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 #7669] Only CPU is used after rebooting #4895

New Issue
Open
opened 2026-04-12 15:56:08 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-12 15:56:08 -05:00
Owner
Copy Link

Originally created by @3DAlgoLab on GitHub (Nov 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7669

Originally assigned to: @dhiltgen on GitHub.

I found someone wrote a thread describing only cpu is used after rebooting in windows
I also had similar problems even in Ubuntu OS.

I used the latest version(0.4.1). I guess this bug comes from that the ollama service is started faster than the init. of GPUs. So I make an ad-hoc solution. Instead of service, I just make a script delaying start serve(ollama serve).

# ollama_run 
echo "Delayed Ollama Runner Start, it delays 10 sec."
sleep 10
ollama serve

Then I make this called from Ubuntu Startup Application Preferences. I think its delaying may not be needed as it is called after GPUs initialization is finished anyway.
capture 2024-11-15 042959

WARNING: After starting ollama by calling directly ollama serve, model storage directory is changed to ~/.ollama/models.(I don't know why?) So previously dowonloaded model is not loaded. In that case, you can copy or move whole models folder to '[home folder]/.ollama from/usr/share/ollama/.ollama`.

Originally posted by @3DAlgoLab in https://github.com/ollama/ollama/issues/4984#issuecomment-2477251430

Originally created by @3DAlgoLab on GitHub (Nov 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7669 Originally assigned to: @dhiltgen on GitHub. [I found someone wrote a thread describing only cpu is used after rebooting in windows ](https://github.com/ollama/ollama/issues/4984#issue-2347076913) I also had similar problems even in Ubuntu OS. I used the latest version(0.4.1). I guess this bug comes from that the ollama service is started faster than the init. of GPUs. So I make an **ad-hoc** solution. Instead of service, I just make a script delaying start serve(ollama serve). ```bash # ollama_run echo "Delayed Ollama Runner Start, it delays 10 sec." sleep 10 ollama serve ``` Then I make this called from *Ubuntu Startup Application Preferences*. I think its delaying may not be needed as it is called after GPUs initialization is finished anyway. ![capture 2024-11-15 042959](https://github.com/user-attachments/assets/80ca322d-49ea-4baa-991d-15b1413612ef) **WARNING**: After starting ollama by calling directly `ollama serve`, model storage directory is changed to `~/.ollama/models`.(I don't know why?) So previously dowonloaded model is not loaded. In that case, you can copy or move whole models folder to '[home folder]/.ollama` from `/usr/share/ollama/.ollama`. _Originally posted by @3DAlgoLab in https://github.com/ollama/ollama/issues/4984#issuecomment-2477251430_
GiteaMirror added the linuxnvidia labels 2026-04-12 15:56:08 -05:00
GiteaMirror commented 2026-04-12 15:56:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 14, 2024):

If you're using the standard way that ollama is installed on a linux system, you can do this in the service file. Run sudo systemctl edit ollama and add

[Service]
ExecStartPre=sleep 10

This will preserve the model location and file ownership.

<!-- gh-comment-id:2477305337 --> @rick-github commented on GitHub (Nov 14, 2024): If you're using the standard way that ollama is installed on a linux system, you can do this in the service file. Run `sudo systemctl edit ollama` and add ``` [Service] ExecStartPre=sleep 10 ``` This will preserve the model location and file ownership.
GiteaMirror commented 2026-04-12 15:56:15 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 15, 2024):

What error was reported in the server log when we tried to discover the GPU without delaying startup? What GPU are you using?

<!-- gh-comment-id:2477676927 --> @dhiltgen commented on GitHub (Nov 15, 2024): What error was reported in the server log when we tried to discover the GPU without delaying startup? What GPU are you using?
GiteaMirror commented 2026-04-12 15:56:17 -05:00
Author
Owner
Copy Link

@3DAlgoLab commented on GitHub (Nov 15, 2024):

What error was reported in the server log when we tried to discover the GPU without delaying startup? What GPU are you using?

I use RTX 4060 16gb x 4 gpus. I attached an image for system info.
system info

Following is the part of log.

# when gpus are working

Nov 12 19:58:16 tal-ai-server systemd[1]: Started Ollama Service.
Nov 12 19:58:16 tal-ai-server ollama[23401]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key.
Nov 12 19:58:16 tal-ai-server ollama[23401]: Your new public key is:
Nov 12 19:58:16 tal-ai-server ollama[23401]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIOZ5r6AlHTCVccHJOCTIWycHVm21fcMyOJkyg0xaDBe+
Nov 12 19:58:16 tal-ai-server ollama[23401]: 2024/11/12 19:58:16 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.186+09:00 level=INFO source=images.go:755 msg="total blobs: 0"
Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.187+09:00 level=INFO source=images.go:762 msg="total unused blobs removed: 0"
Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.187+09:00 level=INFO source=routes.go:1240 msg="Listening on 127.0.0.1:11434 (version 0.4.1)"
Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.187+09:00 level=INFO source=common.go:135 msg="extracting embedded files" dir=/tmp/ollama1650350663/runners
Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.379+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12 rocm]"
Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.379+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-4f5d8b8f-5082-a542-2b46-4a4a5b106800 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB"
Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-f7b952c7-bad8-3ef5-f3b7-2f17738bf00c library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB"
Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-32f83946-441d-392a-e341-4755fef567b5 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB"
Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-08df1c3a-6ee5-2950-7ab1-10263e1f647b library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB"


# When gpus are not detected

Nov 14 08:53:08 tal-ai-server systemd[1]: Started Ollama Service.
Nov 14 08:53:08 tal-ai-server ollama[1296]: 2024/11/14 08:53:08 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.001+09:00 level=INFO source=images.go:755 msg="total blobs: 16"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.001+09:00 level=INFO source=images.go:762 msg="total unused blobs removed: 0"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.001+09:00 level=INFO source=routes.go:1240 msg="Listening on 127.0.0.1:11434 (version 0.4.1)"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.002+09:00 level=INFO source=common.go:135 msg="extracting embedded files" dir=/tmp/ollama4094722987/runners
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.136+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[rocm cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.136+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.162+09:00 level=INFO source=gpu.go:610 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.550.120"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.179+09:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered"
Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.179+09:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="251.6 GiB" available="248.7 GiB"
Nov 14 08:56:29 tal-ai-server ollama[1296]: [GIN] 2024/11/14 - 08:56:29 | 200 |     504.935µs |       127.0.0.1 | HEAD     "/"
Nov 14 08:56:29 tal-ai-server ollama[1296]: [GIN] 2024/11/14 - 08:56:29 | 200 |    1.633768ms |       127.0.0.1 | GET      "/api/tags"
Nov 14 08:58:28 tal-ai-server ollama[1296]: [GIN] 2024/11/14 - 08:58:28 | 200 |      32.461µs |       127.0.0.1 | HEAD     "/"
...

If you're using the standard way that ollama is installed on a linux system, you can do this in the service file. Run sudo systemctl edit ollama and add

[Service]
ExecStartPre=sleep 10

This will preserve the model location and file ownership.

That's a good idea I'll try it!

<!-- gh-comment-id:2477914340 --> @3DAlgoLab commented on GitHub (Nov 15, 2024): > What error was reported in the server log when we tried to discover the GPU without delaying startup? What GPU are you using? I use RTX 4060 16gb x 4 gpus. I attached an image for system info. ![system info](https://github.com/user-attachments/assets/fe58a56e-0107-4a47-b8f0-3847650c5f8c) Following is the part of log. ```log # when gpus are working Nov 12 19:58:16 tal-ai-server systemd[1]: Started Ollama Service. Nov 12 19:58:16 tal-ai-server ollama[23401]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Nov 12 19:58:16 tal-ai-server ollama[23401]: Your new public key is: Nov 12 19:58:16 tal-ai-server ollama[23401]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIOZ5r6AlHTCVccHJOCTIWycHVm21fcMyOJkyg0xaDBe+ Nov 12 19:58:16 tal-ai-server ollama[23401]: 2024/11/12 19:58:16 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.186+09:00 level=INFO source=images.go:755 msg="total blobs: 0" Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.187+09:00 level=INFO source=images.go:762 msg="total unused blobs removed: 0" Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.187+09:00 level=INFO source=routes.go:1240 msg="Listening on 127.0.0.1:11434 (version 0.4.1)" Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.187+09:00 level=INFO source=common.go:135 msg="extracting embedded files" dir=/tmp/ollama1650350663/runners Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.379+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12 rocm]" Nov 12 19:58:16 tal-ai-server ollama[23401]: time=2024-11-12T19:58:16.379+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs" Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-4f5d8b8f-5082-a542-2b46-4a4a5b106800 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB" Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-f7b952c7-bad8-3ef5-f3b7-2f17738bf00c library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB" Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-32f83946-441d-392a-e341-4755fef567b5 library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB" Nov 12 19:58:17 tal-ai-server ollama[23401]: time=2024-11-12T19:58:17.059+09:00 level=INFO source=types.go:123 msg="inference compute" id=GPU-08df1c3a-6ee5-2950-7ab1-10263e1f647b library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4060 Ti" total="15.7 GiB" available="15.6 GiB" # When gpus are not detected Nov 14 08:53:08 tal-ai-server systemd[1]: Started Ollama Service. Nov 14 08:53:08 tal-ai-server ollama[1296]: 2024/11/14 08:53:08 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.001+09:00 level=INFO source=images.go:755 msg="total blobs: 16" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.001+09:00 level=INFO source=images.go:762 msg="total unused blobs removed: 0" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.001+09:00 level=INFO source=routes.go:1240 msg="Listening on 127.0.0.1:11434 (version 0.4.1)" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.002+09:00 level=INFO source=common.go:135 msg="extracting embedded files" dir=/tmp/ollama4094722987/runners Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.136+09:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[rocm cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.136+09:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.162+09:00 level=INFO source=gpu.go:610 msg="no nvidia devices detected by library /usr/lib/x86_64-linux-gnu/libcuda.so.550.120" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.179+09:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered" Nov 14 08:53:09 tal-ai-server ollama[1296]: time=2024-11-14T08:53:09.179+09:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="251.6 GiB" available="248.7 GiB" Nov 14 08:56:29 tal-ai-server ollama[1296]: [GIN] 2024/11/14 - 08:56:29 | 200 | 504.935µs | 127.0.0.1 | HEAD "/" Nov 14 08:56:29 tal-ai-server ollama[1296]: [GIN] 2024/11/14 - 08:56:29 | 200 | 1.633768ms | 127.0.0.1 | GET "/api/tags" Nov 14 08:58:28 tal-ai-server ollama[1296]: [GIN] 2024/11/14 - 08:58:28 | 200 | 32.461µs | 127.0.0.1 | HEAD "/" ... ``` > If you're using the standard way that ollama is installed on a linux system, you can do this in the service file. Run `sudo systemctl edit ollama` and add > > ``` > [Service] > ExecStartPre=sleep 10 > ``` > > This will preserve the model location and file ownership. That's a good idea I'll try it!
GiteaMirror commented 2026-04-12 15:56:18 -05:00
Author
Owner
Copy Link

@3DAlgoLab commented on GitHub (Nov 15, 2024):

I tried rick-github's idea. It works. It's more elegant way as ad-hoc. Thanks.

[Service]
ExecStartPre=sleep 10

$ ollama ps
NAME                   ID              SIZE      PROCESSOR    UNTIL              
llava-llama3:latest    44c161b1f465    9.2 GB    100% GPU     4 minutes from now
<!-- gh-comment-id:2477959445 --> @3DAlgoLab commented on GitHub (Nov 15, 2024): I tried rick-github's idea. It works. It's more elegant way as ad-hoc. Thanks. ```ini [Service] ExecStartPre=sleep 10 ``` ```bash $ ollama ps NAME ID SIZE PROCESSOR UNTIL llava-llama3:latest 44c161b1f465 9.2 GB 100% GPU 4 minutes from now ```
GiteaMirror commented 2026-04-12 15:56:19 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 18, 2024):

Based on those logs, it looks like we did not get an error back from the nvidia libraries, it simply said there were zero GPUs present. The sleep sounds like a reasonable workaround, but we may need to explore wiring up dependencies to wait until after nvidia components are loaded.

<!-- gh-comment-id:2484096229 --> @dhiltgen commented on GitHub (Nov 18, 2024): Based on those logs, it looks like we did not get an error back from the nvidia libraries, it simply said there were zero GPUs present. The sleep sounds like a reasonable workaround, but we may need to explore wiring up dependencies to wait until after nvidia components are loaded.
GiteaMirror commented 2026-04-12 15:56:20 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 19, 2024):

@3DAlgoLab can you confirm that you're booting fresh, and this isn't a suspend/resume scenario? If it is suspend/resume we can track this via #5464

<!-- gh-comment-id:2484465433 --> @dhiltgen commented on GitHub (Nov 19, 2024): @3DAlgoLab can you confirm that you're booting fresh, and this isn't a suspend/resume scenario? If it is suspend/resume we can track this via #5464
GiteaMirror commented 2026-04-12 15:56:20 -05:00
Author
Owner
Copy Link

@3DAlgoLab commented on GitHub (Nov 19, 2024):

@dhiltgen, it seems not related with suspend/resume, as my workstation always wakes on if it is started. but for some curiosity, I tried suspend/resume tomorrow after some job is finished.

<!-- gh-comment-id:2484516937 --> @3DAlgoLab commented on GitHub (Nov 19, 2024): @dhiltgen, it seems not related with suspend/resume, as my workstation always wakes on if it is started. but for some curiosity, I tried suspend/resume tomorrow after some job is finished.
GiteaMirror commented 2026-04-12 15:56:21 -05:00
Author
Owner
Copy Link

@3DAlgoLab commented on GitHub (Nov 19, 2024):

@dhiltgen, after suspended for some minutes, then I resumed it. But no symptons like GPU detection error happened. It worked well.

<!-- gh-comment-id:2484643234 --> @3DAlgoLab commented on GitHub (Nov 19, 2024): @dhiltgen, after suspended for some minutes, then I resumed it. But no symptons like GPU detection error happened. It worked well.
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 linux nvidia
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#4895
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?