f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b7fc8 sp=0xc0004b7f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b7fe0 sp=0xc0004b7fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b7fe8 sp=0xc0004b7fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 119 gp=0xc0004b1dc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b8738 sp=0xc0004b8718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b87c8 sp=0xc0004b8738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b87e0 sp=0xc0004b87c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b87e8 sp=0xc0004b87e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 120 gp=0xc0004ba000 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b8f38 sp=0xc0004b8f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b8fc8 sp=0xc0004b8f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b8fe0 sp=0xc0004b8fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b8fe8 sp=0xc0004b8fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 121 gp=0xc0004ba1c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b9738 sp=0xc0004b9718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b97c8 sp=0xc0004b9738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b97e0 sp=0xc0004b97c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b97e8 sp=0xc0004b97e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 122 gp=0xc0004ba380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b9f38 sp=0xc0004b9f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b9fc8 sp=0xc0004b9f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b9fe0 sp=0xc0004b9fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b9fe8 sp=0xc0004b9fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 123 gp=0xc0004ba540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b2738 sp=0xc0004b2718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b27c8 sp=0xc0004b2738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b27e0 sp=0xc0004b27c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b27e8 sp=0xc0004b27e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 124 gp=0xc0004ba700 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b2f38 sp=0xc0004b2f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b2fc8 sp=0xc0004b2f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b2fe0 sp=0xc0004b2fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b2fe8 sp=0xc0004b2fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 125 gp=0xc0004ba8c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b3738 sp=0xc0004b3718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b37c8 sp=0xc0004b3738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b37e0 sp=0xc0004b37c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b37e8 sp=0xc0004b37e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 126 gp=0xc0004baa80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b3f38 sp=0xc0004b3f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b3fc8 sp=0xc0004b3f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b3fe0 sp=0xc0004b3fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b3fe8 sp=0xc0004b3fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 127 gp=0xc0004bac40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b4738 sp=0xc0004b4718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b47c8 sp=0xc0004b4738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b47e0 sp=0xc0004b47c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b47e8 sp=0xc0004b47e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 128 gp=0xc0004bae00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b4f38 sp=0xc0004b4f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b4fc8 sp=0xc0004b4f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b4fe0 sp=0xc0004b4fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b4fe8 sp=0xc0004b4fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 129 gp=0xc0004bafc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b5738 sp=0xc0004b5718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b57c8 sp=0xc0004b5738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b57e0 sp=0xc0004b57c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b57e8 sp=0xc0004b57e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 130 gp=0xc0004bb180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004b5f38 sp=0xc0004b5f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004b5fc8 sp=0xc0004b5f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004b5fe0 sp=0xc0004b5fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004b5fe8 sp=0xc0004b5fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 131 gp=0xc0004bb340 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c0738 sp=0xc0004c0718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c07c8 sp=0xc0004c0738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c07e0 sp=0xc0004c07c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c07e8 sp=0xc0004c07e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 132 gp=0xc0004bb500 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c0f38 sp=0xc0004c0f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c0fc8 sp=0xc0004c0f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c0fe0 sp=0xc0004c0fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c0fe8 sp=0xc0004c0fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 133 gp=0xc0004bb6c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c1738 sp=0xc0004c1718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c17c8 sp=0xc0004c1738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c17e0 sp=0xc0004c17c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c17e8 sp=0xc0004c17e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 134 gp=0xc0004bb880 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c1f38 sp=0xc0004c1f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c1fc8 sp=0xc0004c1f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c1fe0 sp=0xc0004c1fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c1fe8 sp=0xc0004c1fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 135 gp=0xc0004bba40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c2738 sp=0xc0004c2718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c27c8 sp=0xc0004c2738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c27e0 sp=0xc0004c27c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c27e8 sp=0xc0004c27e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 136 gp=0xc0004bbc00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c2f38 sp=0xc0004c2f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c2fc8 sp=0xc0004c2f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c2fe0 sp=0xc0004c2fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c2fe8 sp=0xc0004c2fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 137 gp=0xc0004bbdc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c3738 sp=0xc0004c3718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c37c8 sp=0xc0004c3738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c37e0 sp=0xc0004c37c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c37e8 sp=0xc0004c37e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 138 gp=0xc0004c4000 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c3f38 sp=0xc0004c3f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c3fc8 sp=0xc0004c3f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c3fe0 sp=0xc0004c3fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c3fe8 sp=0xc0004c3fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 139 gp=0xc0004c41c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004bc738 sp=0xc0004bc718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004bc7c8 sp=0xc0004bc738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004bc7e0 sp=0xc0004bc7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bc7e8 sp=0xc0004bc7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 140 gp=0xc0004c4380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004bcf38 sp=0xc0004bcf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004bcfc8 sp=0xc0004bcf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004bcfe0 sp=0xc0004bcfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bcfe8 sp=0xc0004bcfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 141 gp=0xc0004c4540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004bd738 sp=0xc0004bd718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004bd7c8 sp=0xc0004bd738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004bd7e0 sp=0xc0004bd7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bd7e8 sp=0xc0004bd7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 142 gp=0xc0004c4700 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004bdf38 sp=0xc0004bdf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004bdfc8 sp=0xc0004bdf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004bdfe0 sp=0xc0004bdfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bdfe8 sp=0xc0004bdfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 143 gp=0xc0004c48c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004be738 sp=0xc0004be718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004be7c8 sp=0xc0004be738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004be7e0 sp=0xc0004be7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004be7e8 sp=0xc0004be7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 144 gp=0xc0004c4a80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004bef38 sp=0xc0004bef18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004befc8 sp=0xc0004bef38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004befe0 sp=0xc0004befc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004befe8 sp=0xc0004befe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 145 gp=0xc0004c4c40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004bf738 sp=0xc0004bf718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004bf7c8 sp=0xc0004bf738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004bf7e0 sp=0xc0004bf7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bf7e8 sp=0xc0004bf7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 146 gp=0xc0004c4e00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004bff38 sp=0xc0004bff18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004bffc8 sp=0xc0004bff38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004bffe0 sp=0xc0004bffc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004bffe8 sp=0xc0004bffe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 147 gp=0xc0004c4fc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004ca738 sp=0xc0004ca718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004ca7c8 sp=0xc0004ca738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004ca7e0 sp=0xc0004ca7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ca7e8 sp=0xc0004ca7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 148 gp=0xc0004c5180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004caf38 sp=0xc0004caf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004cafc8 sp=0xc0004caf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004cafe0 sp=0xc0004cafc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004cafe8 sp=0xc0004cafe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 72 gp=0xc000218a80 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000221738 sp=0xc000221718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0002217c8 sp=0xc000221738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0002217e0 sp=0xc0002217c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0002217e8 sp=0xc0002217e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 73 gp=0xc000218c40 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc000221f38 sp=0xc000221f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc000221fc8 sp=0xc000221f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc000221fe0 sp=0xc000221fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000221fe8 sp=0xc000221fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 84 gp=0xc000510000 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021b738 sp=0xc00021b718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021b7c8 sp=0xc00021b738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021b7e0 sp=0xc00021b7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021b7e8 sp=0xc00021b7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 85 gp=0xc0005101c0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021bf38 sp=0xc00021bf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021bfc8 sp=0xc00021bf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021bfe0 sp=0xc00021bfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021bfe8 sp=0xc00021bfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 86 gp=0xc000510380 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021c738 sp=0xc00021c718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021c7c8 sp=0xc00021c738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021c7e0 sp=0xc00021c7c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021c7e8 sp=0xc00021c7e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 87 gp=0xc000510540 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609cd4dd?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00021cf38 sp=0xc00021cf18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc00021cfc8 sp=0xc00021cf38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc00021cfe0 sp=0xc00021cfc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00021cfe8 sp=0xc00021cfe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 74 gp=0xc000218e00 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609b974f?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c6738 sp=0xc0004c6718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c67c8 sp=0xc0004c6738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c67e0 sp=0xc0004c67c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c67e8 sp=0xc0004c67e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 75 gp=0xc000218fc0 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x64c8264ba100?, 0x1?, 0xff?, 0x30?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c6f38 sp=0xc0004c6f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c6fc8 sp=0xc0004c6f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c6fe0 sp=0xc0004c6fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c6fe8 sp=0xc0004c6fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 76 gp=0xc000219180 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x64c8264ba100?, 0x1?, 0xda?, 0x8d?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c7738 sp=0xc0004c7718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c77c8 sp=0xc0004c7738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c77e0 sp=0xc0004c77c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c77e8 sp=0xc0004c77e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 77 gp=0xc000219340 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609beabf?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c7f38 sp=0xc0004c7f18 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c7fc8 sp=0xc0004c7f38 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c7fe0 sp=0xc0004c7fc8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c7fe8 sp=0xc0004c7fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 78 gp=0xc000219500 m=nil [GC worker (idle)]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x70c99609b3c5a?, 0x0?, 0x0?, 0x0?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c8738 sp=0xc0004c8718 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkWorker(0xc000041490) mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1423 +0xe9 fp=0xc0004c87c8 sp=0xc0004c8738 pc=0x64c8248b9089 mar 15 11:39:07 acquario3 ollama[87551]: runtime.gcBgMarkStartWorkers.gowrap1() mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x25 fp=0xc0004c87e0 sp=0xc0004c87c8 pc=0x64c8248b8f65 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c87e8 sp=0xc0004c87e0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by runtime.gcBgMarkStartWorkers in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: runtime/mgc.go:1339 +0x105 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 150 gp=0xc0005116c0 m=nil [sync.WaitGroup.Wait]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x0?, 0x0?, 0xa0?, 0x5?, 0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc0004c9e18 sp=0xc0004c9df8 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.goparkunlock(...) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:441 mar 15 11:39:07 acquario3 ollama[87551]: runtime.semacquire1(0xc0003d26c8, 0x0, 0x1, 0x0, 0x18) mar 15 11:39:07 acquario3 ollama[87551]: runtime/sema.go:188 +0x229 fp=0xc0004c9e80 sp=0xc0004c9e18 pc=0x64c8248eb249 mar 15 11:39:07 acquario3 ollama[87551]: sync.runtime_SemacquireWaitGroup(0x0?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/sema.go:110 +0x25 fp=0xc0004c9eb8 sp=0xc0004c9e80 pc=0x64c82490d285 mar 15 11:39:07 acquario3 ollama[87551]: sync.(*WaitGroup).Wait(0x0?) mar 15 11:39:07 acquario3 ollama[87551]: sync/waitgroup.go:118 +0x48 fp=0xc0004c9ee0 sp=0xc0004c9eb8 pc=0x64c82491ea08 mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0003d26c0, {0x64c825bbb7a0, 0xc000616d20}) mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner/runner.go:316 +0x47 fp=0xc0004c9fb8 sp=0xc0004c9ee0 pc=0x64c824ca9a67 mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2() mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0x28 fp=0xc0004c9fe0 sp=0xc0004c9fb8 pc=0x64c824cae588 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0004c9fe8 sp=0xc0004c9fe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0xd97 mar 15 11:39:07 acquario3 ollama[87551]: goroutine 151 gp=0xc000511880 m=nil [IO wait]: mar 15 11:39:07 acquario3 ollama[87551]: runtime.gopark(0x64c824995505?, 0xc000619900?, 0x40?, 0xfa?, 0xb?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/proc.go:435 +0xce fp=0xc00029f948 sp=0xc00029f928 pc=0x64c82490b86e mar 15 11:39:07 acquario3 ollama[87551]: runtime.netpollblock(0x64c82492ecf8?, 0x248a51a6?, 0xc8?) mar 15 11:39:07 acquario3 ollama[87551]: runtime/netpoll.go:575 +0xf7 fp=0xc00029f980 sp=0xc00029f948 pc=0x64c8248d0677 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.runtime_pollWait(0x7e77302a4d58, 0x72) mar 15 11:39:07 acquario3 ollama[87551]: runtime/netpoll.go:351 +0x85 fp=0xc00029f9a0 sp=0xc00029f980 pc=0x64c82490aa85 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).wait(0xc000619900?, 0xc00035f000?, 0x0) mar 15 11:39:07 acquario3 ollama[87551]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00029f9c8 sp=0xc00029f9a0 pc=0x64c824991f07 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*pollDesc).waitRead(...) mar 15 11:39:07 acquario3 ollama[87551]: internal/poll/fd_poll_runtime.go:89 mar 15 11:39:07 acquario3 ollama[87551]: internal/poll.(*FD).Read(0xc000619900, {0xc00035f000, 0x1000, 0x1000}) mar 15 11:39:07 acquario3 ollama[87551]: internal/poll/fd_unix.go:165 +0x27a fp=0xc00029fa60 sp=0xc00029f9c8 pc=0x64c8249931fa mar 15 11:39:07 acquario3 ollama[87551]: net.(*netFD).Read(0xc000619900, {0xc00035f000?, 0xc00029fad0?, 0x64c8249923c5?}) mar 15 11:39:07 acquario3 ollama[87551]: net/fd_posix.go:55 +0x25 fp=0xc00029faa8 sp=0xc00029fa60 pc=0x64c824a077a5 mar 15 11:39:07 acquario3 ollama[87551]: net.(*conn).Read(0xc000232720, {0xc00035f000?, 0x0?, 0x0?}) mar 15 11:39:07 acquario3 ollama[87551]: net/net.go:194 +0x45 fp=0xc00029faf0 sp=0xc00029faa8 pc=0x64c824a15b65 mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*connReader).Read(0xc00064aff0, {0xc00035f000, 0x1000, 0x1000}) mar 15 11:39:07 acquario3 ollama[87551]: net/http/server.go:798 +0x159 fp=0xc00029fb40 sp=0xc00029faf0 pc=0x64c824c015d9 mar 15 11:39:07 acquario3 ollama[87551]: bufio.(*Reader).fill(0xc000210600) mar 15 11:39:07 acquario3 ollama[87551]: bufio/bufio.go:113 +0x103 fp=0xc00029fb78 sp=0xc00029fb40 pc=0x64c824a2d303 mar 15 11:39:07 acquario3 ollama[87551]: bufio.(*Reader).Peek(0xc000210600, 0x4) mar 15 11:39:07 acquario3 ollama[87551]: bufio/bufio.go:152 +0x53 fp=0xc00029fb98 sp=0xc00029fb78 pc=0x64c824a2d433 mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*conn).serve(0xc0003d2750, {0x64c825bbb768, 0xc000514360}) mar 15 11:39:07 acquario3 ollama[87551]: net/http/server.go:2137 +0x785 fp=0xc00029ffb8 sp=0xc00029fb98 pc=0x64c824c073c5 mar 15 11:39:07 acquario3 ollama[87551]: net/http.(*Server).Serve.gowrap3() mar 15 11:39:07 acquario3 ollama[87551]: net/http/server.go:3454 +0x28 fp=0xc00029ffe0 sp=0xc00029ffb8 pc=0x64c824c0cb28 mar 15 11:39:07 acquario3 ollama[87551]: runtime.goexit({}) mar 15 11:39:07 acquario3 ollama[87551]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00029ffe8 sp=0xc00029ffe0 pc=0x64c824912fa1 mar 15 11:39:07 acquario3 ollama[87551]: created by net/http.(*Server).Serve in goroutine 1 mar 15 11:39:07 acquario3 ollama[87551]: net/http/server.go:3454 +0x485 mar 15 11:39:07 acquario3 ollama[87551]: rax 0x0 mar 15 11:39:07 acquario3 ollama[87551]: rbx 0x7e7730677400 mar 15 11:39:07 acquario3 ollama[87551]: rcx 0x7e77300969fc mar 15 11:39:07 acquario3 ollama[87551]: rdx 0x6 mar 15 11:39:07 acquario3 ollama[87551]: rdi 0x521b1 mar 15 11:39:07 acquario3 ollama[87551]: rsi 0x521b1 mar 15 11:39:07 acquario3 ollama[87551]: rbp 0x521b1 mar 15 11:39:07 acquario3 ollama[87551]: rsp 0x7ffc0a89c730 mar 15 11:39:07 acquario3 ollama[87551]: r8 0x7ffc0a89c800 mar 15 11:39:07 acquario3 ollama[87551]: r9 0x7ffc0a89c7d0 mar 15 11:39:07 acquario3 ollama[87551]: r10 0x8 mar 15 11:39:07 acquario3 ollama[87551]: r11 0x246 mar 15 11:39:07 acquario3 ollama[87551]: r12 0x6 mar 15 11:39:07 acquario3 ollama[87551]: r13 0x16 mar 15 11:39:07 acquario3 ollama[87551]: r14 0x7e76e049242e mar 15 11:39:07 acquario3 ollama[87551]: r15 0x64c82825cbc8 mar 15 11:39:07 acquario3 ollama[87551]: rip 0x7e77300969fc mar 15 11:39:07 acquario3 ollama[87551]: rflags 0x246 mar 15 11:39:07 acquario3 ollama[87551]: cs 0x33 mar 15 11:39:07 acquario3 ollama[87551]: fs 0x0 mar 15 11:39:07 acquario3 ollama[87551]: gs 0x0 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.733+01:00 level=ERROR source=server.go:421 msg="llama runner terminated" error="exit status 2" mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.910+01:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: CUDA error: out of memory\n current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898\n cudaMemGetInfo(free, total)\n//ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error" mar 15 11:39:07 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:07 | 500 | 1.086408297s | 172.19.0.5 | POST "/api/chat" mar 15 11:39:08 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:08.173+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:08 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:08.694+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:08 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:08.957+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.212+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.466+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.726+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:09 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:09.985+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:10 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:10.246+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:10 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:10.503+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:10 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:10.756+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.014+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.269+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.524+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:11 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:11.777+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.030+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.285+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.541+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:12 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:12.804+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:13 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:13.060+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:13 acquario3 ollama[87551]: time=2025-03-15T11:39:13.060+01:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.149805431 model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48 mar 15 11:39:13 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:13.322+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:13 acquario3 ollama[87551]: time=2025-03-15T11:39:13.322+01:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.411542305 model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48 mar 15 11:39:13 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:13.586+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:13 acquario3 ollama[87551]: time=2025-03-15T11:39:13.586+01:00 level=WARN source=sched.go:647 msg="gpu VRAM usage didn't recover within timeout" seconds=5.675742087 model=/usr/share/ollama/.ollama/models/blobs/sha256-619c98e932380bb9f5b7860cda119a6514c67d30432288b368515dda43876f48 mar 15 11:39:22 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:22.578+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:23 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:23.142+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:23 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:23.422+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.439+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.key_length default=128 mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.439+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.value_length default=128 mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.439+01:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 gpu=GPU-8d08743b-a730-6035-e5ed-9d2a4bb7d987 parallel=4 available=50749964288 required="11.5 GiB" mar 15 11:39:23 acquario3 ollama[87551]: cuda driver library failed to get device context 2time=2025-03-15T11:39:23.724+01:00 level=WARN source=gpu.go:434 msg="error looking up nvidia GPU memory" mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.724+01:00 level=INFO source=server.go:97 msg="system memory" total="503.5 GiB" free="431.6 GiB" free_swap="61.3 GiB" mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.key_length default=128 mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=WARN source=ggml.go:136 msg="key not found" key=phi3.attention.value_length default=128 mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=server.go:130 msg=offload library=cuda layers.requested=-1 layers.model=41 layers.offload=41 layers.split="" memory.available="[47.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.5 GiB" memory.required.partial="11.5 GiB" memory.required.kv="1.6 GiB" memory.required.allocations="[11.5 GiB]" memory.weights.total="9.3 GiB" memory.weights.repeating="8.9 GiB" memory.weights.nonrepeating="402.0 MiB" memory.graph.full="1.0 GiB" memory.graph.partial="1.0 GiB" mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 --ctx-size 8192 --batch-size 512 --n-gpu-layers 41 --threads 64 --parallel 4 --port 35965" mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=sched.go:450 msg="loaded runners" count=1 mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.725+01:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding" mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.726+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.742+01:00 level=INFO source=runner.go:931 msg="starting go runner" mar 15 11:39:23 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no mar 15 11:39:23 acquario3 ollama[87551]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no mar 15 11:39:23 acquario3 ollama[87551]: ggml_cuda_init: found 1 CUDA devices: mar 15 11:39:23 acquario3 ollama[87551]: Device 0: NVIDIA RTX A6000, compute capability 8.6, VMM: yes mar 15 11:39:23 acquario3 ollama[87551]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so mar 15 11:39:23 acquario3 ollama[87551]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.806+01:00 level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 500,600,610,700,750,800,860,870,890,900,1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=64 mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.806+01:00 level=INFO source=runner.go:992 msg="Server listening on 127.0.0.1:35965" mar 15 11:39:23 acquario3 ollama[87551]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA RTX A6000) - 48398 MiB free mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: loaded meta data with 33 key-value pairs and 243 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 (version GGUF V3 (latest)) mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 0: general.architecture str = phi3 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 1: general.type str = model mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 2: general.name str = Phi 4 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 3: general.version str = 4 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 4: general.organization str = Microsoft mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 5: general.basename str = phi mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 6: general.size_label str = 15B mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 7: general.license str = mit mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/microsoft/phi-... mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 9: general.tags arr[str,7] = ["phi", "nlp", "math", "code", "chat"... mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 10: general.languages arr[str,1] = ["en"] mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 11: phi3.context_length u32 = 16384 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 12: phi3.rope.scaling.original_context_length u32 = 16384 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 13: phi3.embedding_length u32 = 5120 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 14: phi3.feed_forward_length u32 = 17920 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 15: phi3.block_count u32 = 40 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 16: phi3.attention.head_count u32 = 40 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 17: phi3.attention.head_count_kv u32 = 10 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 18: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 19: phi3.rope.dimension_count u32 = 128 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 20: phi3.rope.freq_base f32 = 250000.000000 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 21: general.file_type u32 = 15 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 22: phi3.attention.sliding_window u32 = 131072 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 24: tokenizer.ggml.pre str = dbrx mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,100352] = ["!", "\"", "#", "$", "%", "&", "'", ... mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,100352] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,100000] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 100257 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 100257 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 30: tokenizer.ggml.padding_token_id u32 = 100257 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 31: tokenizer.chat_template str = {% for message in messages %}{% if (m... mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - kv 32: general.quantization_version u32 = 2 mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type f32: 81 tensors mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type q4_K: 101 tensors mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type q5_K: 40 tensors mar 15 11:39:23 acquario3 ollama[87551]: llama_model_loader: - type q6_K: 21 tensors mar 15 11:39:23 acquario3 ollama[87551]: print_info: file format = GGUF V3 (latest) mar 15 11:39:23 acquario3 ollama[87551]: print_info: file type = Q4_K - Medium mar 15 11:39:23 acquario3 ollama[87551]: print_info: file size = 8.43 GiB (4.94 BPW) mar 15 11:39:23 acquario3 ollama[87551]: load: special tokens cache size = 96 mar 15 11:39:23 acquario3 ollama[87551]: time=2025-03-15T11:39:23.978+01:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" mar 15 11:39:23 acquario3 ollama[87551]: load: token to piece cache size = 0.6151 MB mar 15 11:39:23 acquario3 ollama[87551]: print_info: arch = phi3 mar 15 11:39:23 acquario3 ollama[87551]: print_info: vocab_only = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_ctx_train = 16384 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd = 5120 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_layer = 40 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_head = 40 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_head_kv = 10 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_rot = 128 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_swa = 131072 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_head_k = 128 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_head_v = 128 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_gqa = 4 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_k_gqa = 1280 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_embd_v_gqa = 1280 mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_norm_eps = 0.0e+00 mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_norm_rms_eps = 1.0e-05 mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_clamp_kqv = 0.0e+00 mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_max_alibi_bias = 0.0e+00 mar 15 11:39:23 acquario3 ollama[87551]: print_info: f_logit_scale = 0.0e+00 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_ff = 17920 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_expert = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_expert_used = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: causal attn = 1 mar 15 11:39:23 acquario3 ollama[87551]: print_info: pooling type = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: rope type = 2 mar 15 11:39:23 acquario3 ollama[87551]: print_info: rope scaling = linear mar 15 11:39:23 acquario3 ollama[87551]: print_info: freq_base_train = 250000.0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: freq_scale_train = 1 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_ctx_orig_yarn = 16384 mar 15 11:39:23 acquario3 ollama[87551]: print_info: rope_finetuned = unknown mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_d_conv = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_d_inner = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_d_state = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_dt_rank = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: ssm_dt_b_c_rms = 0 mar 15 11:39:23 acquario3 ollama[87551]: print_info: model type = 14B mar 15 11:39:23 acquario3 ollama[87551]: print_info: model params = 14.66 B mar 15 11:39:23 acquario3 ollama[87551]: print_info: general.name = Phi 4 mar 15 11:39:23 acquario3 ollama[87551]: print_info: vocab type = BPE mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_vocab = 100352 mar 15 11:39:23 acquario3 ollama[87551]: print_info: n_merges = 100000 mar 15 11:39:23 acquario3 ollama[87551]: print_info: BOS token = 100257 '<|endoftext|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOS token = 100257 '<|endoftext|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOT token = 100265 '<|im_end|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: PAD token = 100257 '<|endoftext|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: LF token = 198 'Ċ' mar 15 11:39:23 acquario3 ollama[87551]: print_info: FIM PRE token = 100258 '<|fim_prefix|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: FIM SUF token = 100260 '<|fim_suffix|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: FIM MID token = 100259 '<|fim_middle|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOG token = 100257 '<|endoftext|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: EOG token = 100265 '<|im_end|>' mar 15 11:39:23 acquario3 ollama[87551]: print_info: max token length = 256 mar 15 11:39:23 acquario3 ollama[87551]: load_tensors: loading model tensors, this can take a while... (mmap = true) mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: offloading 40 repeating layers to GPU mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: offloading output layer to GPU mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: offloaded 41/41 layers to GPU mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: CUDA0 model buffer size = 8354.71 MiB mar 15 11:39:24 acquario3 ollama[87551]: load_tensors: CPU_Mapped model buffer size = 275.62 MiB mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_seq_max = 4 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ctx = 8192 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ctx_per_seq = 2048 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_batch = 2048 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ubatch = 512 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: flash_attn = 0 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: freq_base = 250000.0 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: freq_scale = 1 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (16384) -- the full capacity of the model will not be utilized mar 15 11:39:25 acquario3 ollama[87551]: llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 40, can_shift = 1 mar 15 11:39:25 acquario3 ollama[87551]: llama_kv_cache_init: CUDA0 KV buffer size = 1600.00 MiB mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: KV self size = 1600.00 MiB, K (f16): 800.00 MiB, V (f16): 800.00 MiB mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: CUDA_Host output buffer size = 1.61 MiB mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: CUDA0 compute buffer size = 701.00 MiB mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: CUDA_Host compute buffer size = 26.01 MiB mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: graph nodes = 1606 mar 15 11:39:25 acquario3 ollama[87551]: llama_init_from_model: graph splits = 2 mar 15 11:39:25 acquario3 ollama[87551]: time=2025-03-15T11:39:25.484+01:00 level=INFO source=server.go:596 msg="llama runner started in 1.76 seconds" mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: loaded meta data with 33 key-value pairs and 243 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 (version GGUF V3 (latest)) mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 0: general.architecture str = phi3 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 1: general.type str = model mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 2: general.name str = Phi 4 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 3: general.version str = 4 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 4: general.organization str = Microsoft mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 5: general.basename str = phi mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 6: general.size_label str = 15B mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 7: general.license str = mit mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/microsoft/phi-... mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 9: general.tags arr[str,7] = ["phi", "nlp", "math", "code", "chat"... mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 10: general.languages arr[str,1] = ["en"] mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 11: phi3.context_length u32 = 16384 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 12: phi3.rope.scaling.original_context_length u32 = 16384 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 13: phi3.embedding_length u32 = 5120 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 14: phi3.feed_forward_length u32 = 17920 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 15: phi3.block_count u32 = 40 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 16: phi3.attention.head_count u32 = 40 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 17: phi3.attention.head_count_kv u32 = 10 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 18: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 19: phi3.rope.dimension_count u32 = 128 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 20: phi3.rope.freq_base f32 = 250000.000000 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 21: general.file_type u32 = 15 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 22: phi3.attention.sliding_window u32 = 131072 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 24: tokenizer.ggml.pre str = dbrx mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,100352] = ["!", "\"", "#", "$", "%", "&", "'", ... mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,100352] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,100000] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 100257 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 100257 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 30: tokenizer.ggml.padding_token_id u32 = 100257 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 31: tokenizer.chat_template str = {% for message in messages %}{% if (m... mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - kv 32: general.quantization_version u32 = 2 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type f32: 81 tensors mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type q4_K: 101 tensors mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type q5_K: 40 tensors mar 15 11:39:25 acquario3 ollama[87551]: llama_model_loader: - type q6_K: 21 tensors mar 15 11:39:25 acquario3 ollama[87551]: print_info: file format = GGUF V3 (latest) mar 15 11:39:25 acquario3 ollama[87551]: print_info: file type = Q4_K - Medium mar 15 11:39:25 acquario3 ollama[87551]: print_info: file size = 8.43 GiB (4.94 BPW) mar 15 11:39:25 acquario3 ollama[87551]: load: special tokens cache size = 96 mar 15 11:39:25 acquario3 ollama[87551]: load: token to piece cache size = 0.6151 MB mar 15 11:39:25 acquario3 ollama[87551]: print_info: arch = phi3 mar 15 11:39:25 acquario3 ollama[87551]: print_info: vocab_only = 1 mar 15 11:39:25 acquario3 ollama[87551]: print_info: model type = ?B mar 15 11:39:25 acquario3 ollama[87551]: print_info: model params = 14.66 B mar 15 11:39:25 acquario3 ollama[87551]: print_info: general.name = Phi 4 mar 15 11:39:25 acquario3 ollama[87551]: print_info: vocab type = BPE mar 15 11:39:25 acquario3 ollama[87551]: print_info: n_vocab = 100352 mar 15 11:39:25 acquario3 ollama[87551]: print_info: n_merges = 100000 mar 15 11:39:25 acquario3 ollama[87551]: print_info: BOS token = 100257 '<|endoftext|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOS token = 100257 '<|endoftext|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOT token = 100265 '<|im_end|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: PAD token = 100257 '<|endoftext|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: LF token = 198 'Ċ' mar 15 11:39:25 acquario3 ollama[87551]: print_info: FIM PRE token = 100258 '<|fim_prefix|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: FIM SUF token = 100260 '<|fim_suffix|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: FIM MID token = 100259 '<|fim_middle|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOG token = 100257 '<|endoftext|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: EOG token = 100265 '<|im_end|>' mar 15 11:39:25 acquario3 ollama[87551]: print_info: max token length = 256 mar 15 11:39:25 acquario3 ollama[87551]: llama_model_load: vocab only - skipping tensors mar 15 11:39:26 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:26 | 200 | 4.106908544s | 172.19.0.5 | POST "/api/chat" mar 15 11:39:28 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:28 | 200 | 1.580520467s | 172.19.0.5 | POST "/api/chat" mar 15 11:39:31 acquario3 ollama[87551]: [GIN] 2025/03/15 - 11:39:31 | 200 | 3.688297873s | 172.19.0.5 | POST "/api/chat" ``` </details>
GiteaMirror commented 2026-04-29 01:20:28 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 16, 2025):

The first model load in the log that caused the crash is not cas/nous-hermes-2-mistral-7b-dpo:latest (sha256 of 3f99518c1e2c1b2cee14c3cd7c110358ceb89cf2be0be0626d11ebd8571ff0ff).

mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:130 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[47.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="35.3 GiB" memory.required.partial="35.3 GiB" memory.required.kv="2.0 GiB" memory.required.allocations="[35.3 GiB]" memory.weights.total="32.9 GiB" memory.weights.repeating="32.1 GiB" memory.weights.nonrepeating="788.9 MiB" memory.graph.full="676.0 MiB" memory.graph.partial="916.1 MiB"

The model requires 35G VRAM of 47G available, which would normally leave plenty of room for subsequent allocations.

mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 500,600,610,700,750,800,860,870,890,900,1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=64
mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:992 msg="Server listening on 127.0.0.1:34775"
mar 15 11:39:07 acquario3 ollama[87551]: CUDA error: out of memory
mar 15 11:39:07 acquario3 ollama[87551]:   current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898
mar 15 11:39:07 acquario3 ollama[87551]:   cudaMemGetInfo(free, total)
mar 15 11:39:07 acquario3 ollama[87551]: //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error

However, it crashed during the model load, so this is a different failure to the one that @demiurger experienced. For this sort of error I usually recommend some mitigations, but 12G free should really be enough so it's not clear to me why this failed. Can you supply the model name?

The second model load is phi4:14b and works fine.

<!-- gh-comment-id:2727534476 --> @rick-github commented on GitHub (Mar 16, 2025): The first model load in the log that caused the crash is not cas/nous-hermes-2-mistral-7b-dpo:latest (sha256 of 3f99518c1e2c1b2cee14c3cd7c110358ceb89cf2be0be0626d11ebd8571ff0ff). ``` mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.407+01:00 level=INFO source=server.go:130 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[47.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="35.3 GiB" memory.required.partial="35.3 GiB" memory.required.kv="2.0 GiB" memory.required.allocations="[35.3 GiB]" memory.weights.total="32.9 GiB" memory.weights.repeating="32.1 GiB" memory.weights.nonrepeating="788.9 MiB" memory.graph.full="676.0 MiB" memory.graph.partial="916.1 MiB" ``` The model requires 35G VRAM of 47G available, which would normally leave plenty of room for subsequent allocations. ``` mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:934 msg=system info="CPU : LLAMAFILE = 1 | CUDA : ARCHS = 500,600,610,700,750,800,860,870,890,900,1200 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=64 mar 15 11:39:07 acquario3 ollama[87551]: time=2025-03-15T11:39:07.487+01:00 level=INFO source=runner.go:992 msg="Server listening on 127.0.0.1:34775" mar 15 11:39:07 acquario3 ollama[87551]: CUDA error: out of memory mar 15 11:39:07 acquario3 ollama[87551]: current device: 0, in function ggml_backend_cuda_device_get_memory at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2898 mar 15 11:39:07 acquario3 ollama[87551]: cudaMemGetInfo(free, total) mar 15 11:39:07 acquario3 ollama[87551]: //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:73: CUDA error ``` However, it crashed during the model load, so this is a different failure to the one that @demiurger experienced. For this sort of error I usually recommend some [mitigations](https://github.com/ollama/ollama/issues/8597#issuecomment-2614533288), but 12G free should really be enough so it's not clear to me why this failed. Can you supply the model name? The second model load is phi4:14b and works fine.
GiteaMirror commented 2026-04-29 01:20:30 -05:00
Author
Owner
Copy Link

@AlbertoSinigaglia commented on GitHub (Mar 16, 2025):

@rick-github not sure which model name you are referring to, cas/nous-hermes-2-mistral-7b-dpo:latest is the one I tried, but later I've also tried other models, with the same error (I've uploaded only one of the logs). Phi4:14b run withough problem because we always keep that in memory with a cronjob.

Furthermore, that cas/nous-hermes-2-mistral-7b-dpo:latest is extremely small:

cas/nous-hermes-2-mistral-7b-dpo:latest                       1591668a22eb    4.4 GB    3 weeks ago

So it would for sure fit in the 35Gb of GPU mem remaining in cuda:0 and cuda:1

<!-- gh-comment-id:2727546926 --> @AlbertoSinigaglia commented on GitHub (Mar 16, 2025): @rick-github not sure which model name you are referring to, `cas/nous-hermes-2-mistral-7b-dpo:latest` is the one I tried, but later I've also tried other models, with the same error (I've uploaded only one of the logs). Phi4:14b run withough problem because we always keep that in memory with a cronjob. Furthermore, that `cas/nous-hermes-2-mistral-7b-dpo:latest` is extremely small: ``` cas/nous-hermes-2-mistral-7b-dpo:latest 1591668a22eb 4.4 GB 3 weeks ago ``` So it would for sure fit in the 35Gb of GPU mem remaining in cuda:0 and cuda:1
GiteaMirror commented 2026-04-29 01:20:30 -05:00
Author
Owner
Copy Link

@demiurger commented on GitHub (Mar 16, 2025):

@rick-github I used CLI, and entered the following prompt:
C:\Users\hpc> ollama run gemma3:27b

translate into spanish: The pair were due to be on the ISS for only eight days, but because of technical issues with
... the experimental spacecraft they arrived on, they have been there for more than nine months.
Error: POST predict: Post "http://127.0.0.1:59639/completion": read tcp 127.0.0.1:59641->127.0.0.1:59639: wsarecv: An existing connection was forcibly closed by the remote host.

As I said before, it always happens if prompt (or context, sorry I am just a user, not a pro) is more than a few words. If I say something like: "Hello" works, but after a few queries it stops working.

<!-- gh-comment-id:2727568999 --> @demiurger commented on GitHub (Mar 16, 2025): @rick-github I used CLI, and entered the following prompt: C:\Users\hpc> ollama run gemma3:27b >>> translate into spanish: The pair were due to be on the ISS for only eight days, but because of technical issues with ... the experimental spacecraft they arrived on, they have been there for more than nine months. Error: POST predict: Post "http://127.0.0.1:59639/completion": read tcp 127.0.0.1:59641->127.0.0.1:59639: wsarecv: An existing connection was forcibly closed by the remote host. As I said before, it always happens if prompt (or context, sorry I am just a user, not a pro) is more than a few words. If I say something like: "Hello" works, but after a few queries it stops working.
GiteaMirror commented 2026-04-29 01:20:32 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 16, 2025):

@AlbertoSinigaglia

So it would for sure fit in the 35Gb of GPU mem remaining in cuda:0 and cuda:1

I agree that cas/nous-hermes-2-mistral-7b-dpo:latest will fit in the available memory. The model that caused the crash in your log was not cas/nous-hermes-2-mistral-7b-dpo:latest, it was significantly larger with model weights of around 32G, not the 4.4G of nouse-hermes.

<!-- gh-comment-id:2727588590 --> @rick-github commented on GitHub (Mar 16, 2025): @AlbertoSinigaglia > So it would for sure fit in the 35Gb of GPU mem remaining in cuda:0 and cuda:1 I agree that cas/nous-hermes-2-mistral-7b-dpo:latest will fit in the available memory. The model that caused the crash in your log was not cas/nous-hermes-2-mistral-7b-dpo:latest, it was significantly larger with model weights of around 32G, not the 4.4G of nouse-hermes.
GiteaMirror commented 2026-04-29 01:20:34 -05:00
Author
Owner
Copy Link

@AlbertoSinigaglia commented on GitHub (Mar 16, 2025):

@rick-github so i happen to still have the whole nvitop screen:
image

As you can see, the only loaded model was phi4, the 10Gb vram process. The 30Gb-ish model was either Qwen coder or QwQ-32B (most likely)

Not sure if this makes a difference, in case let me know and i'll upload a file with the whole log of yesterday morning (and not just one failure between the many I tried, to see if it was a single model that was causing that problem or if all of them had it)

<!-- gh-comment-id:2727605002 --> @AlbertoSinigaglia commented on GitHub (Mar 16, 2025): @rick-github so i happen to still have the whole nvitop screen: ![image](https://github.com/user-attachments/assets/a63b3b0a-d0fe-47a9-8366-374a948cf280) As you can see, the only loaded model was phi4, the 10Gb vram process. The 30Gb-ish model was either Qwen coder or QwQ-32B (most likely) Not sure if this makes a difference, in case let me know and i'll upload a file with the whole log of yesterday morning (and not just one failure between the many I tried, to see if it was a single model that was causing that problem or if all of them had it)
GiteaMirror commented 2026-04-29 01:20:37 -05:00
Author
Owner
Copy Link

@AlbertoSinigaglia commented on GitHub (Mar 16, 2025):

Also (maybe useless, but worth saying i guess), ollama usually shards models across gpus if they can't fit in a single one, so i'm not sure why it was happening... my only guess was that cuda:2 that was used almost to a saturation point by another user, and thar maybe ollama wanted some mem from that one lol

<!-- gh-comment-id:2727612423 --> @AlbertoSinigaglia commented on GitHub (Mar 16, 2025): Also (maybe useless, but worth saying i guess), ollama usually shards models across gpus if they can't fit in a single one, so i'm not sure why it was happening... my only guess was that cuda:2 that was used almost to a saturation point by another user, and thar maybe ollama wanted some mem from that one lol
GiteaMirror commented 2026-04-29 01:20:42 -05:00
Author
Owner
Copy Link

@nickheyer commented on GitHub (Mar 25, 2025):

Same thing is happening to me with a 48gb card and a relatively large model. I can "fix" this by setting num_gpu to a static number, but it kills performance and concurrency.

<!-- gh-comment-id:2749748661 --> @nickheyer commented on GitHub (Mar 25, 2025): Same thing is happening to me with a 48gb card and a relatively large model. I can "fix" this by setting num_gpu to a static number, but it kills performance and concurrency.
GiteaMirror commented 2026-04-29 01:20:43 -05:00
Author
Owner
Copy Link

@tjwebb commented on GitHub (Apr 13, 2025):

I am also seeing this occasionally with 0.6.5 when loading gemma3:27b into an L40 with 48GB of VRAM. I cannot reproduce consistently.

<!-- gh-comment-id:2799590385 --> @tjwebb commented on GitHub (Apr 13, 2025): I am also seeing this occasionally with 0.6.5 when loading gemma3:27b into an L40 with 48GB of VRAM. I cannot reproduce consistently.
GiteaMirror commented 2026-04-29 01:20:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 13, 2025):

Server logs will aid in diagnosis.

<!-- gh-comment-id:2799905973 --> @rick-github commented on GitHub (Apr 13, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will aid in diagnosis.
GiteaMirror commented 2026-04-29 01:20:44 -05:00
Author
Owner
Copy Link

@JMuff22 commented on GitHub (Apr 21, 2025):

I have a similar issue running Deepseek 671B. The error only occurs if I set OLLAMA_FLASH_ATTENTION=1 on startup. Otherwise I have no issue. Does this help?

Logs time=2025-04-21T12:29:51.160+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-bc3bedc1-3249-b2ab-e15f-cf6ba3e4b329 library=cuda total="79.2 GiB" available="68.3 GiB" time=2025-04-21T12:29:51.160+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-76ddd618-f2df-feab-66aa-f85ce8e5ebc8 library=cuda total="79.2 GiB" available="35.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-6d2eef79-9a59-4516-6456-5b14fbb8681e library=cuda total="79.2 GiB" available="57.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-86ad5f8b-7ba9-7c70-20de-b6ef5d350cf9 library=cuda total="79.2 GiB" available="57.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-530159d7-95ea-c8f8-7a4c-871a99cab07b library=cuda total="79.2 GiB" available="35.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-11f7cd34-11a2-96ed-e7e8-452c48885d47 library=cuda total="79.2 GiB" available="78.7 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-4b2d7293-9b58-7a25-c59a-57cba53a232b library=cuda total="79.2 GiB" available="78.7 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-616e70b1-2ea8-0707-bf19-b814e054f853 library=cuda total="79.2 GiB" available="78.7 GiB" time=2025-04-21T12:29:51.161+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:29:54.249+03:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=10.313002755 model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 time=2025-04-21T12:29:57.363+03:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=13.426501454 model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 time=2025-04-21T12:30:00.475+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:03.583+03:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=19.647088021 model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 time=2025-04-21T12:30:06.844+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:09.978+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:13.119+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:16.357+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:19.620+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:22.744+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:25.949+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:29.094+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:32.193+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:35.261+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:38.534+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:41.687+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:44.811+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:48.041+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:51.271+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:54.416+03:00 level=INFO source=sched.go:732 msg="new model will fit in available VRAM, loading" model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 library=cuda parallel=4 required="449.4 GiB" time=2025-04-21T12:30:57.583+03:00 level=INFO source=server.go:105 msg="system memory" total="1007.4 GiB" free="990.2 GiB" free_swap="9.0 GiB" time=2025-04-21T12:30:57.583+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:31:00.791+03:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=62 layers.offload=62 layers.split=10,11,11,8,7,7,4,4 memory.available="[78.7 GiB 78.7 GiB 78.7 GiB 68.3 GiB 57.6 GiB 57.6 GiB 35.6 GiB 35.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="449.4 GiB" memory.required.partial="449.4 GiB" memory.required.kv="38.1 GiB" memory.required.allocations="[70.7 GiB 69.6 GiB 75.6 GiB 61.3 GiB 54.6 GiB 52.8 GiB 32.8 GiB 31.9 GiB]" memory.weights.total="376.2 GiB" memory.weights.repeating="375.5 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="3.0 GiB" memory.graph.partial="3.0 GiB" time=2025-04-21T12:31:00.791+03:00 level=WARN source=server.go:178 msg="flash attention enabled but not supported by model" llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from ~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = deepseek2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.size_label str = 256x20B llama_model_loader: - kv 3: deepseek2.block_count u32 = 61 llama_model_loader: - kv 4: deepseek2.context_length u32 = 163840 llama_model_loader: - kv 5: deepseek2.embedding_length u32 = 7168 llama_model_loader: - kv 6: deepseek2.feed_forward_length u32 = 18432 llama_model_loader: - kv 7: deepseek2.attention.head_count u32 = 128 llama_model_loader: - kv 8: deepseek2.attention.head_count_kv u32 = 128 llama_model_loader: - kv 9: deepseek2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 10: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 11: deepseek2.expert_used_count u32 = 8 llama_model_loader: - kv 12: deepseek2.leading_dense_block_count u32 = 3 llama_model_loader: - kv 13: deepseek2.vocab_size u32 = 129280 llama_model_loader: - kv 14: deepseek2.attention.q_lora_rank u32 = 1536 llama_model_loader: - kv 15: deepseek2.attention.kv_lora_rank u32 = 512 llama_model_loader: - kv 16: deepseek2.attention.key_length u32 = 192 llama_model_loader: - kv 17: deepseek2.attention.value_length u32 = 128 llama_model_loader: - kv 18: deepseek2.expert_feed_forward_length u32 = 2048 llama_model_loader: - kv 19: deepseek2.expert_count u32 = 256 llama_model_loader: - kv 20: deepseek2.expert_shared_count u32 = 1 llama_model_loader: - kv 21: deepseek2.expert_weights_scale f32 = 2.500000 llama_model_loader: - kv 22: deepseek2.expert_weights_norm bool = true llama_model_loader: - kv 23: deepseek2.expert_gating_func u32 = 2 llama_model_loader: - kv 24: deepseek2.rope.dimension_count u32 = 64 llama_model_loader: - kv 25: deepseek2.rope.scaling.type str = yarn llama_model_loader: - kv 26: deepseek2.rope.scaling.factor f32 = 40.000000 llama_model_loader: - kv 27: deepseek2.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 28: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.100000 llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 30: tokenizer.ggml.pre str = deepseek-v3 llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,129280] = ["<｜begin▁of▁sentence｜>", "<�... llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,129280] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,127741] = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e... llama_model_loader: - kv 34: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 35: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 36: tokenizer.ggml.padding_token_id u32 = 1 llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 38: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 39: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 40: general.quantization_version u32 = 2 llama_model_loader: - kv 41: general.file_type u32 = 15 llama_model_loader: - type f32: 361 tensors llama_model_loader: - type q4_K: 606 tensors llama_model_loader: - type q6_K: 58 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 376.65 GiB (4.82 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 818 load: token to piece cache size = 0.8223 MB print_info: arch = deepseek2 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 671.03 B print_info: general.name = n/a print_info: n_layer_dense_lead = 0 print_info: n_lora_q = 0 print_info: n_lora_kv = 0 print_info: n_ff_exp = 0 print_info: n_expert_shared = 0 print_info: expert_weights_scale = 0.0 print_info: expert_weights_norm = 0 print_info: expert_gating_func = unknown print_info: rope_yarn_log_mul = 0.0000 print_info: vocab type = BPE print_info: n_vocab = 129280 print_info: n_merges = 127741 print_info: BOS token = 0 '<｜begin▁of▁sentence｜>' print_info: EOS token = 1 '<｜end▁of▁sentence｜>' print_info: EOT token = 1 '<｜end▁of▁sentence｜>' print_info: PAD token = 1 '<｜end▁of▁sentence｜>' print_info: LF token = 201 'Ċ' print_info: FIM PRE token = 128801 '<｜fim▁begin｜>' print_info: FIM SUF token = 128800 '<｜fim▁hole｜>' print_info: FIM MID token = 128802 '<｜fim▁end｜>' print_info: EOG token = 1 '<｜end▁of▁sentence｜>' print_info: max token length = 256 llama_model_load: vocab only - skipping tensors time=2025-04-21T12:31:00.947+03:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model ~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 --ctx-size 8192 --batch-size 512 --n-gpu-layers 62 --threads 96 --parallel 4 --tensor-split 10,11,11,8,7,7,4,4 --port 37411" time=2025-04-21T12:31:00.947+03:00 level=INFO source=sched.go:451 msg="loaded runners" count=6 time=2025-04-21T12:31:00.947+03:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding" time=2025-04-21T12:31:00.947+03:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" time=2025-04-21T12:31:00.959+03:00 level=INFO source=runner.go:853 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 8 CUDA devices: Device 0: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 1: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 2: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 3: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 4: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 5: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 6: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 7: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so time=2025-04-21T12:31:03.531+03:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 CUDA.1.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.1.USE_GRAPHS=1 CUDA.1.PEER_MAX_BATCH_SIZE=128 CUDA.2.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.2.USE_GRAPHS=1 CUDA.2.PEER_MAX_BATCH_SIZE=128 CUDA.3.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.3.USE_GRAPHS=1 CUDA.3.PEER_MAX_BATCH_SIZE=128 CUDA.4.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.4.USE_GRAPHS=1 CUDA.4.PEER_MAX_BATCH_SIZE=128 CUDA.5.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.5.USE_GRAPHS=1 CUDA.5.PEER_MAX_BATCH_SIZE=128 CUDA.6.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.6.USE_GRAPHS=1 CUDA.6.PEER_MAX_BATCH_SIZE=128 CUDA.7.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.7.USE_GRAPHS=1 CUDA.7.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2025-04-21T12:31:03.532+03:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:37411" time=2025-04-21T12:31:03.706+03:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA H100 80GB HBM3) - 80580 MiB free llama_model_load_from_file_impl: using device CUDA1 (NVIDIA H100 80GB HBM3) - 80580 MiB free llama_model_load_from_file_impl: using device CUDA2 (NVIDIA H100 80GB HBM3) - 80580 MiB free llama_model_load_from_file_impl: using device CUDA3 (NVIDIA H100 80GB HBM3) - 69911 MiB free llama_model_load_from_file_impl: using device CUDA4 (NVIDIA H100 80GB HBM3) - 59033 MiB free llama_model_load_from_file_impl: using device CUDA5 (NVIDIA H100 80GB HBM3) - 59033 MiB free llama_model_load_from_file_impl: using device CUDA6 (NVIDIA H100 80GB HBM3) - 37089 MiB free llama_model_load_from_file_impl: using device CUDA7 (NVIDIA H100 80GB HBM3) - 37089 MiB free llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from ~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = deepseek2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.size_label str = 256x20B llama_model_loader: - kv 3: deepseek2.block_count u32 = 61 llama_model_loader: - kv 4: deepseek2.context_length u32 = 163840 llama_model_loader: - kv 5: deepseek2.embedding_length u32 = 7168 llama_model_loader: - kv 6: deepseek2.feed_forward_length u32 = 18432 llama_model_loader: - kv 7: deepseek2.attention.head_count u32 = 128 llama_model_loader: - kv 8: deepseek2.attention.head_count_kv u32 = 128 llama_model_loader: - kv 9: deepseek2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 10: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 11: deepseek2.expert_used_count u32 = 8 llama_model_loader: - kv 12: deepseek2.leading_dense_block_count u32 = 3 llama_model_loader: - kv 13: deepseek2.vocab_size u32 = 129280 llama_model_loader: - kv 14: deepseek2.attention.q_lora_rank u32 = 1536 llama_model_loader: - kv 15: deepseek2.attention.kv_lora_rank u32 = 512 llama_model_loader: - kv 16: deepseek2.attention.key_length u32 = 192 llama_model_loader: - kv 17: deepseek2.attention.value_length u32 = 128 llama_model_loader: - kv 18: deepseek2.expert_feed_forward_length u32 = 2048 llama_model_loader: - kv 19: deepseek2.expert_count u32 = 256 llama_model_loader: - kv 20: deepseek2.expert_shared_count u32 = 1 llama_model_loader: - kv 21: deepseek2.expert_weights_scale f32 = 2.500000 llama_model_loader: - kv 22: deepseek2.expert_weights_norm bool = true llama_model_loader: - kv 23: deepseek2.expert_gating_func u32 = 2 llama_model_loader: - kv 24: deepseek2.rope.dimension_count u32 = 64 llama_model_loader: - kv 25: deepseek2.rope.scaling.type str = yarn llama_model_loader: - kv 26: deepseek2.rope.scaling.factor f32 = 40.000000 llama_model_loader: - kv 27: deepseek2.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 28: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.100000 llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 30: tokenizer.ggml.pre str = deepseek-v3 llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,129280] = ["<｜begin▁of▁sentence｜>", "<�... llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,129280] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,127741] = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e... llama_model_loader: - kv 34: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 35: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 36: tokenizer.ggml.padding_token_id u32 = 1 llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 38: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 39: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 40: general.quantization_version u32 = 2 llama_model_loader: - kv 41: general.file_type u32 = 15 llama_model_loader: - type f32: 361 tensors llama_model_loader: - type q4_K: 606 tensors llama_model_loader: - type q6_K: 58 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 376.65 GiB (4.82 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 818 load: token to piece cache size = 0.8223 MB print_info: arch = deepseek2 print_info: vocab_only = 0 print_info: n_ctx_train = 163840 print_info: n_embd = 7168 print_info: n_layer = 61 print_info: n_head = 128 print_info: n_head_kv = 128 print_info: n_rot = 64 print_info: n_swa = 0 print_info: n_embd_head_k = 192 print_info: n_embd_head_v = 128 print_info: n_gqa = 1 print_info: n_embd_k_gqa = 24576 print_info: n_embd_v_gqa = 16384 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-06 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: n_ff = 18432 print_info: n_expert = 256 print_info: n_expert_used = 8 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 0 print_info: rope scaling = yarn print_info: freq_base_train = 10000.0 print_info: freq_scale_train = 0.025 print_info: n_ctx_orig_yarn = 4096 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 671B print_info: model params = 671.03 B print_info: general.name = n/a print_info: n_layer_dense_lead = 3 print_info: n_lora_q = 1536 print_info: n_lora_kv = 512 print_info: n_ff_exp = 2048 print_info: n_expert_shared = 1 print_info: expert_weights_scale = 2.5 print_info: expert_weights_norm = 1 print_info: expert_gating_func = sigmoid print_info: rope_yarn_log_mul = 0.1000 print_info: vocab type = BPE print_info: n_vocab = 129280 print_info: n_merges = 127741 print_info: BOS token = 0 '<｜begin▁of▁sentence｜>' print_info: EOS token = 1 '<｜end▁of▁sentence｜>' print_info: EOT token = 1 '<｜end▁of▁sentence｜>' print_info: PAD token = 1 '<｜end▁of▁sentence｜>' print_info: LF token = 201 'Ċ' print_info: FIM PRE token = 128801 '<｜fim▁begin｜>' print_info: FIM SUF token = 128800 '<｜fim▁hole｜>' print_info: FIM MID token = 128802 '<｜fim▁end｜>' print_info: EOG token = 1 '<｜end▁of▁sentence｜>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (mmap = true) load_tensors: offloading 61 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 62/62 layers to GPU load_tensors: CUDA0 model buffer size = 48928.09 MiB load_tensors: CUDA1 model buffer size = 70752.48 MiB load_tensors: CUDA2 model buffer size = 71680.09 MiB load_tensors: CUDA3 model buffer size = 52215.30 MiB load_tensors: CUDA4 model buffer size = 45108.64 MiB load_tensors: CUDA5 model buffer size = 46036.25 MiB load_tensors: CUDA6 model buffer size = 28426.68 MiB load_tensors: CUDA7 model buffer size = 22044.99 MiB load_tensors: CPU_Mapped model buffer size = 497.11 MiB llama_init_from_model: n_seq_max = 4 llama_init_from_model: n_ctx = 8192 llama_init_from_model: n_ctx_per_seq = 2048 llama_init_from_model: n_batch = 2048 llama_init_from_model: n_ubatch = 512 llama_init_from_model: flash_attn = 0 llama_init_from_model: freq_base = 10000.0 llama_init_from_model: freq_scale = 0.025 llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (163840) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 61, can_shift = 0 llama_kv_cache_init: CUDA0 KV buffer size = 6400.00 MiB llama_kv_cache_init: CUDA1 KV buffer size = 7040.00 MiB llama_kv_cache_init: CUDA2 KV buffer size = 7040.00 MiB llama_kv_cache_init: CUDA3 KV buffer size = 5120.00 MiB llama_kv_cache_init: CUDA4 KV buffer size = 4480.00 MiB llama_kv_cache_init: CUDA5 KV buffer size = 4480.00 MiB llama_kv_cache_init: CUDA6 KV buffer size = 2560.00 MiB llama_kv_cache_init: CUDA7 KV buffer size = 1920.00 MiB llama_init_from_model: KV self size = 39040.00 MiB, K (f16): 23424.00 MiB, V (f16): 15616.00 MiB llama_init_from_model: CUDA_Host output buffer size = 2.08 MiB llama_init_from_model: pipeline parallelism enabled (n_copies=4) ggml_backend_cuda_buffer_type_alloc_buffer: allocating 2322.01 MiB on device 2: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA2 buffer of size 2434801664 ggml_backend_cuda_buffer_type_alloc_buffer: allocating 2322.01 MiB on device 2: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA2 buffer of size 2434801664 llama_init_from_model: failed to allocate compute buffers panic: unable to create llama context

goroutine 111 [running]:
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc000544360, {0x3e, 0x0, 0x1, 0x0, {0xc0005010c0, 0x8, 0x8}, 0xc00055e1a0, 0x0}, ...)
github.com/ollama/ollama/runner/llamarunner/runner.go:779 +0x369
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/llamarunner/runner.go:887 +0xbd7
time=2025-04-21T12:32:01.411+03:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2025-04-21T12:32:02.192+03:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2"
time=2025-04-21T12:32:02.413+03:00 level=ERROR source=sched.go:457 msg="error loading llama server" error="llama runner process has terminated: cudaMalloc failed: out of memory"
[GIN] 2025/04/21 - 12:32:02 | 500 | 2m18s | 127.0.0.1 | POST "/api/generate"
Generation error: llama runner process has terminated: cudaMalloc failed: out of memory (status code: 500)


<!-- gh-comment-id:2818069321 --> @JMuff22 commented on GitHub (Apr 21, 2025): I have a similar issue running Deepseek 671B. The error only occurs if I set `OLLAMA_FLASH_ATTENTION=1` on startup. Otherwise I have no issue. Does this help? <details open> <summary>Logs</summary> <code> time=2025-04-21T12:29:51.160+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-bc3bedc1-3249-b2ab-e15f-cf6ba3e4b329 library=cuda total="79.2 GiB" available="68.3 GiB" time=2025-04-21T12:29:51.160+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-76ddd618-f2df-feab-66aa-f85ce8e5ebc8 library=cuda total="79.2 GiB" available="35.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-6d2eef79-9a59-4516-6456-5b14fbb8681e library=cuda total="79.2 GiB" available="57.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-86ad5f8b-7ba9-7c70-20de-b6ef5d350cf9 library=cuda total="79.2 GiB" available="57.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-530159d7-95ea-c8f8-7a4c-871a99cab07b library=cuda total="79.2 GiB" available="35.6 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-11f7cd34-11a2-96ed-e7e8-452c48885d47 library=cuda total="79.2 GiB" available="78.7 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-4b2d7293-9b58-7a25-c59a-57cba53a232b library=cuda total="79.2 GiB" available="78.7 GiB" time=2025-04-21T12:29:51.161+03:00 level=INFO source=sched.go:509 msg="updated VRAM based on existing loaded models" gpu=GPU-616e70b1-2ea8-0707-bf19-b814e054f853 library=cuda total="79.2 GiB" available="78.7 GiB" time=2025-04-21T12:29:51.161+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:29:54.249+03:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=10.313002755 model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 time=2025-04-21T12:29:57.363+03:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=13.426501454 model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 time=2025-04-21T12:30:00.475+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:03.583+03:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=19.647088021 model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 time=2025-04-21T12:30:06.844+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:09.978+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:13.119+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:16.357+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:19.620+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:22.744+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:25.949+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:29.094+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:32.193+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:35.261+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:38.534+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:41.687+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:44.811+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:48.041+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:51.271+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:30:54.416+03:00 level=INFO source=sched.go:732 msg="new model will fit in available VRAM, loading" model=~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 library=cuda parallel=4 required="449.4 GiB" time=2025-04-21T12:30:57.583+03:00 level=INFO source=server.go:105 msg="system memory" total="1007.4 GiB" free="990.2 GiB" free_swap="9.0 GiB" time=2025-04-21T12:30:57.583+03:00 level=WARN source=ggml.go:152 msg="key not found" key=deepseek2.vision.block_count default=0 time=2025-04-21T12:31:00.791+03:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=62 layers.offload=62 layers.split=10,11,11,8,7,7,4,4 memory.available="[78.7 GiB 78.7 GiB 78.7 GiB 68.3 GiB 57.6 GiB 57.6 GiB 35.6 GiB 35.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="449.4 GiB" memory.required.partial="449.4 GiB" memory.required.kv="38.1 GiB" memory.required.allocations="[70.7 GiB 69.6 GiB 75.6 GiB 61.3 GiB 54.6 GiB 52.8 GiB 32.8 GiB 31.9 GiB]" memory.weights.total="376.2 GiB" memory.weights.repeating="375.5 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="3.0 GiB" memory.graph.partial="3.0 GiB" time=2025-04-21T12:31:00.791+03:00 level=WARN source=server.go:178 msg="flash attention enabled but not supported by model" llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from ~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = deepseek2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.size_label str = 256x20B llama_model_loader: - kv 3: deepseek2.block_count u32 = 61 llama_model_loader: - kv 4: deepseek2.context_length u32 = 163840 llama_model_loader: - kv 5: deepseek2.embedding_length u32 = 7168 llama_model_loader: - kv 6: deepseek2.feed_forward_length u32 = 18432 llama_model_loader: - kv 7: deepseek2.attention.head_count u32 = 128 llama_model_loader: - kv 8: deepseek2.attention.head_count_kv u32 = 128 llama_model_loader: - kv 9: deepseek2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 10: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 11: deepseek2.expert_used_count u32 = 8 llama_model_loader: - kv 12: deepseek2.leading_dense_block_count u32 = 3 llama_model_loader: - kv 13: deepseek2.vocab_size u32 = 129280 llama_model_loader: - kv 14: deepseek2.attention.q_lora_rank u32 = 1536 llama_model_loader: - kv 15: deepseek2.attention.kv_lora_rank u32 = 512 llama_model_loader: - kv 16: deepseek2.attention.key_length u32 = 192 llama_model_loader: - kv 17: deepseek2.attention.value_length u32 = 128 llama_model_loader: - kv 18: deepseek2.expert_feed_forward_length u32 = 2048 llama_model_loader: - kv 19: deepseek2.expert_count u32 = 256 llama_model_loader: - kv 20: deepseek2.expert_shared_count u32 = 1 llama_model_loader: - kv 21: deepseek2.expert_weights_scale f32 = 2.500000 llama_model_loader: - kv 22: deepseek2.expert_weights_norm bool = true llama_model_loader: - kv 23: deepseek2.expert_gating_func u32 = 2 llama_model_loader: - kv 24: deepseek2.rope.dimension_count u32 = 64 llama_model_loader: - kv 25: deepseek2.rope.scaling.type str = yarn llama_model_loader: - kv 26: deepseek2.rope.scaling.factor f32 = 40.000000 llama_model_loader: - kv 27: deepseek2.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 28: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.100000 llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 30: tokenizer.ggml.pre str = deepseek-v3 llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,129280] = ["<｜begin▁of▁sentence｜>", "<�... llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,129280] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,127741] = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e... llama_model_loader: - kv 34: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 35: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 36: tokenizer.ggml.padding_token_id u32 = 1 llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 38: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 39: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 40: general.quantization_version u32 = 2 llama_model_loader: - kv 41: general.file_type u32 = 15 llama_model_loader: - type f32: 361 tensors llama_model_loader: - type q4_K: 606 tensors llama_model_loader: - type q6_K: 58 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 376.65 GiB (4.82 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 818 load: token to piece cache size = 0.8223 MB print_info: arch = deepseek2 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 671.03 B print_info: general.name = n/a print_info: n_layer_dense_lead = 0 print_info: n_lora_q = 0 print_info: n_lora_kv = 0 print_info: n_ff_exp = 0 print_info: n_expert_shared = 0 print_info: expert_weights_scale = 0.0 print_info: expert_weights_norm = 0 print_info: expert_gating_func = unknown print_info: rope_yarn_log_mul = 0.0000 print_info: vocab type = BPE print_info: n_vocab = 129280 print_info: n_merges = 127741 print_info: BOS token = 0 '<｜begin▁of▁sentence｜>' print_info: EOS token = 1 '<｜end▁of▁sentence｜>' print_info: EOT token = 1 '<｜end▁of▁sentence｜>' print_info: PAD token = 1 '<｜end▁of▁sentence｜>' print_info: LF token = 201 'Ċ' print_info: FIM PRE token = 128801 '<｜fim▁begin｜>' print_info: FIM SUF token = 128800 '<｜fim▁hole｜>' print_info: FIM MID token = 128802 '<｜fim▁end｜>' print_info: EOG token = 1 '<｜end▁of▁sentence｜>' print_info: max token length = 256 llama_model_load: vocab only - skipping tensors time=2025-04-21T12:31:00.947+03:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model ~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 --ctx-size 8192 --batch-size 512 --n-gpu-layers 62 --threads 96 --parallel 4 --tensor-split 10,11,11,8,7,7,4,4 --port 37411" time=2025-04-21T12:31:00.947+03:00 level=INFO source=sched.go:451 msg="loaded runners" count=6 time=2025-04-21T12:31:00.947+03:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding" time=2025-04-21T12:31:00.947+03:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" time=2025-04-21T12:31:00.959+03:00 level=INFO source=runner.go:853 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 8 CUDA devices: Device 0: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 1: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 2: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 3: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 4: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 5: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 6: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes Device 7: NVIDIA H100 80GB HBM3, compute capability 9.0, VMM: yes load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so time=2025-04-21T12:31:03.531+03:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 CUDA.1.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.1.USE_GRAPHS=1 CUDA.1.PEER_MAX_BATCH_SIZE=128 CUDA.2.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.2.USE_GRAPHS=1 CUDA.2.PEER_MAX_BATCH_SIZE=128 CUDA.3.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.3.USE_GRAPHS=1 CUDA.3.PEER_MAX_BATCH_SIZE=128 CUDA.4.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.4.USE_GRAPHS=1 CUDA.4.PEER_MAX_BATCH_SIZE=128 CUDA.5.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.5.USE_GRAPHS=1 CUDA.5.PEER_MAX_BATCH_SIZE=128 CUDA.6.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.6.USE_GRAPHS=1 CUDA.6.PEER_MAX_BATCH_SIZE=128 CUDA.7.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.7.USE_GRAPHS=1 CUDA.7.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2025-04-21T12:31:03.532+03:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:37411" time=2025-04-21T12:31:03.706+03:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA H100 80GB HBM3) - 80580 MiB free llama_model_load_from_file_impl: using device CUDA1 (NVIDIA H100 80GB HBM3) - 80580 MiB free llama_model_load_from_file_impl: using device CUDA2 (NVIDIA H100 80GB HBM3) - 80580 MiB free llama_model_load_from_file_impl: using device CUDA3 (NVIDIA H100 80GB HBM3) - 69911 MiB free llama_model_load_from_file_impl: using device CUDA4 (NVIDIA H100 80GB HBM3) - 59033 MiB free llama_model_load_from_file_impl: using device CUDA5 (NVIDIA H100 80GB HBM3) - 59033 MiB free llama_model_load_from_file_impl: using device CUDA6 (NVIDIA H100 80GB HBM3) - 37089 MiB free llama_model_load_from_file_impl: using device CUDA7 (NVIDIA H100 80GB HBM3) - 37089 MiB free llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from ~/.ollama/models/blobs/sha256-d83c18fb2a2ccca56d641920f01e6fe533dfb3fcf4b77c007c931497cd24a517 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = deepseek2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.size_label str = 256x20B llama_model_loader: - kv 3: deepseek2.block_count u32 = 61 llama_model_loader: - kv 4: deepseek2.context_length u32 = 163840 llama_model_loader: - kv 5: deepseek2.embedding_length u32 = 7168 llama_model_loader: - kv 6: deepseek2.feed_forward_length u32 = 18432 llama_model_loader: - kv 7: deepseek2.attention.head_count u32 = 128 llama_model_loader: - kv 8: deepseek2.attention.head_count_kv u32 = 128 llama_model_loader: - kv 9: deepseek2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 10: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 11: deepseek2.expert_used_count u32 = 8 llama_model_loader: - kv 12: deepseek2.leading_dense_block_count u32 = 3 llama_model_loader: - kv 13: deepseek2.vocab_size u32 = 129280 llama_model_loader: - kv 14: deepseek2.attention.q_lora_rank u32 = 1536 llama_model_loader: - kv 15: deepseek2.attention.kv_lora_rank u32 = 512 llama_model_loader: - kv 16: deepseek2.attention.key_length u32 = 192 llama_model_loader: - kv 17: deepseek2.attention.value_length u32 = 128 llama_model_loader: - kv 18: deepseek2.expert_feed_forward_length u32 = 2048 llama_model_loader: - kv 19: deepseek2.expert_count u32 = 256 llama_model_loader: - kv 20: deepseek2.expert_shared_count u32 = 1 llama_model_loader: - kv 21: deepseek2.expert_weights_scale f32 = 2.500000 llama_model_loader: - kv 22: deepseek2.expert_weights_norm bool = true llama_model_loader: - kv 23: deepseek2.expert_gating_func u32 = 2 llama_model_loader: - kv 24: deepseek2.rope.dimension_count u32 = 64 llama_model_loader: - kv 25: deepseek2.rope.scaling.type str = yarn llama_model_loader: - kv 26: deepseek2.rope.scaling.factor f32 = 40.000000 llama_model_loader: - kv 27: deepseek2.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 28: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.100000 llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 30: tokenizer.ggml.pre str = deepseek-v3 llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,129280] = ["<｜begin▁of▁sentence｜>", "<�... llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,129280] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,127741] = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e... llama_model_loader: - kv 34: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 35: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 36: tokenizer.ggml.padding_token_id u32 = 1 llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 38: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 39: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 40: general.quantization_version u32 = 2 llama_model_loader: - kv 41: general.file_type u32 = 15 llama_model_loader: - type f32: 361 tensors llama_model_loader: - type q4_K: 606 tensors llama_model_loader: - type q6_K: 58 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 376.65 GiB (4.82 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 818 load: token to piece cache size = 0.8223 MB print_info: arch = deepseek2 print_info: vocab_only = 0 print_info: n_ctx_train = 163840 print_info: n_embd = 7168 print_info: n_layer = 61 print_info: n_head = 128 print_info: n_head_kv = 128 print_info: n_rot = 64 print_info: n_swa = 0 print_info: n_embd_head_k = 192 print_info: n_embd_head_v = 128 print_info: n_gqa = 1 print_info: n_embd_k_gqa = 24576 print_info: n_embd_v_gqa = 16384 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-06 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: n_ff = 18432 print_info: n_expert = 256 print_info: n_expert_used = 8 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 0 print_info: rope scaling = yarn print_info: freq_base_train = 10000.0 print_info: freq_scale_train = 0.025 print_info: n_ctx_orig_yarn = 4096 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 671B print_info: model params = 671.03 B print_info: general.name = n/a print_info: n_layer_dense_lead = 3 print_info: n_lora_q = 1536 print_info: n_lora_kv = 512 print_info: n_ff_exp = 2048 print_info: n_expert_shared = 1 print_info: expert_weights_scale = 2.5 print_info: expert_weights_norm = 1 print_info: expert_gating_func = sigmoid print_info: rope_yarn_log_mul = 0.1000 print_info: vocab type = BPE print_info: n_vocab = 129280 print_info: n_merges = 127741 print_info: BOS token = 0 '<｜begin▁of▁sentence｜>' print_info: EOS token = 1 '<｜end▁of▁sentence｜>' print_info: EOT token = 1 '<｜end▁of▁sentence｜>' print_info: PAD token = 1 '<｜end▁of▁sentence｜>' print_info: LF token = 201 'Ċ' print_info: FIM PRE token = 128801 '<｜fim▁begin｜>' print_info: FIM SUF token = 128800 '<｜fim▁hole｜>' print_info: FIM MID token = 128802 '<｜fim▁end｜>' print_info: EOG token = 1 '<｜end▁of▁sentence｜>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (mmap = true) load_tensors: offloading 61 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 62/62 layers to GPU load_tensors: CUDA0 model buffer size = 48928.09 MiB load_tensors: CUDA1 model buffer size = 70752.48 MiB load_tensors: CUDA2 model buffer size = 71680.09 MiB load_tensors: CUDA3 model buffer size = 52215.30 MiB load_tensors: CUDA4 model buffer size = 45108.64 MiB load_tensors: CUDA5 model buffer size = 46036.25 MiB load_tensors: CUDA6 model buffer size = 28426.68 MiB load_tensors: CUDA7 model buffer size = 22044.99 MiB load_tensors: CPU_Mapped model buffer size = 497.11 MiB llama_init_from_model: n_seq_max = 4 llama_init_from_model: n_ctx = 8192 llama_init_from_model: n_ctx_per_seq = 2048 llama_init_from_model: n_batch = 2048 llama_init_from_model: n_ubatch = 512 llama_init_from_model: flash_attn = 0 llama_init_from_model: freq_base = 10000.0 llama_init_from_model: freq_scale = 0.025 llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (163840) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 61, can_shift = 0 llama_kv_cache_init: CUDA0 KV buffer size = 6400.00 MiB llama_kv_cache_init: CUDA1 KV buffer size = 7040.00 MiB llama_kv_cache_init: CUDA2 KV buffer size = 7040.00 MiB llama_kv_cache_init: CUDA3 KV buffer size = 5120.00 MiB llama_kv_cache_init: CUDA4 KV buffer size = 4480.00 MiB llama_kv_cache_init: CUDA5 KV buffer size = 4480.00 MiB llama_kv_cache_init: CUDA6 KV buffer size = 2560.00 MiB llama_kv_cache_init: CUDA7 KV buffer size = 1920.00 MiB llama_init_from_model: KV self size = 39040.00 MiB, K (f16): 23424.00 MiB, V (f16): 15616.00 MiB llama_init_from_model: CUDA_Host output buffer size = 2.08 MiB llama_init_from_model: pipeline parallelism enabled (n_copies=4) ggml_backend_cuda_buffer_type_alloc_buffer: allocating 2322.01 MiB on device 2: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA2 buffer of size 2434801664 ggml_backend_cuda_buffer_type_alloc_buffer: allocating 2322.01 MiB on device 2: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA2 buffer of size 2434801664 llama_init_from_model: failed to allocate compute buffers panic: unable to create llama context goroutine 111 [running]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc000544360, {0x3e, 0x0, 0x1, 0x0, {0xc0005010c0, 0x8, 0x8}, 0xc00055e1a0, 0x0}, ...) github.com/ollama/ollama/runner/llamarunner/runner.go:779 +0x369 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/llamarunner/runner.go:887 +0xbd7 time=2025-04-21T12:32:01.411+03:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" time=2025-04-21T12:32:02.192+03:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2" time=2025-04-21T12:32:02.413+03:00 level=ERROR source=sched.go:457 msg="error loading llama server" error="llama runner process has terminated: cudaMalloc failed: out of memory" [GIN] 2025/04/21 - 12:32:02 | 500 | 2m18s | 127.0.0.1 | POST "/api/generate" Generation error: llama runner process has terminated: cudaMalloc failed: out of memory (status code: 500) </code> <br> </details>
GiteaMirror commented 2026-04-29 01:20:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 21, 2025):

time=2025-04-21T12:31:00.791+03:00 level=WARN source=server.go:178 msg="flash attention enabled but not supported by model"

Setting OLLAMA_FLASH_ATTENTION=1 should have no effect. It would be interesting to see the logs from when OLLAMA_FLASH_ATTENTION is not set.

ggml_backend_cuda_buffer_type_alloc_buffer: allocating 2322.01 MiB on device 2: cudaMalloc failed: out of memory
ggml_gallocr_reserve_n: failed to allocate CUDA2 buffer of size 2434801664

ollama OOMed allocating VRAM on device 2.

time=2025-04-21T12:31:00.791+03:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=62 layers.offload=62 layers.split=10,11,11,8,7,7,4,4 memory.available="[78.7 GiB 78.7 GiB 78.7 GiB 68.3 GiB 57.6 GiB 57.6 GiB 35.6 GiB 35.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="449.4 GiB" memory.required.partial="449.4 GiB" memory.required.kv="38.1 GiB" memory.required.allocations="[70.7 GiB 69.6 GiB 75.6 GiB 61.3 GiB 54.6 GiB 52.8 GiB 32.8 GiB 31.9 GiB]" memory.weights.total="376.2 GiB" memory.weights.repeating="375.5 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="3.0 GiB" memory.graph.partial="3.0 GiB"
...
load_tensors:        CUDA2 model buffer size = 71680.09 MiB

Device 2 had the largest allocation, 75.6G out of 78.7G available. It looks like the model failed during loading (rather than inference) so it's likely not a transient allocation that caused the failure. You can try reducing the occurrence of this using some of the mitigations listed here. Improving the memory estimation is a work in progress.

<!-- gh-comment-id:2818990602 --> @rick-github commented on GitHub (Apr 21, 2025): ``` time=2025-04-21T12:31:00.791+03:00 level=WARN source=server.go:178 msg="flash attention enabled but not supported by model" ``` Setting `OLLAMA_FLASH_ATTENTION=1` should have no effect. It would be interesting to see the logs from when `OLLAMA_FLASH_ATTENTION` is not set. ``` ggml_backend_cuda_buffer_type_alloc_buffer: allocating 2322.01 MiB on device 2: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA2 buffer of size 2434801664 ``` ollama OOMed allocating VRAM on device 2. ``` time=2025-04-21T12:31:00.791+03:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=62 layers.offload=62 layers.split=10,11,11,8,7,7,4,4 memory.available="[78.7 GiB 78.7 GiB 78.7 GiB 68.3 GiB 57.6 GiB 57.6 GiB 35.6 GiB 35.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="449.4 GiB" memory.required.partial="449.4 GiB" memory.required.kv="38.1 GiB" memory.required.allocations="[70.7 GiB 69.6 GiB 75.6 GiB 61.3 GiB 54.6 GiB 52.8 GiB 32.8 GiB 31.9 GiB]" memory.weights.total="376.2 GiB" memory.weights.repeating="375.5 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="3.0 GiB" memory.graph.partial="3.0 GiB" ... load_tensors: CUDA2 model buffer size = 71680.09 MiB ``` Device 2 had the largest allocation, 75.6G out of 78.7G available. It looks like the model failed during loading (rather than inference) so it's likely not a transient allocation that caused the failure. You can try reducing the occurrence of this using some of the mitigations listed [here](https://github.com/ollama/ollama/issues/8597#issuecomment-2614533288). Improving the memory estimation is a [work in progress](https://github.com/ollama/ollama/issues/10041#issuecomment-2816399723).
GiteaMirror commented 2026-04-29 01:20:49 -05:00
Author
Owner
Copy Link

@carbolymer commented on GitHub (Apr 29, 2025):

I have RTX 3050 Ti mobile GPU with 4GB RAM. I can run larger models like qwen3:14b (mostly on CPU) just fine, but this one for example errors out:

$ ollama run qwen3:8b 
Error: llama runner process has terminated: cudaMalloc failed: out of memory
ggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 838447104
Log 
Apr 29 12:31:28 gravitino ollama[1654667]:         /build/ollama/src/ollama/runner/llamarunner/runner.go:779 +0x369
Apr 29 12:31:28 gravitino ollama[1654667]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
Apr 29 12:31:28 gravitino ollama[1654667]:         /build/ollama/src/ollama/runner/llamarunner/runner.go:887 +0xbd7
Apr 29 12:31:28 gravitino ollama[1654667]: time=2025-04-29T12:31:28.270+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
Apr 29 12:31:28 gravitino ollama[1654667]: time=2025-04-29T12:31:28.357+02:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2"
Apr 29 12:31:28 gravitino ollama[1654667]: time=2025-04-29T12:31:28.521+02:00 level=ERROR source=sched.go:457 msg="error loading llama server" error="llama runner process has terminated: cudaMalloc failed: out of memory\nggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 838447104"
Apr 29 12:31:28 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:28 | 500 |  3.058028071s |       127.0.0.1 | POST     "/api/generate"
Apr 29 12:31:33 gravitino ollama[1654667]: time=2025-04-29T12:31:33.668+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.147323348 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f
Apr 29 12:31:33 gravitino ollama[1654667]: time=2025-04-29T12:31:33.919+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.398024401 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f
Apr 29 12:31:34 gravitino ollama[1654667]: time=2025-04-29T12:31:34.169+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.647933446 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f
Apr 29 12:31:48 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:48 | 200 |      17.188µs |       127.0.0.1 | HEAD     "/"
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.055+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.065+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
Apr 29 12:31:48 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:48 | 200 |   21.863514ms |       127.0.0.1 | POST     "/api/show"
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.077+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.267+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.276+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=INFO source=server.go:105 msg="system memory" total="62.5 GiB" free="41.9 GiB" free_swap="32.0 GiB"
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=22 layers.split="" memory.available="[3.4 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="3.4 GiB" memory.required.kv="288.0 MiB" memory.required.allocations="[3.4 GiB]" memory.weights.total="4.5 GiB" memory.weights.repeating="4.1 GiB" memory.weights.nonrepeating="486.9 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB"
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: loaded meta data with 28 key-value pairs and 399 tensors from /var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f (version GGUF V3 (latest))
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   0:                       general.architecture str              = qwen3
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   1:                               general.type str              = model
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   2:                               general.name str              = Qwen3 8B
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   3:                           general.basename str              = Qwen3
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   4:                         general.size_label str              = 8B
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   5:                            general.license str              = apache-2.0
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   6:                          qwen3.block_count u32              = 36
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   7:                       qwen3.context_length u32              = 40960
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   8:                     qwen3.embedding_length u32              = 4096
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   9:                  qwen3.feed_forward_length u32              = 12288
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  10:                 qwen3.attention.head_count u32              = 32
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  11:              qwen3.attention.head_count_kv u32              = 8
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  12:                       qwen3.rope.freq_base f32              = 1000000.000000
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  13:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  14:                 qwen3.attention.key_length u32              = 128
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  15:               qwen3.attention.value_length u32              = 128
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  16:                       tokenizer.ggml.model str              = gpt2
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  17:                         tokenizer.ggml.pre str              = qwen2
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  18:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  19:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  20:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  21:                tokenizer.ggml.eos_token_id u32              = 151645
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  22:            tokenizer.ggml.padding_token_id u32              = 151643
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 151643
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  24:               tokenizer.ggml.add_bos_token bool             = false
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  26:               general.quantization_version u32              = 2
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  27:                          general.file_type u32              = 15
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type  f32:  145 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type  f16:   36 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q4_K:  199 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q6_K:   19 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file format = GGUF V3 (latest)
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file type   = Q4_K - Medium
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file size   = 4.86 GiB (5.10 BPW)
Apr 29 12:31:48 gravitino ollama[1654667]: load: special tokens cache size = 26
Apr 29 12:31:48 gravitino ollama[1654667]: load: token to piece cache size = 0.9311 MB
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: arch             = qwen3
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab_only       = 1
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model type       = ?B
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model params     = 8.19 B
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: general.name     = Qwen3 8B
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab type       = BPE
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_vocab          = 151936
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_merges         = 151387
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: BOS token        = 151643 '<|endoftext|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOS token        = 151645 '<|im_end|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOT token        = 151645 '<|im_end|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: PAD token        = 151643 '<|endoftext|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: LF token         = 198 'Ċ'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM MID token    = 151660 '<|fim_middle|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PAD token    = 151662 '<|fim_pad|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM REP token    = 151663 '<|repo_name|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SEP token    = 151664 '<|file_sep|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151643 '<|endoftext|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151645 '<|im_end|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151662 '<|fim_pad|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151663 '<|repo_name|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151664 '<|file_sep|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: max token length = 256
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_load: vocab only - skipping tensors
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model /var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --ctx-size 2048 --batch-size 512 --n-gpu-layers 22 --threads 6 --parallel 1 --port 34915"
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=sched.go:451 msg="loaded runners" count=1
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding"
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.597+02:00 level=INFO source=runner.go:853 msg="starting go runner"
Apr 29 12:31:48 gravitino ollama[1654667]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Apr 29 12:31:48 gravitino ollama[1654667]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Apr 29 12:31:48 gravitino ollama[1654667]: ggml_cuda_init: found 1 CUDA devices:
Apr 29 12:31:48 gravitino ollama[1654667]:   Device 0: NVIDIA GeForce RTX 3050 Ti Laptop GPU, compute capability 8.6, VMM: yes
Apr 29 12:31:48 gravitino ollama[1654667]: load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so
Apr 29 12:31:48 gravitino ollama[1654667]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.651+02:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,530,600,610,620,700,720,750,800,860,870,890,900 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.651+02:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:34915"
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3050 Ti Laptop GPU) - 3489 MiB free
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: loaded meta data with 28 key-value pairs and 399 tensors from /var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f (version GGUF V3 (latest))
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   0:                       general.architecture str              = qwen3
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   1:                               general.type str              = model
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   2:                               general.name str              = Qwen3 8B
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   3:                           general.basename str              = Qwen3
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   4:                         general.size_label str              = 8B
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   5:                            general.license str              = apache-2.0
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   6:                          qwen3.block_count u32              = 36
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   7:                       qwen3.context_length u32              = 40960
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   8:                     qwen3.embedding_length u32              = 4096
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv   9:                  qwen3.feed_forward_length u32              = 12288
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  10:                 qwen3.attention.head_count u32              = 32
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  11:              qwen3.attention.head_count_kv u32              = 8
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  12:                       qwen3.rope.freq_base f32              = 1000000.000000
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  13:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  14:                 qwen3.attention.key_length u32              = 128
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  15:               qwen3.attention.value_length u32              = 128
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  16:                       tokenizer.ggml.model str              = gpt2
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  17:                         tokenizer.ggml.pre str              = qwen2
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  18:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  19:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  20:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  21:                tokenizer.ggml.eos_token_id u32              = 151645
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  22:            tokenizer.ggml.padding_token_id u32              = 151643
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 151643
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  24:               tokenizer.ggml.add_bos_token bool             = false
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  26:               general.quantization_version u32              = 2
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv  27:                          general.file_type u32              = 15
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type  f32:  145 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type  f16:   36 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q4_K:  199 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q6_K:   19 tensors
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file format = GGUF V3 (latest)
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file type   = Q4_K - Medium
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file size   = 4.86 GiB (5.10 BPW)
Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.840+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
Apr 29 12:31:48 gravitino ollama[1654667]: load: special tokens cache size = 26
Apr 29 12:31:48 gravitino ollama[1654667]: load: token to piece cache size = 0.9311 MB
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: arch             = qwen3
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab_only       = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_ctx_train      = 40960
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd           = 4096
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_layer          = 36
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_head           = 32
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_head_kv        = 8
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_rot            = 128
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_swa            = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_swa_pattern    = 1
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_head_k    = 128
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_head_v    = 128
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_gqa            = 4
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_k_gqa     = 1024
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_v_gqa     = 1024
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_norm_eps       = 0.0e+00
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_norm_rms_eps   = 1.0e-06
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_clamp_kqv      = 0.0e+00
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_max_alibi_bias = 0.0e+00
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_logit_scale    = 0.0e+00
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_attn_scale     = 0.0e+00
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_ff             = 12288
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_expert         = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_expert_used    = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: causal attn      = 1
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: pooling type     = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: rope type        = 2
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: rope scaling     = linear
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: freq_base_train  = 1000000.0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: freq_scale_train = 1
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_ctx_orig_yarn  = 40960
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: rope_finetuned   = unknown
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_d_conv       = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_d_inner      = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_d_state      = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_dt_rank      = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_dt_b_c_rms   = 0
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model type       = ?B
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model params     = 8.19 B
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: general.name     = Qwen3 8B
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab type       = BPE
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_vocab          = 151936
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_merges         = 151387
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: BOS token        = 151643 '<|endoftext|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOS token        = 151645 '<|im_end|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOT token        = 151645 '<|im_end|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: PAD token        = 151643 '<|endoftext|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: LF token         = 198 'Ċ'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM MID token    = 151660 '<|fim_middle|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PAD token    = 151662 '<|fim_pad|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM REP token    = 151663 '<|repo_name|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SEP token    = 151664 '<|file_sep|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151643 '<|endoftext|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151645 '<|im_end|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151662 '<|fim_pad|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151663 '<|repo_name|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token        = 151664 '<|file_sep|>'
Apr 29 12:31:48 gravitino ollama[1654667]: print_info: max token length = 256
Apr 29 12:31:48 gravitino ollama[1654667]: load_tensors: loading model tensors, this can take a while... (mmap = true)
^OApr 29 12:31:49 gravitino ollama[1654667]: load_tensors: offloading 22 repeating layers to GPU
Apr 29 12:31:49 gravitino ollama[1654667]: load_tensors: offloaded 22/37 layers to GPU
Apr 29 12:31:49 gravitino ollama[1654667]: load_tensors:        CUDA0 model buffer size =  2540.33 MiB
Apr 29 12:31:49 gravitino ollama[1654667]: load_tensors:   CPU_Mapped model buffer size =  2437.29 MiB
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: constructing llama_context
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_seq_max     = 1
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ctx         = 2048
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ctx_per_seq = 2048
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_batch       = 512
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ubatch      = 512
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: causal_attn   = 1
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: flash_attn    = 0
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: freq_base     = 1000000.0
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: freq_scale    = 1
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ctx_per_seq (2048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context:        CPU  output buffer size =     0.60 MiB
Apr 29 12:31:50 gravitino ollama[1654667]: init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1
Apr 29 12:31:50 gravitino ollama[1654667]: init:      CUDA0 KV buffer size =   176.00 MiB
Apr 29 12:31:50 gravitino ollama[1654667]: init:        CPU KV buffer size =   112.00 MiB
Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: KV self size  =  288.00 MiB, K (f16):  144.00 MiB, V (f16):  144.00 MiB
Apr 29 12:31:50 gravitino ollama[1654667]: ggml_backend_cuda_buffer_type_alloc_buffer: allocating 799.61 MiB on device 0: cudaMalloc failed: out of memory
Apr 29 12:31:50 gravitino ollama[1654667]: ggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 838447104
Apr 29 12:31:50 gravitino ollama[1654667]: llama_init_from_model: failed to initialize the context: failed to allocate compute pp buffers
Apr 29 12:31:50 gravitino ollama[1654667]: panic: unable to create llama context
Apr 29 12:31:50 gravitino ollama[1654667]: goroutine 47 [running]:
Apr 29 12:31:50 gravitino ollama[1654667]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc00015a000, {0x16, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc0000447f0, 0x0}, ...)
Apr 29 12:31:50 gravitino ollama[1654667]:         /build/ollama/src/ollama/runner/llamarunner/runner.go:779 +0x369
Apr 29 12:31:50 gravitino ollama[1654667]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
Apr 29 12:31:50 gravitino ollama[1654667]:         /build/ollama/src/ollama/runner/llamarunner/runner.go:887 +0xbd7
Apr 29 12:31:50 gravitino ollama[1654667]: time=2025-04-29T12:31:50.095+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
Apr 29 12:31:50 gravitino ollama[1654667]: time=2025-04-29T12:31:50.212+02:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2"
Apr 29 12:31:50 gravitino ollama[1654667]: time=2025-04-29T12:31:50.345+02:00 level=ERROR source=sched.go:457 msg="error loading llama server" error="llama runner process has terminated: cudaMalloc failed: out of memory"
Apr 29 12:31:50 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:50 | 500 |  2.279007182s |       127.0.0.1 | POST     "/api/generate"
Apr 29 12:31:55 gravitino ollama[1654667]: time=2025-04-29T12:31:55.497+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.151842467 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f
Apr 29 12:31:55 gravitino ollama[1654667]: time=2025-04-29T12:31:55.747+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.401755723 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f
Apr 29 12:31:55 gravitino ollama[1654667]: time=2025-04-29T12:31:55.997+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.651718681 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f
<!-- gh-comment-id:2838270796 --> @carbolymer commented on GitHub (Apr 29, 2025): I have RTX 3050 Ti mobile GPU with 4GB RAM. I can run larger models like `qwen3:14b` (mostly on CPU) just fine, but this one for example errors out: ``` $ ollama run qwen3:8b Error: llama runner process has terminated: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 838447104 ``` <details> <summary>Log</summary> Apr 29 12:31:28 gravitino ollama[1654667]: /build/ollama/src/ollama/runner/llamarunner/runner.go:779 +0x369 Apr 29 12:31:28 gravitino ollama[1654667]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 Apr 29 12:31:28 gravitino ollama[1654667]: /build/ollama/src/ollama/runner/llamarunner/runner.go:887 +0xbd7 Apr 29 12:31:28 gravitino ollama[1654667]: time=2025-04-29T12:31:28.270+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" Apr 29 12:31:28 gravitino ollama[1654667]: time=2025-04-29T12:31:28.357+02:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2" Apr 29 12:31:28 gravitino ollama[1654667]: time=2025-04-29T12:31:28.521+02:00 level=ERROR source=sched.go:457 msg="error loading llama server" error="llama runner process has terminated: cudaMalloc failed: out of memory\nggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 838447104" Apr 29 12:31:28 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:28 | 500 | 3.058028071s | 127.0.0.1 | POST "/api/generate" Apr 29 12:31:33 gravitino ollama[1654667]: time=2025-04-29T12:31:33.668+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.147323348 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f Apr 29 12:31:33 gravitino ollama[1654667]: time=2025-04-29T12:31:33.919+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.398024401 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f Apr 29 12:31:34 gravitino ollama[1654667]: time=2025-04-29T12:31:34.169+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.647933446 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f Apr 29 12:31:48 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:48 | 200 | 17.188µs | 127.0.0.1 | HEAD "/" Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.055+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.065+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 Apr 29 12:31:48 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:48 | 200 | 21.863514ms | 127.0.0.1 | POST "/api/show" Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.077+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.267+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.276+02:00 level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.277+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=INFO source=server.go:105 msg="system memory" total="62.5 GiB" free="41.9 GiB" free_swap="32.0 GiB" Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen3.vision.block_count default=0 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=22 layers.split="" memory.available="[3.4 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="3.4 GiB" memory.required.kv="288.0 MiB" memory.required.allocations="[3.4 GiB]" memory.weights.total="4.5 GiB" memory.weights.repeating="4.1 GiB" memory.weights.nonrepeating="486.9 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: loaded meta data with 28 key-value pairs and 399 tensors from /var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f (version GGUF V3 (latest)) Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 0: general.architecture str = qwen3 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 1: general.type str = model Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 2: general.name str = Qwen3 8B Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 3: general.basename str = Qwen3 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 4: general.size_label str = 8B Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 5: general.license str = apache-2.0 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 6: qwen3.block_count u32 = 36 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 7: qwen3.context_length u32 = 40960 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 8: qwen3.embedding_length u32 = 4096 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 12288 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 32 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 16: tokenizer.ggml.model str = gpt2 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 17: tokenizer.ggml.pre str = qwen2 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 19: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 20: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 151645 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 151643 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 151643 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 25: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 26: general.quantization_version u32 = 2 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 27: general.file_type u32 = 15 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type f32: 145 tensors Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type f16: 36 tensors Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q4_K: 199 tensors Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q6_K: 19 tensors Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file format = GGUF V3 (latest) Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file type = Q4_K - Medium Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file size = 4.86 GiB (5.10 BPW) Apr 29 12:31:48 gravitino ollama[1654667]: load: special tokens cache size = 26 Apr 29 12:31:48 gravitino ollama[1654667]: load: token to piece cache size = 0.9311 MB Apr 29 12:31:48 gravitino ollama[1654667]: print_info: arch = qwen3 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab_only = 1 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model type = ?B Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model params = 8.19 B Apr 29 12:31:48 gravitino ollama[1654667]: print_info: general.name = Qwen3 8B Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab type = BPE Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_vocab = 151936 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_merges = 151387 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: BOS token = 151643 '<|endoftext|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOS token = 151645 '<|im_end|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOT token = 151645 '<|im_end|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: PAD token = 151643 '<|endoftext|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: LF token = 198 'Ċ' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM MID token = 151660 '<|fim_middle|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PAD token = 151662 '<|fim_pad|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM REP token = 151663 '<|repo_name|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SEP token = 151664 '<|file_sep|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151643 '<|endoftext|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151645 '<|im_end|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151662 '<|fim_pad|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151663 '<|repo_name|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151664 '<|file_sep|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: max token length = 256 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_load: vocab only - skipping tensors Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --model /var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --ctx-size 2048 --batch-size 512 --n-gpu-layers 22 --threads 6 --parallel 1 --port 34915" Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=sched.go:451 msg="loaded runners" count=1 Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding" Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.589+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.597+02:00 level=INFO source=runner.go:853 msg="starting go runner" Apr 29 12:31:48 gravitino ollama[1654667]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Apr 29 12:31:48 gravitino ollama[1654667]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Apr 29 12:31:48 gravitino ollama[1654667]: ggml_cuda_init: found 1 CUDA devices: Apr 29 12:31:48 gravitino ollama[1654667]: Device 0: NVIDIA GeForce RTX 3050 Ti Laptop GPU, compute capability 8.6, VMM: yes Apr 29 12:31:48 gravitino ollama[1654667]: load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so Apr 29 12:31:48 gravitino ollama[1654667]: load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.651+02:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,530,600,610,620,700,720,750,800,860,870,890,900 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.651+02:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:34915" Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3050 Ti Laptop GPU) - 3489 MiB free Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: loaded meta data with 28 key-value pairs and 399 tensors from /var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f (version GGUF V3 (latest)) Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 0: general.architecture str = qwen3 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 1: general.type str = model Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 2: general.name str = Qwen3 8B Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 3: general.basename str = Qwen3 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 4: general.size_label str = 8B Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 5: general.license str = apache-2.0 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 6: qwen3.block_count u32 = 36 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 7: qwen3.context_length u32 = 40960 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 8: qwen3.embedding_length u32 = 4096 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 12288 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 32 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 16: tokenizer.ggml.model str = gpt2 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 17: tokenizer.ggml.pre str = qwen2 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 19: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 20: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 151645 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 151643 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 151643 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 25: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 26: general.quantization_version u32 = 2 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - kv 27: general.file_type u32 = 15 Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type f32: 145 tensors Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type f16: 36 tensors Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q4_K: 199 tensors Apr 29 12:31:48 gravitino ollama[1654667]: llama_model_loader: - type q6_K: 19 tensors Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file format = GGUF V3 (latest) Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file type = Q4_K - Medium Apr 29 12:31:48 gravitino ollama[1654667]: print_info: file size = 4.86 GiB (5.10 BPW) Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.840+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" Apr 29 12:31:48 gravitino ollama[1654667]: load: special tokens cache size = 26 Apr 29 12:31:48 gravitino ollama[1654667]: load: token to piece cache size = 0.9311 MB Apr 29 12:31:48 gravitino ollama[1654667]: print_info: arch = qwen3 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab_only = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_ctx_train = 40960 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd = 4096 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_layer = 36 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_head = 32 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_head_kv = 8 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_rot = 128 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_swa = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_swa_pattern = 1 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_head_k = 128 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_head_v = 128 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_gqa = 4 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_k_gqa = 1024 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_embd_v_gqa = 1024 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_norm_eps = 0.0e+00 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_norm_rms_eps = 1.0e-06 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_clamp_kqv = 0.0e+00 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_max_alibi_bias = 0.0e+00 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_logit_scale = 0.0e+00 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: f_attn_scale = 0.0e+00 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_ff = 12288 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_expert = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_expert_used = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: causal attn = 1 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: pooling type = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: rope type = 2 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: rope scaling = linear Apr 29 12:31:48 gravitino ollama[1654667]: print_info: freq_base_train = 1000000.0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: freq_scale_train = 1 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_ctx_orig_yarn = 40960 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: rope_finetuned = unknown Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_d_conv = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_d_inner = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_d_state = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_dt_rank = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: ssm_dt_b_c_rms = 0 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model type = ?B Apr 29 12:31:48 gravitino ollama[1654667]: print_info: model params = 8.19 B Apr 29 12:31:48 gravitino ollama[1654667]: print_info: general.name = Qwen3 8B Apr 29 12:31:48 gravitino ollama[1654667]: print_info: vocab type = BPE Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_vocab = 151936 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: n_merges = 151387 Apr 29 12:31:48 gravitino ollama[1654667]: print_info: BOS token = 151643 '<|endoftext|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOS token = 151645 '<|im_end|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOT token = 151645 '<|im_end|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: PAD token = 151643 '<|endoftext|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: LF token = 198 'Ċ' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM MID token = 151660 '<|fim_middle|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM PAD token = 151662 '<|fim_pad|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM REP token = 151663 '<|repo_name|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: FIM SEP token = 151664 '<|file_sep|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151643 '<|endoftext|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151645 '<|im_end|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151662 '<|fim_pad|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151663 '<|repo_name|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: EOG token = 151664 '<|file_sep|>' Apr 29 12:31:48 gravitino ollama[1654667]: print_info: max token length = 256 Apr 29 12:31:48 gravitino ollama[1654667]: load_tensors: loading model tensors, this can take a while... (mmap = true) ^OApr 29 12:31:49 gravitino ollama[1654667]: load_tensors: offloading 22 repeating layers to GPU Apr 29 12:31:49 gravitino ollama[1654667]: load_tensors: offloaded 22/37 layers to GPU Apr 29 12:31:49 gravitino ollama[1654667]: load_tensors: CUDA0 model buffer size = 2540.33 MiB Apr 29 12:31:49 gravitino ollama[1654667]: load_tensors: CPU_Mapped model buffer size = 2437.29 MiB Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: constructing llama_context Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_seq_max = 1 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ctx = 2048 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ctx_per_seq = 2048 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_batch = 512 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ubatch = 512 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: causal_attn = 1 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: flash_attn = 0 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: freq_base = 1000000.0 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: freq_scale = 1 Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: n_ctx_per_seq (2048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: CPU output buffer size = 0.60 MiB Apr 29 12:31:50 gravitino ollama[1654667]: init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1 Apr 29 12:31:50 gravitino ollama[1654667]: init: CUDA0 KV buffer size = 176.00 MiB Apr 29 12:31:50 gravitino ollama[1654667]: init: CPU KV buffer size = 112.00 MiB Apr 29 12:31:50 gravitino ollama[1654667]: llama_context: KV self size = 288.00 MiB, K (f16): 144.00 MiB, V (f16): 144.00 MiB Apr 29 12:31:50 gravitino ollama[1654667]: ggml_backend_cuda_buffer_type_alloc_buffer: allocating 799.61 MiB on device 0: cudaMalloc failed: out of memory Apr 29 12:31:50 gravitino ollama[1654667]: ggml_gallocr_reserve_n: failed to allocate CUDA0 buffer of size 838447104 Apr 29 12:31:50 gravitino ollama[1654667]: llama_init_from_model: failed to initialize the context: failed to allocate compute pp buffers Apr 29 12:31:50 gravitino ollama[1654667]: panic: unable to create llama context Apr 29 12:31:50 gravitino ollama[1654667]: goroutine 47 [running]: Apr 29 12:31:50 gravitino ollama[1654667]: github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc00015a000, {0x16, 0x0, 0x1, 0x0, {0x0, 0x0, 0x0}, 0xc0000447f0, 0x0}, ...) Apr 29 12:31:50 gravitino ollama[1654667]: /build/ollama/src/ollama/runner/llamarunner/runner.go:779 +0x369 Apr 29 12:31:50 gravitino ollama[1654667]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 Apr 29 12:31:50 gravitino ollama[1654667]: /build/ollama/src/ollama/runner/llamarunner/runner.go:887 +0xbd7 Apr 29 12:31:50 gravitino ollama[1654667]: time=2025-04-29T12:31:50.095+02:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" Apr 29 12:31:50 gravitino ollama[1654667]: time=2025-04-29T12:31:50.212+02:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2" Apr 29 12:31:50 gravitino ollama[1654667]: time=2025-04-29T12:31:50.345+02:00 level=ERROR source=sched.go:457 msg="error loading llama server" error="llama runner process has terminated: cudaMalloc failed: out of memory" Apr 29 12:31:50 gravitino ollama[1654667]: [GIN] 2025/04/29 - 12:31:50 | 500 | 2.279007182s | 127.0.0.1 | POST "/api/generate" Apr 29 12:31:55 gravitino ollama[1654667]: time=2025-04-29T12:31:55.497+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.151842467 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f Apr 29 12:31:55 gravitino ollama[1654667]: time=2025-04-29T12:31:55.747+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.401755723 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f Apr 29 12:31:55 gravitino ollama[1654667]: time=2025-04-29T12:31:55.997+02:00 level=WARN source=sched.go:648 msg="gpu VRAM usage didn't recover within timeout" seconds=5.651718681 model=/var/lib/ollama/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f </details>
GiteaMirror commented 2026-04-29 01:20:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 29, 2025):

Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=INFO source=server.go:138 msg=offload
 library=cuda layers.requested=-1 layers.model=37 layers.offload=22 layers.split="" memory.available="[3.4 GiB]"
 memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="3.4 GiB" memory.required.kv="288.0 MiB"
 memory.required.allocations="[3.4 GiB]" memory.weights.total="4.5 GiB" memory.weights.repeating="4.1 GiB"
 memory.weights.nonrepeating="486.9 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB"

ollama allocated 3.4G of the 3.4G available, ie left no room for error. You can mitigate this by using some of the techniques shown here.

<!-- gh-comment-id:2838494882 --> @rick-github commented on GitHub (Apr 29, 2025): ``` Apr 29 12:31:48 gravitino ollama[1654667]: time=2025-04-29T12:31:48.454+02:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=22 layers.split="" memory.available="[3.4 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="3.4 GiB" memory.required.kv="288.0 MiB" memory.required.allocations="[3.4 GiB]" memory.weights.total="4.5 GiB" memory.weights.repeating="4.1 GiB" memory.weights.nonrepeating="486.9 MiB" memory.graph.full="192.0 MiB" memory.graph.partial="192.0 MiB" ``` ollama allocated 3.4G of the 3.4G available, ie left no room for error. You can mitigate this by using some of the techniques shown [here](https://github.com/ollama/ollama/issues/8597#issuecomment-2614533288).
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#52908
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?