github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10119] Ollama hangs while generating a response #53151

New Issue
Closed
opened 2026-04-29 02:07:35 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 02:07:35 -05:00
Owner
Copy Link

Originally created by @jefferson-vm on GitHub (Apr 3, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10119

What is the issue?

Models tested with: Llama3.1:8b, Qwen2.5:14b, Gemma3:12b

Issue: Ollama repeatedly stops generating a response midway through agent execution causing a hanged state. I've been experiencing this very often after switching to 0.6.x. The number of tokens in input + output is lesser than set ctx_num. Once the time alive period runs out, the model is stuck at 'stopping' state.

Relevant log output

Apr 03 22:48:12 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:48:12 | 200 |     120.452µs |       127.0.0.1 | GET      "/api/ps"
Apr 03 22:48:12 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:48:12 | 200 |      28.131µs |       127.0.0.1 | HEAD     "/"
Apr 03 22:44:37 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:44:37 | 200 |  5.054276458s |       127.0.0.1 | POST     "/api/chat"
Apr 03 22:44:32 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:44:32 | 200 | 22.029005923s |       127.0.0.1 | POST     "/api/chat"
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: time=2025-04-03T22:44:16.649Z level=INFO source=server.go:619 msg="llama runner started in 2.01 seconds"
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: graph splits = 2
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: graph nodes  = 1030
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model:  CUDA_Host compute buffer size =   168.01 MiB
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model:      CUDA0 compute buffer size =  5312.00 MiB
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model:  CUDA_Host  output buffer size =     2.02 MiB
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: KV self size  = 10240.00 MiB, K (f16): 5120.00 MiB, V (f16): 5120.00 MiB
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_kv_cache_init:      CUDA0 KV buffer size = 10240.00 MiB
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_kv_cache_init: kv_size = 81920, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ctx_per_seq (20480) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: freq_scale    = 1
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: freq_base     = 500000.0
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: flash_attn    = 0
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ubatch      = 512
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_batch       = 2048
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ctx_per_seq = 20480
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ctx         = 81920
Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_seq_max     = 4
Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors:   CPU_Mapped model buffer size =   281.81 MiB
Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors:        CUDA0 model buffer size =  4403.49 MiB
Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: offloaded 33/33 layers to GPU
Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: offloading output layer to GPU
Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: offloading 32 repeating layers to GPU
Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: loading model tensors, this can take a while... (mmap = true)

OS

Linux

GPU

Nvidia A10G 24g x 4

CPU

AMD

Ollama version

0.6.3

Originally created by @jefferson-vm on GitHub (Apr 3, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10119 ### What is the issue? Models tested with: Llama3.1:8b, Qwen2.5:14b, Gemma3:12b Issue: Ollama repeatedly stops generating a response midway through agent execution causing a hanged state. I've been experiencing this very often after switching to 0.6.x. The number of tokens in input + output is lesser than set ctx_num. Once the time alive period runs out, the model is stuck at 'stopping' state. ### Relevant log output ```shell Apr 03 22:48:12 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:48:12 | 200 | 120.452µs | 127.0.0.1 | GET "/api/ps" Apr 03 22:48:12 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:48:12 | 200 | 28.131µs | 127.0.0.1 | HEAD "/" Apr 03 22:44:37 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:44:37 | 200 | 5.054276458s | 127.0.0.1 | POST "/api/chat" Apr 03 22:44:32 ip-xxx-xx-xx-xxx ollama[743374]: [GIN] 2025/04/03 - 22:44:32 | 200 | 22.029005923s | 127.0.0.1 | POST "/api/chat" Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: time=2025-04-03T22:44:16.649Z level=INFO source=server.go:619 msg="llama runner started in 2.01 seconds" Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: graph splits = 2 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: graph nodes = 1030 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: CUDA_Host compute buffer size = 168.01 MiB Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: CUDA0 compute buffer size = 5312.00 MiB Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: CUDA_Host output buffer size = 2.02 MiB Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: KV self size = 10240.00 MiB, K (f16): 5120.00 MiB, V (f16): 5120.00 MiB Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_kv_cache_init: CUDA0 KV buffer size = 10240.00 MiB Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_kv_cache_init: kv_size = 81920, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ctx_per_seq (20480) < n_ctx_train (131072) -- the full capacity of the model will not be utilized Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: freq_scale = 1 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: freq_base = 500000.0 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: flash_attn = 0 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ubatch = 512 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_batch = 2048 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ctx_per_seq = 20480 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_ctx = 81920 Apr 03 22:44:16 ip-xxx-xx-xx-xxx ollama[743374]: llama_init_from_model: n_seq_max = 4 Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: CPU_Mapped model buffer size = 281.81 MiB Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: CUDA0 model buffer size = 4403.49 MiB Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: offloaded 33/33 layers to GPU Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: offloading output layer to GPU Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: offloading 32 repeating layers to GPU Apr 03 22:44:15 ip-xxx-xx-xx-xxx ollama[743374]: load_tensors: loading model tensors, this can take a while... (mmap = true) ``` ### OS Linux ### GPU Nvidia A10G 24g x 4 ### CPU AMD ### Ollama version 0.6.3
GiteaMirror added the bug label 2026-04-29 02:07:35 -05:00
GiteaMirror commented 2026-04-29 02:07:40 -05:00
Author
Owner
Copy Link

@luisgg98 commented on GitHub (Apr 7, 2025):

Good afternoon I am experimenting the same issue.

Image

OS
Ubuntu 22.04.5 LTS
GPU
NVIDIA H100 PCIe 80g x 4
Ollama version
0.5.7

<!-- gh-comment-id:2783331390 --> @luisgg98 commented on GitHub (Apr 7, 2025): Good afternoon I am experimenting the same issue. ![Image](https://github.com/user-attachments/assets/54fe6653-3a8e-4220-a36f-d9d330ea660c) **OS** Ubuntu 22.04.5 LTS **GPU** NVIDIA H100 PCIe 80g x 4 **Ollama version** 0.5.7
GiteaMirror commented 2026-04-29 02:07:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 9, 2025):

There seems to be a race somewhere in the scheduler under heavy load, possibly related to clients closing connections prematurely. If people are still seeing models get stuck in a "Stopping..." state in the ollama ps output and the model never actually unloads, please try running the server with OLLAMA_DEBUG=1 and share the logs including the model load, and eventual stuck state.

<!-- gh-comment-id:2791070598 --> @dhiltgen commented on GitHub (Apr 9, 2025): There seems to be a race somewhere in the scheduler under heavy load, possibly related to clients closing connections prematurely. If people are still seeing models get stuck in a "Stopping..." state in the `ollama ps` output and the model never actually unloads, please try running the server with OLLAMA_DEBUG=1 and share the logs including the model load, and eventual stuck state.
GiteaMirror commented 2026-04-29 02:07:46 -05:00
Author
Owner
Copy Link

@jefferson-vm commented on GitHub (Apr 10, 2025):

@dhiltgen here's the logs, let me know if this helps identify the issue:


Apr 10 19:36:18 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:18 | 200 |      22.041µs |       127.0.0.1 | HEAD     "/"

Apr 10 19:36:16 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:16 | 200 |       35.91µs |       127.0.0.1 | GET      "/api/ps"

Apr 10 19:36:16 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:16 | 200 |       21.43µs |       127.0.0.1 | HEAD     "/"

Apr 10 19:36:14 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:14 | 200 |      53.451µs |       127.0.0.1 | GET      "/api/ps"

Apr 10 19:36:14 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:14 | 200 |      22.841µs |       127.0.0.1 | HEAD     "/"

Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=sched.go:310 msg="ignoring unload event with no pending requests"

Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=sched.go:386 msg="sending an unloaded event" modelPath=/opt/ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa

Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=sched.go:661 msg="gpu VRAM free memory converged after 2.34 seconds" model=/opt/ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa

Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: releasing cuda driver library

Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f0ec61ab-a500-6a59-4aa1-0a960a525f15 name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="21.7 GiB" now.total="22.0 GiB" now.free="21.7 GiB" now.used="256.4 MiB"

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.952Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-533622a7-7b70-ef13-089d-ae37f430b06d name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="15.5 GiB" now.total="22.0 GiB" now.free="20.6 GiB" now.used="1.3 GiB"

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.743Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-47fa09ae-cc7e-eb60-bb7b-b888d94accf4 name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="19.9 GiB" now.total="22.0 GiB" now.free="19.9 GiB" now.used="2.1 GiB"

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.535Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f4e38c22-86fb-3e62-0e31-d64c6e167a07 name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="9.1 GiB" now.total="22.0 GiB" now.free="9.1 GiB" now.used="12.8 GiB"

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: device count 4

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: calling cuDeviceGetCount

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: CUDA driver version: 12.4

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: raw version 0x2f08

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: calling cuDriverGetVersion

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: calling cuInit

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuCtxDestroy - 0x774f7c8e1850

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuMemGetInfo_v2 - 0x774f7c886e20

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuCtxCreate_v3 - 0x774f7c87cee0

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetName - 0x774f7c87cc40

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetUuid - 0x774f7c87cc60

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetAttribute - 0x774f7c87cd00

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGet - 0x774f7c87cc00

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetCount - 0x774f7c87cc20

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDriverGetVersion - 0x774f7c87cbe0

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuInit - 0x774f7c87cbc0

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.120

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.113Z level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="373.7 GiB" before.free="347.4 GiB" before.free_swap="0 B" now.total="373.7 GiB" now.free="347.7 GiB" now.free_swap="0 B"

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.030Z level=DEBUG source=sched.go:382 msg="runner released" modelPath=/opt/ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa

Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.030Z level=DEBUG source=server.go:1011 msg="llama server stopped"

Apr 10 19:35:52 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:52.907Z level=DEBUG source=server.go:1007 msg="waiting for llama server to exit"

Apr 10 19:35:52 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:52.906Z level=DEBUG source=server.go:1001 msg="stopping llama server"

Apr 10 19:35:52 ip-172-31-91-221 ollama[829868]: releasing cuda driver library```
<!-- gh-comment-id:2794984675 --> @jefferson-vm commented on GitHub (Apr 10, 2025): @dhiltgen here's the logs, let me know if this helps identify the issue: ```Apr 10 19:36:18 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:18 | 200 | 36.841µs | 127.0.0.1 | GET "/api/ps" Apr 10 19:36:18 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:18 | 200 | 22.041µs | 127.0.0.1 | HEAD "/" Apr 10 19:36:16 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:16 | 200 | 35.91µs | 127.0.0.1 | GET "/api/ps" Apr 10 19:36:16 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:16 | 200 | 21.43µs | 127.0.0.1 | HEAD "/" Apr 10 19:36:14 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:14 | 200 | 53.451µs | 127.0.0.1 | GET "/api/ps" Apr 10 19:36:14 ip-172-31-91-221 ollama[829868]: [GIN] 2025/04/10 - 19:36:14 | 200 | 22.841µs | 127.0.0.1 | HEAD "/" Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=sched.go:310 msg="ignoring unload event with no pending requests" Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=sched.go:386 msg="sending an unloaded event" modelPath=/opt/ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=sched.go:661 msg="gpu VRAM free memory converged after 2.34 seconds" model=/opt/ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: releasing cuda driver library Apr 10 19:35:54 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:54.155Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f0ec61ab-a500-6a59-4aa1-0a960a525f15 name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="21.7 GiB" now.total="22.0 GiB" now.free="21.7 GiB" now.used="256.4 MiB" Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.952Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-533622a7-7b70-ef13-089d-ae37f430b06d name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="15.5 GiB" now.total="22.0 GiB" now.free="20.6 GiB" now.used="1.3 GiB" Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.743Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-47fa09ae-cc7e-eb60-bb7b-b888d94accf4 name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="19.9 GiB" now.total="22.0 GiB" now.free="19.9 GiB" now.used="2.1 GiB" Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.535Z level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f4e38c22-86fb-3e62-0e31-d64c6e167a07 name="NVIDIA A10G" overhead="0 B" before.total="22.0 GiB" before.free="9.1 GiB" now.total="22.0 GiB" now.free="9.1 GiB" now.used="12.8 GiB" Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: device count 4 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: calling cuDeviceGetCount Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: CUDA driver version: 12.4 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: raw version 0x2f08 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: calling cuDriverGetVersion Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: calling cuInit Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuCtxDestroy - 0x774f7c8e1850 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuMemGetInfo_v2 - 0x774f7c886e20 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuCtxCreate_v3 - 0x774f7c87cee0 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetName - 0x774f7c87cc40 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetUuid - 0x774f7c87cc60 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetAttribute - 0x774f7c87cd00 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGet - 0x774f7c87cc00 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDeviceGetCount - 0x774f7c87cc20 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuDriverGetVersion - 0x774f7c87cbe0 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: dlsym: cuInit - 0x774f7c87cbc0 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.550.120 Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.113Z level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="373.7 GiB" before.free="347.4 GiB" before.free_swap="0 B" now.total="373.7 GiB" now.free="347.7 GiB" now.free_swap="0 B" Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.030Z level=DEBUG source=sched.go:382 msg="runner released" modelPath=/opt/ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa Apr 10 19:35:53 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:53.030Z level=DEBUG source=server.go:1011 msg="llama server stopped" Apr 10 19:35:52 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:52.907Z level=DEBUG source=server.go:1007 msg="waiting for llama server to exit" Apr 10 19:35:52 ip-172-31-91-221 ollama[829868]: time=2025-04-10T19:35:52.906Z level=DEBUG source=server.go:1001 msg="stopping llama server" Apr 10 19:35:52 ip-172-31-91-221 ollama[829868]: releasing cuda driver library```
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#53151
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?