github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12411] iGPU Memory not used, System Memory is filled with loaded model #54757

New Issue
Closed
opened 2026-04-29 07:13:48 -05:00 by GiteaMirror · 24 comments
GiteaMirror commented 2026-04-29 07:13:48 -05:00
Owner
Copy Link

Originally created by @fayakun-it-consulting on GitHub (Sep 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12411

What is the issue?

I have a Mini-PC with 48 GB of RAM from which I have reserved 16 GB of VRAM from the BIOS.
After having being able to run qwen2.5vl:latest on my AMD Ryzen™ 7 7840HS w/ Radeon™ 780M Graphics, I made the realization that the iGPU is used to compute the prompt but the model is not loaded into the reserved space for the iGPU.

The model is loaded in system RAM:

Image

The model is processed by the iGPU:
Image

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @fayakun-it-consulting on GitHub (Sep 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12411 ### What is the issue? I have a Mini-PC with 48 GB of RAM from which I have reserved 16 GB of VRAM from the BIOS. After having being able to run **qwen2.5vl:latest** on my AMD Ryzen™ 7 7840HS w/ Radeon™ 780M Graphics, I made the realization that the iGPU is used to compute the prompt but the model is not loaded into the reserved space for the iGPU. The model is loaded in system RAM: <img width="1153" height="801" alt="Image" src="https://github.com/user-attachments/assets/0e4ba09d-5223-47dd-8b32-63773e47527f" /> The model is processed by the iGPU: <img width="868" height="629" alt="Image" src="https://github.com/user-attachments/assets/8ba5db66-b454-46fb-aced-c09f922c4f5d" /> ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bugneeds more info labels 2026-04-29 07:13:48 -05:00
GiteaMirror commented 2026-04-29 07:13:52 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

780m is not officially supported but some users have apparently made it work with a choice of driver and environment variables. Server logs may help debugging.

<!-- gh-comment-id:3334432209 --> @rick-github commented on GitHub (Sep 25, 2025): 780m is not [officially supported](https://github.com/ollama/ollama/blob/main/docs/gpu.md#linux-support) but some users have apparently made it work with a choice of driver and environment variables. [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may help debugging.
GiteaMirror commented 2026-04-29 07:13:52 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

I tried to run gpt4all with a pretty heavy model and the model is loaded in the iGPU's allocated memory as you can see on the screen.

Image
<!-- gh-comment-id:3334496813 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): I tried to run gpt4all with a pretty heavy model and the model is loaded in the iGPU's allocated memory as you can see on the screen. <img width="1920" height="1080" alt="Image" src="https://github.com/user-attachments/assets/eb4c6b6c-5b4a-4f62-b1d5-25fed9a9eabb" />
GiteaMirror commented 2026-04-29 07:13:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

Text logs.

<!-- gh-comment-id:3334502152 --> @rick-github commented on GitHub (Sep 25, 2025): Text logs.
GiteaMirror commented 2026-04-29 07:13:54 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

I tried to load Distill-Qwen-32B-GGUF which is massive and it worked with gpt4all.

Image
<!-- gh-comment-id:3334524419 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): I tried to load Distill-Qwen-32B-GGUF which is massive and it worked with gpt4all. <img width="1891" height="1020" alt="Image" src="https://github.com/user-attachments/assets/550bec10-f7fd-4296-9080-89226443e91d" />
GiteaMirror commented 2026-04-29 07:13:55 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

https://github.com/ollama/ollama/issues/12411#issuecomment-3334502152

<!-- gh-comment-id:3334529243 --> @rick-github commented on GitHub (Sep 25, 2025): https://github.com/ollama/ollama/issues/12411#issuecomment-3334502152
GiteaMirror commented 2026-04-29 07:13:55 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

Text logs.

How can I show/get the logs ?

<!-- gh-comment-id:3334534387 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): > Text logs. How can I show/get the logs ?
GiteaMirror commented 2026-04-29 07:13:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

https://github.com/ollama/ollama/issues/12411#issuecomment-3334432209

<!-- gh-comment-id:3334537718 --> @rick-github commented on GitHub (Sep 25, 2025): https://github.com/ollama/ollama/issues/12411#issuecomment-3334432209
GiteaMirror commented 2026-04-29 07:13:57 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

#12411 (comment)

ollama-logs.txt

<!-- gh-comment-id:3334606527 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): > [#12411 (comment)](https://github.com/ollama/ollama/issues/12411#issuecomment-3334432209) [ollama-logs.txt](https://github.com/user-attachments/files/22539612/ollama-logs.txt)
GiteaMirror commented 2026-04-29 07:13:58 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

Sep 25 16:36:14 PCRT-5G ollama[177688]: time=2025-09-25T16:36:14.204+02:00 level=INFO source=routes.go:1357 msg="Listening on 127.0.0.1:11434 (version 0.11.4)"

Try upgrading to a later release, the 0.12.* series has better memory management.

Sep 25 16:54:48 PCRT-5G ollama[177688]: time=2025-09-25T16:54:48.927+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"

The runner went unresponsive for reasons that are not clear.

Run

sudo systemctl edit ollama

and add the following lines:

[Service]
Environment=OLLAMA_DEBUG=1

and then restart the ollama server:

sudo systemctl stop ollama
sudo systemctl start ollama

Then post the logs from trying to load a model.

<!-- gh-comment-id:3334636292 --> @rick-github commented on GitHub (Sep 25, 2025): ``` Sep 25 16:36:14 PCRT-5G ollama[177688]: time=2025-09-25T16:36:14.204+02:00 level=INFO source=routes.go:1357 msg="Listening on 127.0.0.1:11434 (version 0.11.4)" ``` Try upgrading to a later release, the 0.12.* series has better memory management. ``` Sep 25 16:54:48 PCRT-5G ollama[177688]: time=2025-09-25T16:54:48.927+02:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" ``` The runner went unresponsive for reasons that are not clear. Run ``` sudo systemctl edit ollama ``` and add the following lines: ``` [Service] Environment=OLLAMA_DEBUG=1 ``` and then restart the ollama server: ``` sudo systemctl stop ollama sudo systemctl start ollama ``` Then post the logs from trying to load a model.
GiteaMirror commented 2026-04-29 07:14:02 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

Ollama version : 0.11.4

ollama-logs.txt

<!-- gh-comment-id:3334688946 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): Ollama version : 0.11.4 [ollama-logs.txt](https://github.com/user-attachments/files/22539927/ollama-logs.txt)
GiteaMirror commented 2026-04-29 07:14:05 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

I am trying to update with : curl -fsSL https://ollama.com/install.sh | sh

I didn't install for the AMD GPU's

curl -L https://ollama.com/download/ollama-linux-amd64-rocm.tgz -o ollama-linux-amd64-rocm.tgz
sudo tar -C /usr -xzf ollama-linux-amd64-rocm.tgz
<!-- gh-comment-id:3334699786 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): I am trying to update with : **curl -fsSL https://ollama.com/install.sh | sh** I didn't install for the AMD GPU's ``` curl -L https://ollama.com/download/ollama-linux-amd64-rocm.tgz -o ollama-linux-amd64-rocm.tgz sudo tar -C /usr -xzf ollama-linux-amd64-rocm.tgz ```
GiteaMirror commented 2026-04-29 07:14:06 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

I am trying to update with : curl -fsSL https://ollama.com/install.sh | sh

I didn't install for the AMD GPU's

curl -L https://ollama.com/download/ollama-linux-amd64-rocm.tgz -o ollama-linux-amd64-rocm.tgz
sudo tar -C /usr -xzf ollama-linux-amd64-rocm.tgz

It seems that the install does it automatically!

<!-- gh-comment-id:3334723181 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): > I am trying to update with : **curl -fsSL https://ollama.com/install.sh | sh** > > I didn't install for the AMD GPU's > > ``` > curl -L https://ollama.com/download/ollama-linux-amd64-rocm.tgz -o ollama-linux-amd64-rocm.tgz > sudo tar -C /usr -xzf ollama-linux-amd64-rocm.tgz > ``` It seems that the install does it automatically!
GiteaMirror commented 2026-04-29 07:14:07 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

Sep 25 17:14:55 PCRT-5G ollama[212541]: time=2025-09-25T17:14:55.876+02:00 level=DEBUG source=server.go:643 msg="model load progress 0.00"
Sep 25 17:17:28 PCRT-5G ollama[212541]: time=2025-09-25T17:17:28.028+02:00 level=DEBUG source=server.go:643 msg="model load progress 0.43"

It's just taking a long time to load the model, 43% in 2m33s so about 6 minutes in total. Is your model storage on a networked filesystem or similar?

In any case, the model is being loaded partially into GPU:

Sep 25 17:14:54 PCRT-5G ollama[212541]: load_tensors: offloading 47 repeating layers to GPU
Sep 25 17:14:54 PCRT-5G ollama[212541]: load_tensors: offloaded 47/65 layers to GPU

The reason it's also using system RAM is because the model is bigger than your available VRAM:

Sep 25 17:14:11 PCRT-5G ollama[212541]: time=2025-09-25T17:14:11.245+02:00 level=INFO source=server.go:175 msg=offload
 library=rocm layers.requested=-1 layers.model=65 layers.offload=47 layers.split="" memory.available="[15.3 GiB]"
 memory.gpu_overhead="0 B" memory.required.full="20.7 GiB" memory.required.partial="15.1 GiB" memory.required.kv="1.0 GiB"
 memory.required.allocations="[15.1 GiB]" memory.weights.total="18.1 GiB" memory.weights.repeating="17.5 GiB"
 memory.weights.nonrepeating="609.1 MiB" memory.graph.full="348.0 MiB" memory.graph.partial="916.1 MiB"

The full model requires 20.7GiB and there's only 15.3GiB available, so the remainder of the model is loaded in system RAM.

<!-- gh-comment-id:3334743807 --> @rick-github commented on GitHub (Sep 25, 2025): ``` Sep 25 17:14:55 PCRT-5G ollama[212541]: time=2025-09-25T17:14:55.876+02:00 level=DEBUG source=server.go:643 msg="model load progress 0.00" Sep 25 17:17:28 PCRT-5G ollama[212541]: time=2025-09-25T17:17:28.028+02:00 level=DEBUG source=server.go:643 msg="model load progress 0.43" ``` It's just taking a long time to load the model, 43% in 2m33s so about 6 minutes in total. Is your model storage on a networked filesystem or similar? In any case, the model is being loaded partially into GPU: ``` Sep 25 17:14:54 PCRT-5G ollama[212541]: load_tensors: offloading 47 repeating layers to GPU Sep 25 17:14:54 PCRT-5G ollama[212541]: load_tensors: offloaded 47/65 layers to GPU ``` The reason it's also using system RAM is because the model is bigger than your available VRAM: ``` Sep 25 17:14:11 PCRT-5G ollama[212541]: time=2025-09-25T17:14:11.245+02:00 level=INFO source=server.go:175 msg=offload library=rocm layers.requested=-1 layers.model=65 layers.offload=47 layers.split="" memory.available="[15.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="20.7 GiB" memory.required.partial="15.1 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[15.1 GiB]" memory.weights.total="18.1 GiB" memory.weights.repeating="17.5 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="348.0 MiB" memory.graph.partial="916.1 MiB" ``` The full model requires 20.7GiB and there's only 15.3GiB available, so the remainder of the model is loaded in system RAM.
GiteaMirror commented 2026-04-29 07:14:07 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

The model is never loaded to the iGPU allocated RAM. Although that the processing is done by the iGPU. You can see in the logs and in the screenshot.

ollama-logs.txt

Image
<!-- gh-comment-id:3334801193 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): The model is never loaded to the iGPU allocated RAM. Although that the processing is done by the iGPU. You can see in the logs and in the screenshot. [ollama-logs.txt](https://github.com/user-attachments/files/22540386/ollama-logs.txt) <img width="1891" height="940" alt="Image" src="https://github.com/user-attachments/assets/518d7ee6-fae1-4635-862d-d36524b5e6b1" />
GiteaMirror commented 2026-04-29 07:14:08 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

https://github.com/user-attachments/assets/3fcd2cd7-d5f3-4452-953d-625873db932d

It's just taking a long time to load the model, 43% in 2m33s so about 6 minutes in total. Is your model storage on a networked filesystem or similar?

I noticed that the loading of the models are really slow because I have pci-e 4.0 NVMe. When loading with gpt4all I noticed that it is 1.5 to 3 GB per second.

<!-- gh-comment-id:3334825309 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): https://github.com/user-attachments/assets/3fcd2cd7-d5f3-4452-953d-625873db932d > It's just taking a long time to load the model, 43% in 2m33s so about 6 minutes in total. Is your model storage on a networked filesystem or similar? I noticed that the loading of the models are really slow because I have pci-e 4.0 NVMe. When loading with gpt4all I noticed that it is 1.5 to 3 GB per second.
GiteaMirror commented 2026-04-29 07:14:08 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

Logs indicate that the model is being loaded into the GPU:

Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloading 47 repeating layers to GPU
Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloaded 47/65 layers to GPU
Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors:        ROCm0 model buffer size = 13054.53 MiB
Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_kv_cache_unified:      ROCm0 KV buffer size =   752.00 MiB
Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_context:      ROCm0 compute buffer size =   360.00 MiB

What do rocm-smi and radeontop show?

<!-- gh-comment-id:3334878633 --> @rick-github commented on GitHub (Sep 25, 2025): Logs indicate that the model is being loaded into the GPU: ``` Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloading 47 repeating layers to GPU Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloaded 47/65 layers to GPU Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: ROCm0 model buffer size = 13054.53 MiB Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_kv_cache_unified: ROCm0 KV buffer size = 752.00 MiB Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_context: ROCm0 compute buffer size = 360.00 MiB ``` What do `rocm-smi` and `radeontop` show?
GiteaMirror commented 2026-04-29 07:14:08 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

Logs indicate that the model is being loaded into the GPU:

Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloading 47 repeating layers to GPU
Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloaded 47/65 layers to GPU
Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors:        ROCm0 model buffer size = 13054.53 MiB
Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_kv_cache_unified:      ROCm0 KV buffer size =   752.00 MiB
Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_context:      ROCm0 compute buffer size =   360.00 MiB

What do rocm-smi and radeontop show?

========================================= ROCm System Management Interface =========================================
=================================================== Concise Info ===================================================
Device  Node  IDs              Temp    Power     Partitions          SCLK  MCLK     Fan  Perf  PwrCap  VRAM%  GPU%  
              (DID,     GUID)  (Edge)  (Socket)  (Mem, Compute, ID)                                                 
====================================================================================================================
0       1     0x15bf,   53078  48.0°C  21.219W   N/A, N/A, 0         N/A   1000Mhz  0%   low   N/A     57%    98%   
====================================================================================================================
=============================================== End of ROCm SMI Log ================================================
Image

Nvtop is showing that none of the allocated 16 GB VRAM from BIOS is used.

Image

Once the model is loaded it crashes!

ollama run deepseek-r1:32b
>>> Hi can you tell me a funny joke?
Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details

Sep 25 18:57:25 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:57:25.774+02:00 level=DEBUG source=server.go:1295 msg="model load progress 1.00"
Sep 25 18:57:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:57:26.029+02:00 level=DEBUG source=server.go:1298 msg="model load completed, waiting for server to become available" status="llm server loading model"
Sep 25 18:57:27 FYKN-PC-02 ollama[253762]: llama_kv_cache_unified:      ROCm0 KV buffer size =   752.00 MiB
Sep 25 18:58:57 FYKN-PC-02 ollama[253762]: llama_kv_cache_unified:        CPU KV buffer size =   272.00 MiB
Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_kv_cache_unified: size = 1024.00 MiB (  4096 cells,  64 layers,  1/1 seqs), K (f16):  512.00 MiB, V (f16):  512.00 MiB
Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: enumerating backends
Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: backend_ptrs.size() = 2
Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: max_nodes = 6168
Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 0
Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: graph_reserve: reserving a graph for ubatch with n_tokens =  512, n_seqs =  1, n_outputs =  512
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: graph_reserve: reserving a graph for ubatch with n_tokens =    1, n_seqs =  1, n_outputs =    1
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: graph_reserve: reserving a graph for ubatch with n_tokens =  512, n_seqs =  1, n_outputs =  512
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context:      ROCm0 compute buffer size =   360.00 MiB
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context:  ROCm_Host compute buffer size =    26.01 MiB
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context: graph nodes  = 2438
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context: graph splits = 36 (with bs=512), 102 (with bs=1)
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.177+02:00 level=INFO source=server.go:1289 msg="llama runner started in 153.40 seconds"
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.193+02:00 level=INFO source=sched.go:470 msg="loaded runners" count=1
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.195+02:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding"
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.196+02:00 level=INFO source=server.go:1289 msg="llama runner started in 153.42 seconds"
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.197+02:00 level=DEBUG source=sched.go:482 msg="finished setting up" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: [GIN] 2025/09/25 - 18:58:59 | 200 |         2m34s |       127.0.0.1 | POST     "/api/generate"
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.211+02:00 level=DEBUG source=sched.go:490 msg="context for request finished"
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.212+02:00 level=DEBUG source=sched.go:286 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 duration=5m0s
Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.213+02:00 level=DEBUG source=sched.go:304 msg="after processing request finished event" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 refCount=0
Sep 25 19:01:21 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:21.409+02:00 level=DEBUG source=sched.go:580 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93
Sep 25 19:01:21 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:21.461+02:00 level=DEBUG source=server.go:1388 msg="completion request" images=0 prompt=61 format=""
Sep 25 19:01:21 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:21.501+02:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=12 used=0 remaining=12
Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: ggml_cuda_compute_forward: MUL failed
Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: ROCm error: invalid device function
Sep 25 19:01:23 FYKN-PC-02 ollama[253762]:   current device: 0, in function ggml_cuda_compute_forward at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2568
Sep 25 19:01:23 FYKN-PC-02 ollama[253762]:   err
Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:84: ROCm error
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318566]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318544]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318543]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318542]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318541]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318540]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318539]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318538]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318537]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318536]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318535]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318534]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318113]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318112]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318111]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318110]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318109]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318108]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318107]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318106]
Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318105]
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: [Thread debugging using libthread_db enabled]
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: Using host libthread_db library "/lib/x86_64-linux-gnu/libthread_db.so.1".
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: 0x00005a20bd8d0da3 in ?? ()
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #0  0x00005a20bd8d0da3 in ?? ()
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #1  0x00005a20bd88d070 in ?? ()
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #2  0x00005a20bf641100 in ?? ()
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #3  0x0000000000000080 in ?? ()
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #4  0x0000000000000000 in ?? ()
Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: [Inferior 1 (process 318104) detached]
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: SIGABRT: abort
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: PC=0x73032f1eff1c m=9 sigcode=18446744073709551610
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: signal arrived during cgo execution
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 14 gp=0xc000602fc0 m=9 mp=0xc000600008 [syscall]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.cgocall(0x5a20be5bc490, 0xc000097bd8)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/cgocall.go:167 +0x4b fp=0xc000097bb0 sp=0xc000097b78 pc=0x5a20bd8c43eb
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7302d7ed3e70, {0xc, 0x72fc68000b70, 0x0, 0x72fc68001380, 0x72fc68001b90, 0x72fc680023a0, 0x72fc68007390})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         _cgo_gotypes.go:668 +0x4a fp=0xc000097bd8 sp=0xc000097bb0 pc=0x5a20bdc762ca
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama.(*Context).Decode.func1(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/llama/llama.go:150
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama.(*Context).Decode(0xc00050bd88?, 0x1?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/llama/llama.go:150 +0xed fp=0xc000097cc0 sp=0xc000097bd8 pc=0x5a20bdc790ad
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0006ee280, 0xc000177040, 0xc00050bf28)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/runner/llamarunner/runner.go:441 +0x209 fp=0xc000097ee8 sp=0xc000097cc0 pc=0x5a20bdd44209
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0006ee280, {0x5a20bed90ab0, 0xc0006bc5a0})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/runner/llamarunner/runner.go:346 +0x1d5 fp=0xc000097fb8 sp=0xc000097ee8 pc=0x5a20bdd43e95
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/runner/llamarunner/runner.go:880 +0x28 fp=0xc000097fe0 sp=0xc000097fb8 pc=0x5a20bdd48be8
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000097fe8 sp=0xc000097fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/runner/llamarunner/runner.go:880 +0x4c5
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 1 gp=0xc000002380 m=nil [IO wait]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc00001d790 sp=0xc00001d770 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.netpollblock(0xc00001d810?, 0xbd860666?, 0x20?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/netpoll.go:575 +0xf7 fp=0xc00001d7c8 sp=0xc00001d790 pc=0x5a20bd88c357
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.runtime_pollWait(0x73032ee4fde0, 0x72)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/netpoll.go:351 +0x85 fp=0xc00001d7e8 sp=0xc00001d7c8 pc=0x5a20bd8c6a85
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).wait(0xc0006cc680?, 0x5a20bd86f066?, 0x0)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00001d810 sp=0xc00001d7e8 pc=0x5a20bd94dec7
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).waitRead(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         internal/poll/fd_poll_runtime.go:89
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*FD).Accept(0xc0006cc680)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         internal/poll/fd_unix.go:620 +0x295 fp=0xc00001d8b8 sp=0xc00001d810 pc=0x5a20bd953295
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*netFD).accept(0xc0006cc680)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/fd_unix.go:172 +0x29 fp=0xc00001d970 sp=0xc00001d8b8 pc=0x5a20bd9c6249
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*TCPListener).accept(0xc00043f700)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/tcpsock_posix.go:159 +0x1b fp=0xc00001d9c0 sp=0xc00001d970 pc=0x5a20bd9dbbfb
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*TCPListener).Accept(0xc00043f700)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/tcpsock.go:380 +0x30 fp=0xc00001d9f0 sp=0xc00001d9c0 pc=0x5a20bd9daab0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*onceCloseListener).Accept(0xc000316000?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         <autogenerated>:1 +0x24 fp=0xc00001da08 sp=0xc00001d9f0 pc=0x5a20bdbf2204
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*Server).Serve(0xc000037300, {0x5a20bed8e568, 0xc00043f700})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:3424 +0x30c fp=0xc00001db38 sp=0xc00001da08 pc=0x5a20bdbc9acc
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000130140, 0x4, 0x4})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/runner/llamarunner/runner.go:901 +0x8f5 fp=0xc00001dd08 sp=0xc00001db38 pc=0x5a20bdd48975
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner.Execute({0xc000130130?, 0x0?, 0x0?})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc00001dd30 sp=0xc00001dd08 pc=0x5a20bddd8874
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000037000?, {0x5a20be8a00b2?, 0x4?, 0x5a20be8a00b6?})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/cmd/cmd.go:1706 +0x45 fp=0xc00001dd58 sp=0xc00001dd30 pc=0x5a20be54a3a5
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).execute(0xc0006d9508, {0xc00043f500, 0x4, 0x4})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc00001de78 sp=0xc00001dd58 pc=0x5a20bda3f89c
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).ExecuteC(0xc000694908)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc00001df30 sp=0xc00001de78 pc=0x5a20bda400e5
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).Execute(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/spf13/cobra@v1.7.0/command.go:992
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/spf13/cobra@v1.7.0/command.go:985
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: main.main()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/main.go:12 +0x4d fp=0xc00001df50 sp=0xc00001df30 pc=0x5a20be54ae6d
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.main()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:283 +0x29d fp=0xc00001dfe0 sp=0xc00001df50 pc=0x5a20bd8939dd
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00001dfe8 sp=0xc00001dfe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle), 2 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b45a2b8c744?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000084fa8 sp=0xc000084f88 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goparkunlock(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:441
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.forcegchelper()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:348 +0xb8 fp=0xc000084fe0 sp=0xc000084fa8 pc=0x5a20bd893d18
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000084fe8 sp=0xc000084fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.init.7 in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:336 +0x1a
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000085780 sp=0xc000085760 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goparkunlock(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:441
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.bgsweep(0xc000038100)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgcsweep.go:316 +0xdf fp=0xc0000857c8 sp=0xc000085780 pc=0x5a20bd87e4bf
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcenable.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:204 +0x25 fp=0xc0000857e0 sp=0xc0000857c8 pc=0x5a20bd8728a5
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000857e8 sp=0xc0000857e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcenable in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:204 +0x66
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x3ba07f53?, 0x3b9aca00?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goparkunlock(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:441
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.(*scavengerState).park(0x5a20bf63e1a0)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x5a20bd87bf09
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.bgscavenge(0xc000038100)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x5a20bd87c499
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcenable.gowrap2()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x5a20bd872845
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcenable in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:205 +0xa5
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x5a20bed7b0a8?, 0x0?, 0x0?, 0x1000000010?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000084630 sp=0xc000084610 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.runfinq()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mfinal.go:196 +0x107 fp=0xc0000847e0 sp=0xc000084630 pc=0x5a20bd871867
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000847e8 sp=0xc0000847e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.createfing in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mfinal.go:166 +0x3d
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 19 gp=0xc000103180 m=nil [chan receive]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0xc00017b9a0?, 0xc000010048?, 0x60?, 0x7?, 0x5a20bd9ace88?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000080718 sp=0xc0000806f8 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.chanrecv(0xc000110310, 0x0, 0x1)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/chan.go:664 +0x445 fp=0xc000080790 sp=0xc000080718 pc=0x5a20bd863245
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.chanrecv1(0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/chan.go:506 +0x12 fp=0xc0000807b8 sp=0xc000080790 pc=0x5a20bd862dd2
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1796
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1799 +0x2f fp=0xc0000807e0 sp=0xc0000807b8 pc=0x5a20bd875a4f
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000807e8 sp=0xc0000807e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1794 +0x85
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 20 gp=0xc000103500 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000080f38 sp=0xc000080f18 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc000080fc8 sp=0xc000080f38 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc000080fe0 sp=0xc000080fc8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b0825215285?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000081738 sp=0xc000081718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000817c8 sp=0xc000081738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc0000817e0 sp=0xc0000817c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000817e8 sp=0xc0000817e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle), 2 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0x6e?, 0x2c?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b082521552f?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000086738 sp=0xc000086718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000867c8 sp=0xc000086738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc0000867e0 sp=0xc0000867c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000867e8 sp=0xc0000867e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 22 gp=0xc000103880 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252a0ece?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000081f38 sp=0xc000081f18 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc000081fc8 sp=0xc000081f38 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc000081fe0 sp=0xc000081fc8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b0825216afb?, 0x3?, 0x6d?, 0xed?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b0825290d3f?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000086f38 sp=0xc000086f18 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc000086fc8 sp=0xc000086f38 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc000086fe0 sp=0xc000086fc8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000086fe8 sp=0xc000086fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 7 gp=0xc000003dc0 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252037d7?, 0x3?, 0x44?, 0x28?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000087738 sp=0xc000087718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000877c8 sp=0xc000087738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc0000877e0 sp=0xc0000877c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000877e8 sp=0xc0000877e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 8 gp=0xc0000b6000 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b082521561f?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000087f38 sp=0xc000087f18 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc000087fc8 sp=0xc000087f38 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc000087fe0 sp=0xc000087fc8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 9 gp=0xc0000b61c0 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b082520c746?, 0x3?, 0x94?, 0x42?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 23 gp=0xc000103a40 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252150b9?, 0x3?, 0x3d?, 0x25?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000082738 sp=0xc000082718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000827c8 sp=0xc000082738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc0000827e0 sp=0xc0000827c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000827e8 sp=0xc0000827e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0x2e?, 0x8e?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 10 gp=0xc0000b6380 m=nil [GC worker (idle), 2 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0xe7?, 0x6f?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000506f38 sp=0xc000506f18 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc000506fc8 sp=0xc000506f38 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc000506fe0 sp=0xc000506fc8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000506fe8 sp=0xc000506fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 11 gp=0xc0000b6540 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0x74?, 0xd7?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000507738 sp=0xc000507718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005077c8 sp=0xc000507738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc0005077e0 sp=0xc0005077c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005077e8 sp=0xc0005077e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 12 gp=0xc0000b6700 m=nil [GC worker (idle), 4 minutes]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252c919e?, 0x1?, 0xd4?, 0x5c?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000507f38 sp=0xc000507f18 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc000507fc8 sp=0xc000507f38 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc000507fe0 sp=0xc000507fc8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000507fe8 sp=0xc000507fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 13 gp=0xc0000b68c0 m=nil [GC worker (idle)]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b45a511aae1?, 0x1?, 0xab?, 0xda?, 0x0?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc000508738 sp=0xc000508718 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005087c8 sp=0xc000508738 pc=0x5a20bd874d69
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x25 fp=0xc0005087e0 sp=0xc0005087c8 pc=0x5a20bd874c45
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005087e8 sp=0xc0005087e0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/mgc.go:1339 +0x105
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 141 gp=0xc000603180 m=nil [IO wait]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc0000f3dd8 sp=0xc0000f3db8 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.netpollblock(0x5a20bd8eabd8?, 0xbd860666?, 0x20?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/netpoll.go:575 +0xf7 fp=0xc0000f3e10 sp=0xc0000f3dd8 pc=0x5a20bd88c357
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.runtime_pollWait(0x73032ee4f980, 0x72)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/netpoll.go:351 +0x85 fp=0xc0000f3e30 sp=0xc0000f3e10 pc=0x5a20bd8c6a85
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).wait(0xc0003e2100?, 0xc0000cc071?, 0x0)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000f3e58 sp=0xc0000f3e30 pc=0x5a20bd94dec7
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).waitRead(...)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         internal/poll/fd_poll_runtime.go:89
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*FD).Read(0xc0003e2100, {0xc0000cc071, 0x1, 0x1})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         internal/poll/fd_unix.go:165 +0x27a fp=0xc0000f3ef0 sp=0xc0000f3e58 pc=0x5a20bd94f1ba
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*netFD).Read(0xc0003e2100, {0xc0000cc071?, 0x0?, 0x0?})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/fd_posix.go:55 +0x25 fp=0xc0000f3f38 sp=0xc0000f3ef0 pc=0x5a20bd9c42a5
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*conn).Read(0xc00007c000, {0xc0000cc071?, 0x0?, 0x0?})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/net.go:194 +0x45 fp=0xc0000f3f80 sp=0xc0000f3f38 pc=0x5a20bd9d2665
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*connReader).backgroundRead(0xc0000cc060)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:690 +0x37 fp=0xc0000f3fc8 sp=0xc0000f3f80 pc=0x5a20bdbbe4d7
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*connReader).startBackgroundRead.gowrap2()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:686 +0x25 fp=0xc0000f3fe0 sp=0xc0000f3fc8 pc=0x5a20bdbbe405
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000f3fe8 sp=0xc0000f3fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by net/http.(*connReader).startBackgroundRead in goroutine 656
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:686 +0xb6
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 656 gp=0xc0005a0700 m=nil [select]:
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0xc000049a78?, 0x2?, 0xa?, 0x0?, 0xc0000498c4?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/proc.go:435 +0xce fp=0xc0000496f8 sp=0xc0000496d8 pc=0x5a20bd8c786e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.selectgo(0xc000049a78, 0xc0000498c0, 0xc?, 0x0, 0x1?, 0x1)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/select.go:351 +0x837 fp=0xc000049830 sp=0xc0000496f8 pc=0x5a20bd8a5ed7
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0006ee280, {0x5a20bed8e748, 0xc000172000}, 0xc000690000)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         github.com/ollama/ollama/runner/llamarunner/runner.go:629 +0xb37 fp=0xc000049ac0 sp=0xc000049830 pc=0x5a20bdd45e17
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x5a20bed8e748?, 0xc000172000?}, 0xc00001fb40?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         <autogenerated>:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x5a20bdd48ff6
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.HandlerFunc.ServeHTTP(0xc000510780?, {0x5a20bed8e748?, 0xc000172000?}, 0xc00001fb60?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x5a20bdbc6109
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*ServeMux).ServeHTTP(0x5a20bd86bd85?, {0x5a20bed8e748, 0xc000172000}, 0xc000690000)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x5a20bdbc8004
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.serverHandler.ServeHTTP({0x5a20bed8ad90?}, {0x5a20bed8e748?, 0xc000172000?}, 0x1?)
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x5a20bdbe5a8e
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*conn).serve(0xc000316000, {0x5a20bed90a78, 0xc0006d4d50})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x5a20bdbc4605
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*Server).Serve.gowrap3()
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x5a20bdbc9ec8
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({})
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x5a20bd8cefa1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by net/http.(*Server).Serve in goroutine 1
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]:         net/http/server.go:3454 +0x485
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rax    0x0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rbx    0x4daa0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rcx    0x73032f1eff1c
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rdx    0x6
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rdi    0x4da98
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rsi    0x4daa0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rbp    0x7302e5563c10
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rsp    0x7302e5563bd0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r8     0x0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r9     0x0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r10    0x8
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r11    0x246
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r12    0x6
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r13    0x73029ec1b723
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r14    0x16
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r15    0x73029ec1b723
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rip    0x73032f1eff1c
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rflags 0x246
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: cs     0x33
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: fs     0x0
Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: gs     0x0
Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.063+02:00 level=ERROR source=server.go:1459 msg="post predict" error="Post \"http://127.0.0.1:35263/completion\": EOF"
Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.063+02:00 level=ERROR source=server.go:425 msg="llama runner terminated" error="exit status 2"
Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: [GIN] 2025/09/25 - 19:01:26 | 200 |  4.874648918s |       127.0.0.1 | POST     "/api/chat"
Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.064+02:00 level=DEBUG source=sched.go:377 msg="context for request finished" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096
Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.064+02:00 level=DEBUG source=sched.go:286 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 duration=5m0s
Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.064+02:00 level=DEBUG source=sched.go:304 msg="after processing request finished event" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 refCount=0
<!-- gh-comment-id:3335085427 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): > Logs indicate that the model is being loaded into the GPU: > > ``` > Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloading 47 repeating layers to GPU > Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: offloaded 47/65 layers to GPU > Sep 25 17:33:18 PCRT-5G ollama[228855]: load_tensors: ROCm0 model buffer size = 13054.53 MiB > Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_kv_cache_unified: ROCm0 KV buffer size = 752.00 MiB > Sep 25 17:34:05 PCRT-5G ollama[228855]: llama_context: ROCm0 compute buffer size = 360.00 MiB > ``` > > What do `rocm-smi` and `radeontop` show? ``` ========================================= ROCm System Management Interface ========================================= =================================================== Concise Info =================================================== Device Node IDs Temp Power Partitions SCLK MCLK Fan Perf PwrCap VRAM% GPU% (DID, GUID) (Edge) (Socket) (Mem, Compute, ID) ==================================================================================================================== 0 1 0x15bf, 53078 48.0°C 21.219W N/A, N/A, 0 N/A 1000Mhz 0% low N/A 57% 98% ==================================================================================================================== =============================================== End of ROCm SMI Log ================================================ ``` <img width="1298" height="780" alt="Image" src="https://github.com/user-attachments/assets/40cd6741-8970-4371-8c24-a2337134cb74" /> Nvtop is showing that none of the allocated 16 GB VRAM from BIOS is used. <img width="868" height="629" alt="Image" src="https://github.com/user-attachments/assets/f6a0c0db-368b-4122-a478-4fe7a7aebe9b" /> Once the model is loaded it crashes! ``` ollama run deepseek-r1:32b >>> Hi can you tell me a funny joke? Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details Sep 25 18:57:25 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:57:25.774+02:00 level=DEBUG source=server.go:1295 msg="model load progress 1.00" Sep 25 18:57:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:57:26.029+02:00 level=DEBUG source=server.go:1298 msg="model load completed, waiting for server to become available" status="llm server loading model" Sep 25 18:57:27 FYKN-PC-02 ollama[253762]: llama_kv_cache_unified: ROCm0 KV buffer size = 752.00 MiB Sep 25 18:58:57 FYKN-PC-02 ollama[253762]: llama_kv_cache_unified: CPU KV buffer size = 272.00 MiB Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_kv_cache_unified: size = 1024.00 MiB ( 4096 cells, 64 layers, 1/1 seqs), K (f16): 512.00 MiB, V (f16): 512.00 MiB Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: enumerating backends Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: backend_ptrs.size() = 2 Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: max_nodes = 6168 Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: llama_context: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 0 Sep 25 18:58:58 FYKN-PC-02 ollama[253762]: graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512 Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512 Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context: ROCm0 compute buffer size = 360.00 MiB Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context: ROCm_Host compute buffer size = 26.01 MiB Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context: graph nodes = 2438 Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: llama_context: graph splits = 36 (with bs=512), 102 (with bs=1) Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.177+02:00 level=INFO source=server.go:1289 msg="llama runner started in 153.40 seconds" Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.193+02:00 level=INFO source=sched.go:470 msg="loaded runners" count=1 Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.195+02:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding" Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.196+02:00 level=INFO source=server.go:1289 msg="llama runner started in 153.42 seconds" Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.197+02:00 level=DEBUG source=sched.go:482 msg="finished setting up" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: [GIN] 2025/09/25 - 18:58:59 | 200 | 2m34s | 127.0.0.1 | POST "/api/generate" Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.211+02:00 level=DEBUG source=sched.go:490 msg="context for request finished" Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.212+02:00 level=DEBUG source=sched.go:286 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 duration=5m0s Sep 25 18:58:59 FYKN-PC-02 ollama[253762]: time=2025-09-25T18:58:59.213+02:00 level=DEBUG source=sched.go:304 msg="after processing request finished event" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 refCount=0 Sep 25 19:01:21 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:21.409+02:00 level=DEBUG source=sched.go:580 msg="evaluating already loaded" model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 Sep 25 19:01:21 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:21.461+02:00 level=DEBUG source=server.go:1388 msg="completion request" images=0 prompt=61 format="" Sep 25 19:01:21 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:21.501+02:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=12 used=0 remaining=12 Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: ggml_cuda_compute_forward: MUL failed Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: ROCm error: invalid device function Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: current device: 0, in function ggml_cuda_compute_forward at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2568 Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: err Sep 25 19:01:23 FYKN-PC-02 ollama[253762]: //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:84: ROCm error Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318566] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318544] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318543] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318542] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318541] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318540] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318539] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318538] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318537] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318536] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318535] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318534] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318113] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318112] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318111] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318110] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318109] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318108] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318107] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318106] Sep 25 19:01:24 FYKN-PC-02 ollama[322847]: [New LWP 318105] Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: [Thread debugging using libthread_db enabled] Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: Using host libthread_db library "/lib/x86_64-linux-gnu/libthread_db.so.1". Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: 0x00005a20bd8d0da3 in ?? () Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #0 0x00005a20bd8d0da3 in ?? () Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #1 0x00005a20bd88d070 in ?? () Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #2 0x00005a20bf641100 in ?? () Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #3 0x0000000000000080 in ?? () Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: #4 0x0000000000000000 in ?? () Sep 25 19:01:25 FYKN-PC-02 ollama[322847]: [Inferior 1 (process 318104) detached] Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: SIGABRT: abort Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: PC=0x73032f1eff1c m=9 sigcode=18446744073709551610 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: signal arrived during cgo execution Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 14 gp=0xc000602fc0 m=9 mp=0xc000600008 [syscall]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.cgocall(0x5a20be5bc490, 0xc000097bd8) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/cgocall.go:167 +0x4b fp=0xc000097bb0 sp=0xc000097b78 pc=0x5a20bd8c43eb Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7302d7ed3e70, {0xc, 0x72fc68000b70, 0x0, 0x72fc68001380, 0x72fc68001b90, 0x72fc680023a0, 0x72fc68007390}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: _cgo_gotypes.go:668 +0x4a fp=0xc000097bd8 sp=0xc000097bb0 pc=0x5a20bdc762ca Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama.(*Context).Decode.func1(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama/llama.go:150 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama.(*Context).Decode(0xc00050bd88?, 0x1?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/llama/llama.go:150 +0xed fp=0xc000097cc0 sp=0xc000097bd8 pc=0x5a20bdc790ad Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0006ee280, 0xc000177040, 0xc00050bf28) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner/runner.go:441 +0x209 fp=0xc000097ee8 sp=0xc000097cc0 pc=0x5a20bdd44209 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0006ee280, {0x5a20bed90ab0, 0xc0006bc5a0}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner/runner.go:346 +0x1d5 fp=0xc000097fb8 sp=0xc000097ee8 pc=0x5a20bdd43e95 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner/runner.go:880 +0x28 fp=0xc000097fe0 sp=0xc000097fb8 pc=0x5a20bdd48be8 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000097fe8 sp=0xc000097fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner/runner.go:880 +0x4c5 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 1 gp=0xc000002380 m=nil [IO wait]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc00001d790 sp=0xc00001d770 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.netpollblock(0xc00001d810?, 0xbd860666?, 0x20?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/netpoll.go:575 +0xf7 fp=0xc00001d7c8 sp=0xc00001d790 pc=0x5a20bd88c357 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.runtime_pollWait(0x73032ee4fde0, 0x72) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/netpoll.go:351 +0x85 fp=0xc00001d7e8 sp=0xc00001d7c8 pc=0x5a20bd8c6a85 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).wait(0xc0006cc680?, 0x5a20bd86f066?, 0x0) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00001d810 sp=0xc00001d7e8 pc=0x5a20bd94dec7 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).waitRead(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll/fd_poll_runtime.go:89 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*FD).Accept(0xc0006cc680) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll/fd_unix.go:620 +0x295 fp=0xc00001d8b8 sp=0xc00001d810 pc=0x5a20bd953295 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*netFD).accept(0xc0006cc680) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/fd_unix.go:172 +0x29 fp=0xc00001d970 sp=0xc00001d8b8 pc=0x5a20bd9c6249 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*TCPListener).accept(0xc00043f700) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/tcpsock_posix.go:159 +0x1b fp=0xc00001d9c0 sp=0xc00001d970 pc=0x5a20bd9dbbfb Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*TCPListener).Accept(0xc00043f700) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/tcpsock.go:380 +0x30 fp=0xc00001d9f0 sp=0xc00001d9c0 pc=0x5a20bd9daab0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*onceCloseListener).Accept(0xc000316000?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: <autogenerated>:1 +0x24 fp=0xc00001da08 sp=0xc00001d9f0 pc=0x5a20bdbf2204 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*Server).Serve(0xc000037300, {0x5a20bed8e568, 0xc00043f700}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:3424 +0x30c fp=0xc00001db38 sp=0xc00001da08 pc=0x5a20bdbc9acc Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000130140, 0x4, 0x4}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner/runner.go:901 +0x8f5 fp=0xc00001dd08 sp=0xc00001db38 pc=0x5a20bdd48975 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner.Execute({0xc000130130?, 0x0?, 0x0?}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc00001dd30 sp=0xc00001dd08 pc=0x5a20bddd8874 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000037000?, {0x5a20be8a00b2?, 0x4?, 0x5a20be8a00b6?}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/cmd/cmd.go:1706 +0x45 fp=0xc00001dd58 sp=0xc00001dd30 pc=0x5a20be54a3a5 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).execute(0xc0006d9508, {0xc00043f500, 0x4, 0x4}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc00001de78 sp=0xc00001dd58 pc=0x5a20bda3f89c Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).ExecuteC(0xc000694908) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc00001df30 sp=0xc00001de78 pc=0x5a20bda400e5 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).Execute(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra@v1.7.0/command.go:992 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra.(*Command).ExecuteContext(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/spf13/cobra@v1.7.0/command.go:985 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: main.main() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/main.go:12 +0x4d fp=0xc00001df50 sp=0xc00001df30 pc=0x5a20be54ae6d Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.main() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:283 +0x29d fp=0xc00001dfe0 sp=0xc00001df50 pc=0x5a20bd8939dd Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00001dfe8 sp=0xc00001dfe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle), 2 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b45a2b8c744?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000084fa8 sp=0xc000084f88 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goparkunlock(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:441 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.forcegchelper() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:348 +0xb8 fp=0xc000084fe0 sp=0xc000084fa8 pc=0x5a20bd893d18 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000084fe8 sp=0xc000084fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.init.7 in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:336 +0x1a Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000085780 sp=0xc000085760 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goparkunlock(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:441 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.bgsweep(0xc000038100) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgcsweep.go:316 +0xdf fp=0xc0000857c8 sp=0xc000085780 pc=0x5a20bd87e4bf Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcenable.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:204 +0x25 fp=0xc0000857e0 sp=0xc0000857c8 pc=0x5a20bd8728a5 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000857e8 sp=0xc0000857e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcenable in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:204 +0x66 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x3ba07f53?, 0x3b9aca00?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000085f78 sp=0xc000085f58 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goparkunlock(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:441 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.(*scavengerState).park(0x5a20bf63e1a0) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgcscavenge.go:425 +0x49 fp=0xc000085fa8 sp=0xc000085f78 pc=0x5a20bd87bf09 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.bgscavenge(0xc000038100) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgcscavenge.go:658 +0x59 fp=0xc000085fc8 sp=0xc000085fa8 pc=0x5a20bd87c499 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcenable.gowrap2() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:205 +0x25 fp=0xc000085fe0 sp=0xc000085fc8 pc=0x5a20bd872845 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000085fe8 sp=0xc000085fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcenable in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:205 +0xa5 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x5a20bed7b0a8?, 0x0?, 0x0?, 0x1000000010?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000084630 sp=0xc000084610 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.runfinq() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mfinal.go:196 +0x107 fp=0xc0000847e0 sp=0xc000084630 pc=0x5a20bd871867 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000847e8 sp=0xc0000847e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.createfing in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mfinal.go:166 +0x3d Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 19 gp=0xc000103180 m=nil [chan receive]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0xc00017b9a0?, 0xc000010048?, 0x60?, 0x7?, 0x5a20bd9ace88?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000080718 sp=0xc0000806f8 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.chanrecv(0xc000110310, 0x0, 0x1) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/chan.go:664 +0x445 fp=0xc000080790 sp=0xc000080718 pc=0x5a20bd863245 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.chanrecv1(0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/chan.go:506 +0x12 fp=0xc0000807b8 sp=0xc000080790 pc=0x5a20bd862dd2 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1796 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1799 +0x2f fp=0xc0000807e0 sp=0xc0000807b8 pc=0x5a20bd875a4f Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000807e8 sp=0xc0000807e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1794 +0x85 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 20 gp=0xc000103500 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000080f38 sp=0xc000080f18 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc000080fc8 sp=0xc000080f38 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc000080fe0 sp=0xc000080fc8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b0825215285?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000081738 sp=0xc000081718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc0000817c8 sp=0xc000081738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc0000817e0 sp=0xc0000817c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000817e8 sp=0xc0000817e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle), 2 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0x6e?, 0x2c?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b082521552f?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000086738 sp=0xc000086718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc0000867c8 sp=0xc000086738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc0000867e0 sp=0xc0000867c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000867e8 sp=0xc0000867e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 22 gp=0xc000103880 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252a0ece?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000081f38 sp=0xc000081f18 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc000081fc8 sp=0xc000081f38 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc000081fe0 sp=0xc000081fc8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000081fe8 sp=0xc000081fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b0825216afb?, 0x3?, 0x6d?, 0xed?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b0825290d3f?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000086f38 sp=0xc000086f18 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc000086fc8 sp=0xc000086f38 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc000086fe0 sp=0xc000086fc8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000086fe8 sp=0xc000086fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 7 gp=0xc000003dc0 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252037d7?, 0x3?, 0x44?, 0x28?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000087738 sp=0xc000087718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc0000877c8 sp=0xc000087738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc0000877e0 sp=0xc0000877c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000877e8 sp=0xc0000877e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 8 gp=0xc0000b6000 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b082521561f?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000087f38 sp=0xc000087f18 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc000087fc8 sp=0xc000087f38 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc000087fe0 sp=0xc000087fc8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000087fe8 sp=0xc000087fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 9 gp=0xc0000b61c0 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b082520c746?, 0x3?, 0x94?, 0x42?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 23 gp=0xc000103a40 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252150b9?, 0x3?, 0x3d?, 0x25?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000082738 sp=0xc000082718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc0000827c8 sp=0xc000082738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc0000827e0 sp=0xc0000827c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000827e8 sp=0xc0000827e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0x2e?, 0x8e?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 10 gp=0xc0000b6380 m=nil [GC worker (idle), 2 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0xe7?, 0x6f?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000506f38 sp=0xc000506f18 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc000506fc8 sp=0xc000506f38 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc000506fe0 sp=0xc000506fc8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000506fe8 sp=0xc000506fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 11 gp=0xc0000b6540 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x5a20bf6edea0?, 0x1?, 0x74?, 0xd7?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000507738 sp=0xc000507718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc0005077c8 sp=0xc000507738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc0005077e0 sp=0xc0005077c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0005077e8 sp=0xc0005077e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 12 gp=0xc0000b6700 m=nil [GC worker (idle), 4 minutes]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b08252c919e?, 0x1?, 0xd4?, 0x5c?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000507f38 sp=0xc000507f18 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc000507fc8 sp=0xc000507f38 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc000507fe0 sp=0xc000507fc8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000507fe8 sp=0xc000507fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 13 gp=0xc0000b68c0 m=nil [GC worker (idle)]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x2b45a511aae1?, 0x1?, 0xab?, 0xda?, 0x0?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc000508738 sp=0xc000508718 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkWorker(0xc000111730) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1423 +0xe9 fp=0xc0005087c8 sp=0xc000508738 pc=0x5a20bd874d69 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x25 fp=0xc0005087e0 sp=0xc0005087c8 pc=0x5a20bd874c45 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0005087e8 sp=0xc0005087e0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/mgc.go:1339 +0x105 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 141 gp=0xc000603180 m=nil [IO wait]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc0000f3dd8 sp=0xc0000f3db8 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.netpollblock(0x5a20bd8eabd8?, 0xbd860666?, 0x20?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/netpoll.go:575 +0xf7 fp=0xc0000f3e10 sp=0xc0000f3dd8 pc=0x5a20bd88c357 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.runtime_pollWait(0x73032ee4f980, 0x72) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/netpoll.go:351 +0x85 fp=0xc0000f3e30 sp=0xc0000f3e10 pc=0x5a20bd8c6a85 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).wait(0xc0003e2100?, 0xc0000cc071?, 0x0) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000f3e58 sp=0xc0000f3e30 pc=0x5a20bd94dec7 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*pollDesc).waitRead(...) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll/fd_poll_runtime.go:89 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll.(*FD).Read(0xc0003e2100, {0xc0000cc071, 0x1, 0x1}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: internal/poll/fd_unix.go:165 +0x27a fp=0xc0000f3ef0 sp=0xc0000f3e58 pc=0x5a20bd94f1ba Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*netFD).Read(0xc0003e2100, {0xc0000cc071?, 0x0?, 0x0?}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/fd_posix.go:55 +0x25 fp=0xc0000f3f38 sp=0xc0000f3ef0 pc=0x5a20bd9c42a5 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net.(*conn).Read(0xc00007c000, {0xc0000cc071?, 0x0?, 0x0?}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/net.go:194 +0x45 fp=0xc0000f3f80 sp=0xc0000f3f38 pc=0x5a20bd9d2665 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*connReader).backgroundRead(0xc0000cc060) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:690 +0x37 fp=0xc0000f3fc8 sp=0xc0000f3f80 pc=0x5a20bdbbe4d7 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*connReader).startBackgroundRead.gowrap2() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:686 +0x25 fp=0xc0000f3fe0 sp=0xc0000f3fc8 pc=0x5a20bdbbe405 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000f3fe8 sp=0xc0000f3fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by net/http.(*connReader).startBackgroundRead in goroutine 656 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:686 +0xb6 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: goroutine 656 gp=0xc0005a0700 m=nil [select]: Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.gopark(0xc000049a78?, 0x2?, 0xa?, 0x0?, 0xc0000498c4?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/proc.go:435 +0xce fp=0xc0000496f8 sp=0xc0000496d8 pc=0x5a20bd8c786e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.selectgo(0xc000049a78, 0xc0000498c0, 0xc?, 0x0, 0x1?, 0x1) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/select.go:351 +0x837 fp=0xc000049830 sp=0xc0000496f8 pc=0x5a20bd8a5ed7 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0006ee280, {0x5a20bed8e748, 0xc000172000}, 0xc000690000) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner/runner.go:629 +0xb37 fp=0xc000049ac0 sp=0xc000049830 pc=0x5a20bdd45e17 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x5a20bed8e748?, 0xc000172000?}, 0xc00001fb40?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: <autogenerated>:1 +0x36 fp=0xc000049af0 sp=0xc000049ac0 pc=0x5a20bdd48ff6 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.HandlerFunc.ServeHTTP(0xc000510780?, {0x5a20bed8e748?, 0xc000172000?}, 0xc00001fb60?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:2294 +0x29 fp=0xc000049b18 sp=0xc000049af0 pc=0x5a20bdbc6109 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*ServeMux).ServeHTTP(0x5a20bd86bd85?, {0x5a20bed8e748, 0xc000172000}, 0xc000690000) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:2822 +0x1c4 fp=0xc000049b68 sp=0xc000049b18 pc=0x5a20bdbc8004 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.serverHandler.ServeHTTP({0x5a20bed8ad90?}, {0x5a20bed8e748?, 0xc000172000?}, 0x1?) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:3301 +0x8e fp=0xc000049b98 sp=0xc000049b68 pc=0x5a20bdbe5a8e Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*conn).serve(0xc000316000, {0x5a20bed90a78, 0xc0006d4d50}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:2102 +0x625 fp=0xc000049fb8 sp=0xc000049b98 pc=0x5a20bdbc4605 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http.(*Server).Serve.gowrap3() Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x5a20bdbc9ec8 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime.goexit({}) Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x5a20bd8cefa1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: created by net/http.(*Server).Serve in goroutine 1 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: net/http/server.go:3454 +0x485 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rax 0x0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rbx 0x4daa0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rcx 0x73032f1eff1c Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rdx 0x6 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rdi 0x4da98 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rsi 0x4daa0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rbp 0x7302e5563c10 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rsp 0x7302e5563bd0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r8 0x0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r9 0x0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r10 0x8 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r11 0x246 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r12 0x6 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r13 0x73029ec1b723 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r14 0x16 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: r15 0x73029ec1b723 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rip 0x73032f1eff1c Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: rflags 0x246 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: cs 0x33 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: fs 0x0 Sep 25 19:01:25 FYKN-PC-02 ollama[253762]: gs 0x0 Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.063+02:00 level=ERROR source=server.go:1459 msg="post predict" error="Post \"http://127.0.0.1:35263/completion\": EOF" Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.063+02:00 level=ERROR source=server.go:425 msg="llama runner terminated" error="exit status 2" Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: [GIN] 2025/09/25 - 19:01:26 | 200 | 4.874648918s | 127.0.0.1 | POST "/api/chat" Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.064+02:00 level=DEBUG source=sched.go:377 msg="context for request finished" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.064+02:00 level=DEBUG source=sched.go:286 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 duration=5m0s Sep 25 19:01:26 FYKN-PC-02 ollama[253762]: time=2025-09-25T19:01:26.064+02:00 level=DEBUG source=sched.go:304 msg="after processing request finished event" runner.name=registry.ollama.ai/library/deepseek-r1:32b runner.inference=rocm runner.devices=1 runner.size="20.7 GiB" runner.vram="15.1 GiB" runner.parallel=1 runner.pid=318104 runner.model=/usr/share/ollama/.ollama/models/blobs/sha256-6150cb382311b69f09cc0f9a1b69fc029cbd742b66bb8ec531aa5ecf5c613e93 runner.num_ctx=4096 refCount=0 ```
GiteaMirror commented 2026-04-29 07:14:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 25, 2025):

What's the result of

grep amd /var/log/dmesg

and

cat /sys/module/amdgpu/parameters/no_system_mem_limit
<!-- gh-comment-id:3335131188 --> @rick-github commented on GitHub (Sep 25, 2025): What's the result of ``` grep amd /var/log/dmesg ``` and ``` cat /sys/module/amdgpu/parameters/no_system_mem_limit ```
GiteaMirror commented 2026-04-29 07:14:09 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 25, 2025):

grep amd /var/log/dmesg

[   11.324920] kernel: Linux version 6.11.0-26-generic (buildd@lcy02-amd64-107) (x86_64-linux-gnu-gcc-14 (Ubuntu 14.2.0-4ubuntu2) 14.2.0, GNU ld (GNU Binutils for Ubuntu) 2.43.1) #26-Ubuntu SMP PREEMPT_DYNAMIC Sat Apr 12 11:25:41 UTC 2025 (Ubuntu 6.11.0-26.26-generic 6.11.11)
[   11.353160] kernel: perf/amd_iommu: Detected AMD IOMMU #0 (2 banks, 4 counters/bank).
[   11.679974] kernel: kvm_amd: TSC scaling supported
[   11.679991] kernel: kvm_amd: Nested Virtualization enabled
[   11.680028] kernel: kvm_amd: Nested Paging enabled
[   11.680036] kernel: kvm_amd: LBR virtualization supported
[   11.680045] kernel: kvm_amd: Virtual GIF supported
[   11.680055] kernel: kvm_amd: Virtual NMI enabled
[   11.741006] kernel: amd_atl: AMD Address Translation Library initialized
[   12.856027] kernel: [drm] amdgpu kernel modesetting enabled.
[   12.870761] kernel: amdgpu: Virtual CRAT table created for CPU
[   12.870787] kernel: amdgpu: Topology: Add CPU node
[   12.870806] kernel: amdgpu 0000:c5:00.0: enabling device (0006 -> 0007)
[   13.796966] kernel: amdgpu 0000:c5:00.0: amdgpu: Fetched VBIOS from VFCT
[   13.797274] kernel: amdgpu: ATOM BIOS: 113-PHXGENERIC-001
[   13.797293] kernel: amdgpu 0000:c5:00.0: vgaarb: deactivate vga console
[   13.797579] kernel: amdgpu 0000:c5:00.0: amdgpu: Trusted Memory Zone (TMZ) feature enabled
[   13.797900] kernel: amdgpu 0000:c5:00.0: amdgpu: VRAM: 16384M 0x0000008000000000 - 0x00000083FFFFFFFF (16384M used)
[   13.798166] kernel: amdgpu 0000:c5:00.0: amdgpu: GART: 512M 0x00007FFF00000000 - 0x00007FFF1FFFFFFF
[   13.798379] kernel: [drm] amdgpu: 16384M of VRAM memory ready
[   13.798390] kernel: [drm] amdgpu: 15704M of GTT memory ready.
[   13.798454] kernel: amdgpu 0000:c5:00.0: amdgpu: reserve 0x4000000 from 0x83f8000000 for PSP TMR
[   13.798666] kernel: amdgpu 0000:c5:00.0: amdgpu: RAS: optional ras ta ucode is not available
[   13.798782] kernel: amdgpu 0000:c5:00.0: amdgpu: RAP: optional rap ta ucode is not available
[   13.798899] kernel: amdgpu 0000:c5:00.0: amdgpu: SECUREDISPLAY: securedisplay ta ucode is not available
[   13.799035] kernel: amdgpu 0000:c5:00.0: amdgpu: SMU is initialized successfully!
[   13.799209] kernel: snd_hda_intel 0000:c5:00.1: bound 0000:c5:00.0 (ops amdgpu_dm_audio_component_bind_ops [amdgpu])
[   13.799329] kernel: kfd kfd: amdgpu: Allocated 3969056 bytes on gart
[   13.799462] kernel: kfd kfd: amdgpu: Total number of KFD nodes to be created: 1
[   13.799602] kernel: amdgpu: Virtual CRAT table created for GPU
[   13.799617] kernel: amdgpu: Topology: Add dGPU node [0x15bf:0x1002]
[   13.799625] kernel: kfd kfd: amdgpu: added device 1002:15bf
[   13.799731] kernel: amdgpu 0000:c5:00.0: amdgpu: SE 1, SH per SE 2, CU per SH 6, active_cu_number 12
[   13.799875] kernel: amdgpu 0000:c5:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[   13.799989] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[   13.800102] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[   13.800210] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0
[   13.800335] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0
[   13.800430] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0
[   13.800517] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0
[   13.800604] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0
[   13.800714] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0
[   13.800826] kernel: amdgpu 0000:c5:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0
[   13.800952] kernel: amdgpu 0000:c5:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[   13.801065] kernel: amdgpu 0000:c5:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8
[   13.801186] kernel: amdgpu 0000:c5:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0
[   13.801364] kernel: amdgpu 0000:c5:00.0: amdgpu: Runtime PM not available
[   13.801476] kernel: [drm] Initialized amdgpu 3.61.0 for 0000:c5:00.0 on minor 1
[   13.801506] kernel: fbcon: amdgpudrmfb (fb0) is primary device
[   13.801524] kernel: amdgpu 0000:c5:00.0: [drm] fb0: amdgpudrmfb frame buffer device


cat /sys/module/amdgpu/parameters/no_system_mem_limit
N
<!-- gh-comment-id:3335173804 --> @fayakun-it-consulting commented on GitHub (Sep 25, 2025): > grep amd /var/log/dmesg ``` [ 11.324920] kernel: Linux version 6.11.0-26-generic (buildd@lcy02-amd64-107) (x86_64-linux-gnu-gcc-14 (Ubuntu 14.2.0-4ubuntu2) 14.2.0, GNU ld (GNU Binutils for Ubuntu) 2.43.1) #26-Ubuntu SMP PREEMPT_DYNAMIC Sat Apr 12 11:25:41 UTC 2025 (Ubuntu 6.11.0-26.26-generic 6.11.11) [ 11.353160] kernel: perf/amd_iommu: Detected AMD IOMMU #0 (2 banks, 4 counters/bank). [ 11.679974] kernel: kvm_amd: TSC scaling supported [ 11.679991] kernel: kvm_amd: Nested Virtualization enabled [ 11.680028] kernel: kvm_amd: Nested Paging enabled [ 11.680036] kernel: kvm_amd: LBR virtualization supported [ 11.680045] kernel: kvm_amd: Virtual GIF supported [ 11.680055] kernel: kvm_amd: Virtual NMI enabled [ 11.741006] kernel: amd_atl: AMD Address Translation Library initialized [ 12.856027] kernel: [drm] amdgpu kernel modesetting enabled. [ 12.870761] kernel: amdgpu: Virtual CRAT table created for CPU [ 12.870787] kernel: amdgpu: Topology: Add CPU node [ 12.870806] kernel: amdgpu 0000:c5:00.0: enabling device (0006 -> 0007) [ 13.796966] kernel: amdgpu 0000:c5:00.0: amdgpu: Fetched VBIOS from VFCT [ 13.797274] kernel: amdgpu: ATOM BIOS: 113-PHXGENERIC-001 [ 13.797293] kernel: amdgpu 0000:c5:00.0: vgaarb: deactivate vga console [ 13.797579] kernel: amdgpu 0000:c5:00.0: amdgpu: Trusted Memory Zone (TMZ) feature enabled [ 13.797900] kernel: amdgpu 0000:c5:00.0: amdgpu: VRAM: 16384M 0x0000008000000000 - 0x00000083FFFFFFFF (16384M used) [ 13.798166] kernel: amdgpu 0000:c5:00.0: amdgpu: GART: 512M 0x00007FFF00000000 - 0x00007FFF1FFFFFFF [ 13.798379] kernel: [drm] amdgpu: 16384M of VRAM memory ready [ 13.798390] kernel: [drm] amdgpu: 15704M of GTT memory ready. [ 13.798454] kernel: amdgpu 0000:c5:00.0: amdgpu: reserve 0x4000000 from 0x83f8000000 for PSP TMR [ 13.798666] kernel: amdgpu 0000:c5:00.0: amdgpu: RAS: optional ras ta ucode is not available [ 13.798782] kernel: amdgpu 0000:c5:00.0: amdgpu: RAP: optional rap ta ucode is not available [ 13.798899] kernel: amdgpu 0000:c5:00.0: amdgpu: SECUREDISPLAY: securedisplay ta ucode is not available [ 13.799035] kernel: amdgpu 0000:c5:00.0: amdgpu: SMU is initialized successfully! [ 13.799209] kernel: snd_hda_intel 0000:c5:00.1: bound 0000:c5:00.0 (ops amdgpu_dm_audio_component_bind_ops [amdgpu]) [ 13.799329] kernel: kfd kfd: amdgpu: Allocated 3969056 bytes on gart [ 13.799462] kernel: kfd kfd: amdgpu: Total number of KFD nodes to be created: 1 [ 13.799602] kernel: amdgpu: Virtual CRAT table created for GPU [ 13.799617] kernel: amdgpu: Topology: Add dGPU node [0x15bf:0x1002] [ 13.799625] kernel: kfd kfd: amdgpu: added device 1002:15bf [ 13.799731] kernel: amdgpu 0000:c5:00.0: amdgpu: SE 1, SH per SE 2, CU per SH 6, active_cu_number 12 [ 13.799875] kernel: amdgpu 0000:c5:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0 [ 13.799989] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0 [ 13.800102] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0 [ 13.800210] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 6 on hub 0 [ 13.800335] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 7 on hub 0 [ 13.800430] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 8 on hub 0 [ 13.800517] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 9 on hub 0 [ 13.800604] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 10 on hub 0 [ 13.800714] kernel: amdgpu 0000:c5:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 11 on hub 0 [ 13.800826] kernel: amdgpu 0000:c5:00.0: amdgpu: ring sdma0 uses VM inv eng 12 on hub 0 [ 13.800952] kernel: amdgpu 0000:c5:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8 [ 13.801065] kernel: amdgpu 0000:c5:00.0: amdgpu: ring jpeg_dec uses VM inv eng 1 on hub 8 [ 13.801186] kernel: amdgpu 0000:c5:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 13 on hub 0 [ 13.801364] kernel: amdgpu 0000:c5:00.0: amdgpu: Runtime PM not available [ 13.801476] kernel: [drm] Initialized amdgpu 3.61.0 for 0000:c5:00.0 on minor 1 [ 13.801506] kernel: fbcon: amdgpudrmfb (fb0) is primary device [ 13.801524] kernel: amdgpu 0000:c5:00.0: [drm] fb0: amdgpudrmfb frame buffer device cat /sys/module/amdgpu/parameters/no_system_mem_limit N ```
GiteaMirror commented 2026-04-29 07:14:09 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Sep 26, 2025):

Any update?

<!-- gh-comment-id:3340694392 --> @fayakun-it-consulting commented on GitHub (Sep 26, 2025): Any update?
GiteaMirror commented 2026-04-29 07:14:10 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Oct 6, 2025):

What is the difference between GTT & VRAM?

<!-- gh-comment-id:3371239803 --> @fayakun-it-consulting commented on GitHub (Oct 6, 2025): What is the difference between GTT & VRAM?
GiteaMirror commented 2026-04-29 07:14:10 -05:00
Author
Owner
Copy Link

@Djip007 commented on GitHub (Oct 21, 2025):

The model is never loaded to the iGPU allocated RAM. Although that the processing is done by the iGPU. You can see in the logs and in the screenshot.

so what is the probleme?

for RAM vs vRAM vs GTT see: https://github.com/ollama/ollama/issues/12342#issuecomment-3428629934

<!-- gh-comment-id:3428893128 --> @Djip007 commented on GitHub (Oct 21, 2025): > The model is never loaded to the iGPU allocated RAM. Although that the processing is done by the iGPU. You can see in the logs and in the screenshot. so what is the probleme? for RAM vs vRAM vs GTT see: https://github.com/ollama/ollama/issues/12342#issuecomment-3428629934
GiteaMirror commented 2026-04-29 07:14:11 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Oct 21, 2025):

The model is never loaded to the iGPU allocated RAM. Although that the processing is done by the iGPU. You can see in the logs and in the screenshot.

so what is the probleme?

for RAM vs vRAM vs GTT see: https://github.com/ollama/ollama/issues/12342#issuecomment-3428629934

The problem is that the VRAM that I reserved on my RAM which is 16GB for the Radeon 780M is not used at all. The GTT is filled but not the VRAM.

When I use gpt4all it loads the model into the reserved VRAM. And in the GTT.

There's a waste of 16 GB VRAM.

Look at the orange line in screenshots: They are used with gpt4all but not with Ollama.

https://github.com/ollama/ollama/issues/12411#issuecomment-3335085427

<!-- gh-comment-id:3429461017 --> @fayakun-it-consulting commented on GitHub (Oct 21, 2025): > > The model is never loaded to the iGPU allocated RAM. Although that the processing is done by the iGPU. You can see in the logs and in the screenshot. > > so what is the probleme? > > for RAM vs vRAM vs GTT see: https://github.com/ollama/ollama/issues/12342#issuecomment-3428629934 The problem is that the VRAM that I reserved on my RAM which is 16GB for the Radeon 780M is not used at all. The GTT is filled but not the VRAM. When I use gpt4all it loads the model into the reserved VRAM. And in the GTT. There's a waste of 16 GB VRAM. Look at the orange line in screenshots: They are used with gpt4all but not with Ollama. https://github.com/ollama/ollama/issues/12411#issuecomment-3335085427
GiteaMirror commented 2026-04-29 07:14:11 -05:00
Author
Owner
Copy Link

@fayakun-it-consulting commented on GitHub (Oct 21, 2025):

It looks like this https://github.com/ollama/ollama/issues/12342

<!-- gh-comment-id:3429499169 --> @fayakun-it-consulting commented on GitHub (Oct 21, 2025): It looks like this https://github.com/ollama/ollama/issues/12342
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 needs more info
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#54757
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?