ollama не находит GPU
Добавлено: 09 авг 2026, 00:28
adm1007s
Бьюсь уже несколько дней, не получается запустить модель с использованием GPU Nvidia, не находит видеокарту просто.
Поиски в интернет подводят к тому, что сборка ollama сделана с жёсткой привязкой значения параметра OLLAMA_LIBRARY_PATH=[/usr/bin], когда нужно вроде OLLAMA_LIBRARY_PATH=/usr/lib64/ollama.
По тем же рекомендациям выставлял параметры сервису и при непосредственном старте в окружение загонял пути, не помогает.
В принципе до запуска модели я добарлся через LM Studio, но хочется из дистриба пакет заставить работать.
Может кто победил уже?
Весь лог запуска прилагаю.
Поиски в интернет подводят к тому, что сборка ollama сделана с жёсткой привязкой значения параметра OLLAMA_LIBRARY_PATH=[/usr/bin], когда нужно вроде OLLAMA_LIBRARY_PATH=/usr/lib64/ollama.
По тем же рекомендациям выставлял параметры сервису и при непосредственном старте в окружение загонял пути, не помогает.
[Service]
Environment="OLLAMA_LIBRARY_PATH=/usr/lib64/ollama"
Environment="LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64:/usr/lib64/nvidia580/"
Environment="OLLAMA_DEBUG=1"
Environment="OLLAMA_LIBRARY_PATH=/usr/lib64/ollama"
Environment="LD_LIBRARY_PATH=/usr/lib64/ollama:/usr/lib64:/usr/lib64/nvidia580/"
Environment="OLLAMA_DEBUG=1"
Может кто победил уже?
Весь лог запуска прилагаю.
авг 09 00:05:41 rosa systemd[1]: Started Ollama Service.
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=routes.go:1631 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/lib/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=images.go:473 msg="total blobs: 7"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
авг 09 00:05:41 rosa ollama[9716]: - using env: export GIN_MODE=release
авг 09 00:05:41 rosa ollama[9716]: - using code: gin.SetMode(gin.ReleaseMode)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func3 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func4 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/me --> github.com/ollama/ollama/server.(*Server).WhoamiHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/signout --> github.com/ollama/ollama/server.(*Server).SignoutHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] DELETE /api/user/keys/:encodedKey --> github.com/ollama/ollama/server.(*Server).SignoutHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/responses --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/images/generations --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/images/edits --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/messages --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=routes.go:1684 msg="Listening on 127.0.0.1:11434 (version 0.0.0)"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.097+03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.097+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35281"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.097+03:00 level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin OLLAMA_CUDA_VERSION=12.9 OLLAMA_LIBRARY_PATH=/usr/bin LD_LIBRARY_PATH=/usr/bin:/usr/lib64/ollama:/usr/lib64:/usr/lib64/nvidia580/ OLLAMA_DEBUG=1
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=26.373459ms OLLAMA_LIBRARY_PATH=[/usr/bin] extra_envs=map[]
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=30.02131ms
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="62.4 GiB" available="57.8 GiB"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=INFO source=routes.go:1725 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
авг 09 00:05:48 rosa systemd[1]: Stopping Ollama Service...
авг 09 00:05:48 rosa systemd[1]: ollama.service: Deactivated successfully.
авг 09 00:05:48 rosa systemd[1]: Stopped Ollama Service.
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=routes.go:1631 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/var/lib/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=images.go:473 msg="total blobs: 7"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.
авг 09 00:05:41 rosa ollama[9716]: - using env: export GIN_MODE=release
авг 09 00:05:41 rosa ollama[9716]: - using code: gin.SetMode(gin.ReleaseMode)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func1 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET / --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func2 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func3 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(*Server).GenerateRoutes.func4 (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(*Server).PullHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(*Server).PushHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(*Server).DeleteHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/me --> github.com/ollama/ollama/server.(*Server).WhoamiHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/signout --> github.com/ollama/ollama/server.(*Server).SignoutHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] DELETE /api/user/keys/:encodedKey --> github.com/ollama/ollama/server.(*Server).SignoutHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(*Server).CreateHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).CreateBlobHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(*Server).HeadBlobHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(*Server).CopyHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(*Server).PsHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(*Server).EmbedHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(*Server).ListHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(*Server).ShowHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/responses --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/images/generations --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/images/edits --> github.com/ollama/ollama/server.(*Server).GenerateHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: [GIN-debug] POST /v1/messages --> github.com/ollama/ollama/server.(*Server).ChatHandler-fm (6 handlers)
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=INFO source=routes.go:1684 msg="Listening on 127.0.0.1:11434 (version 0.0.0)"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.093+03:00 level=DEBUG source=sched.go:121 msg="starting llm scheduler"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.097+03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.097+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 35281"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.097+03:00 level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin OLLAMA_CUDA_VERSION=12.9 OLLAMA_LIBRARY_PATH=/usr/bin LD_LIBRARY_PATH=/usr/bin:/usr/lib64/ollama:/usr/lib64:/usr/lib64/nvidia580/ OLLAMA_DEBUG=1
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=26.373459ms OLLAMA_LIBRARY_PATH=[/usr/bin] extra_envs=map[]
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=30.02131ms
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="62.4 GiB" available="57.8 GiB"
авг 09 00:05:41 rosa ollama[9716]: time=2026-08-09T00:05:41.123+03:00 level=INFO source=routes.go:1725 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
авг 09 00:05:48 rosa systemd[1]: Stopping Ollama Service...
авг 09 00:05:48 rosa systemd[1]: ollama.service: Deactivated successfully.
авг 09 00:05:48 rosa systemd[1]: Stopped Ollama Service.