Pastein: nvidia-smi Wed Sep 2 19:32:26 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.173.02 Driver Version: 580.173.02

Загрузка данных
nvidia-smi
Wed Sep  2 19:32:26 2026       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.173.02             Driver Version: 580.173.02     CUDA Version: 13.0     |
+-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  Tesla P40                      Off |   00000000:01:00.0 Off |                  Off |
| N/A   77C    P8             18W /  250W |       4MiB /  24576MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|    0   N/A  N/A            2671      G   /usr/bin/gnome-shell                      3MiB |
+-----------------------------------------------------------------------------------------+
user@user-MS-7D91:~$ sudo journalctl -u ollama -e -n 40 --no-pager
Sep 02 19:31:55 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | checking checkpoint with [70, 70] against 41...
Sep 02 19:31:55 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | forcing full prompt re-processing due to lack of cache data (likely due to SWA or hybrid/recurrent memory, see https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
Sep 02 19:31:55 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | erased invalidated context checkpoint (pos_min = 70, pos_max = 70, n_tokens = 71, n_swa = 0, pos_next = 0, size = 149.626 MiB)
Sep 02 19:31:55 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | erased invalidated context checkpoint (pos_min = 331, pos_max = 331, n_tokens = 332, n_swa = 0, pos_next = 0, size = 149.626 MiB)
Sep 02 19:31:55 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 0, memory_seq_rm [0, end)
Sep 02 19:31:56 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 512, memory_seq_rm [512, end)
Sep 02 19:31:58 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   1024, progress = 0.17, t =   3.01 s / 340.02 tokens per second
Sep 02 19:31:58 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 1024, memory_seq_rm [1024, end)
Sep 02 19:32:00 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   1536, progress = 0.25, t =   5.03 s / 305.62 tokens per second
Sep 02 19:32:00 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 1536, memory_seq_rm [1536, end)
Sep 02 19:32:02 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   2048, progress = 0.33, t =   7.07 s / 289.77 tokens per second
Sep 02 19:32:02 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 2048, memory_seq_rm [2048, end)
Sep 02 19:32:04 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   2560, progress = 0.42, t =   9.13 s / 280.37 tokens per second
Sep 02 19:32:04 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 2560, memory_seq_rm [2560, end)
Sep 02 19:32:06 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   3072, progress = 0.50, t =  11.22 s / 273.76 tokens per second
Sep 02 19:32:06 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 3072, memory_seq_rm [3072, end)
Sep 02 19:32:08 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   3584, progress = 0.59, t =  13.34 s / 268.66 tokens per second
Sep 02 19:32:08 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 3584, memory_seq_rm [3584, end)
Sep 02 19:32:10 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   4096, progress = 0.67, t =  15.48 s / 264.56 tokens per second
Sep 02 19:32:10 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 4096, memory_seq_rm [4096, end)
Sep 02 19:32:13 user-MS-7D91 ollama[4117]: slot print_timing: id  0 | task 136 | prompt processing, n_tokens =   4608, progress = 0.75, t =  17.65 s / 261.06 tokens per second
Sep 02 19:32:13 user-MS-7D91 ollama[4117]: slot   operator(): id  0 | task 136 | cached n_tokens = 4608, memory_seq_rm [4608, end)
Sep 02 19:32:15 user-MS-7D91 systemd[1]: Stopping ollama.service - Ollama Service...
Sep 02 19:32:15 user-MS-7D91 ollama[4117]: [GIN] 2026/09/02 - 19:32:15 | 500 | 41.897783312s |      172.17.0.2 | POST     "/api/chat"
Sep 02 19:32:16 user-MS-7D91 systemd[1]: ollama.service: Deactivated successfully.
Sep 02 19:32:16 user-MS-7D91 systemd[1]: Stopped ollama.service - Ollama Service.
Sep 02 19:32:16 user-MS-7D91 systemd[1]: ollama.service: Consumed 1min 33.182s CPU time over 2min 53.819s wall clock time, 17.2G memory peak.
Sep 02 19:32:16 user-MS-7D91 systemd[1]: Started ollama.service - Ollama Service.
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.260+03:00 level=INFO source=routes.go:1951 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: LLAMA_ARG_FIT: LLAMA_ARG_FIT_TARGET: NO_PROXY: OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GO_TEMPLATE:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_IGPU_ENABLE: 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_MAX_TRANSFER_STREAMS:4 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.261+03:00 level=INFO source=routes.go:1953 msg="Ollama cloud disabled: false"
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.261+03:00 level=INFO source=images.go:919 msg="total blobs: 5"
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.262+03:00 level=INFO source=images.go:926 msg="total unused blobs removed: 0"
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.262+03:00 level=INFO source=routes.go:2008 msg="Listening on [::]:11434 (version 0.33.2)"
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.263+03:00 level=INFO source=runner.go:60 msg="discovering available GPUs..."
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.265+03:00 level=INFO source=model_list_cache.go:112 msg="model list cache hydration complete" models=2 failures=0 elapsed=2.890929ms
Sep 02 19:32:16 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:16.429+03:00 level=INFO source=model_recommendations.go:177 msg="model recommendations cache sleep scheduled" wait=4h11m46.603519324s consecutive_failures=0
Sep 02 19:32:17 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:17.291+03:00 level=INFO source=llama_server.go:295 msg="skipping CUDA device — compute capability not in compiled architectures" device="Tesla P40" cc=610 archs="[750 800 860 870 890 900 1000 1030 1100 1200 1210]" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]"
Sep 02 19:32:17 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:17.439+03:00 level=INFO source=runner.go:405 msg="dropping integrated GPU; to enable, set OLLAMA_IGPU_ENABLE=1" id=0 library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Graphics (RPL-S)" pci_id=0000:00:02.0
Sep 02 19:32:17 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:17.878+03:00 level=INFO source=types.go:32 msg="inference compute" id=0 filter_id=0 library=CUDA compute=6.1 name=CUDA0 description="Tesla P40" libdirs=ollama,cuda_v12 driver=13.0 pci_id=0000:01:00.0 type=discrete total="23.9 GiB" available="23.7 GiB"
Sep 02 19:32:17 user-MS-7D91 ollama[6454]: time=2026-09-02T19:32:17.878+03:00 level=INFO source=routes.go:2058 msg="vram-based default context" total_vram="23.9 GiB" default_num_ctx=32768
user@user-MS-7D91:~$
Больше возможностей при регистрации:
