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 #9819] fail to use gpu #68485

New Issue
Closed
opened 2026-05-04 14:08:21 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 14:08:21 -05:00
Owner
Copy Link

Originally created by @yongjer on GitHub (Mar 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9819

What is the issue?

start the container:

docker run -d \
    --gpus all \
    -v ollama:/root/.ollama \
    -p 11434:11434 \
    --name ollama \
    -e OLLAMA_FLASH_ATTENTION=1 \
    ollama/ollama

using ollama ps shows that the whole model running on CPU
gpu: RTX 4060Ti

Relevant log output

container log:

2025/03/17 11:20:06 routes.go:1230: 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_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-03-17T11:20:06.479Z level=INFO source=images.go:432 msg="total blobs: 31"
time=2025-03-17T11:20:06.479Z level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-17T11:20:06.480Z level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.1)"
time=2025-03-17T11:20:06.480Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-03-17T11:20:06.482Z level=WARN source=gpu.go:605 msg="unknown error initializing cuda driver library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15: cuda driver library init failure: 999. see https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md for more information"
time=2025-03-17T11:20:06.483Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-03-17T11:20:06.483Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="31.2 GiB" available="23.4 GiB"
[GIN] 2025/03/17 - 11:20:13 | 200 |      42.099µs |       127.0.0.1 | GET      "/api/version"

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

0.6.1

Originally created by @yongjer on GitHub (Mar 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9819 ### What is the issue? start the container: ``` docker run -d \ --gpus all \ -v ollama:/root/.ollama \ -p 11434:11434 \ --name ollama \ -e OLLAMA_FLASH_ATTENTION=1 \ ollama/ollama ``` using ```ollama ps``` shows that the whole model running on CPU gpu: ```RTX 4060Ti``` ### Relevant log output ```shell container log: 2025/03/17 11:20:06 routes.go:1230: 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_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false 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:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-03-17T11:20:06.479Z level=INFO source=images.go:432 msg="total blobs: 31" time=2025-03-17T11:20:06.479Z level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-17T11:20:06.480Z level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.1)" time=2025-03-17T11:20:06.480Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-03-17T11:20:06.482Z level=WARN source=gpu.go:605 msg="unknown error initializing cuda driver library /usr/lib/x86_64-linux-gnu/libcuda.so.570.86.15: cuda driver library init failure: 999. see https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md for more information" time=2025-03-17T11:20:06.483Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-03-17T11:20:06.483Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="31.2 GiB" available="23.4 GiB" [GIN] 2025/03/17 - 11:20:13 | 200 | 42.099µs | 127.0.0.1 | GET "/api/version" ``` ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version 0.6.1
GiteaMirror added the bug label 2026-05-04 14:08:21 -05:00
GiteaMirror commented 2026-05-04 14:08:28 -05:00
Author
Owner
Copy Link

@yongjer commented on GitHub (Mar 17, 2025):

using nvidia-smi in docker:

Mon Mar 17 11:27:12 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.86.15              Driver Version: 570.86.15      CUDA Version: 12.8     |
|-----------------------------------------+------------------------+----------------------+
| 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  NVIDIA GeForce RTX 4060 Ti     Off |   00000000:01:00.0  On |                  N/A |
|  0%   37C    P8             13W /  165W |     786MiB /  16380MiB |     36%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
+-----------------------------------------------------------------------------------------+
<!-- gh-comment-id:2729144972 --> @yongjer commented on GitHub (Mar 17, 2025): using ```nvidia-smi``` in docker: ``` Mon Mar 17 11:27:12 2025 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 570.86.15 Driver Version: 570.86.15 CUDA Version: 12.8 | |-----------------------------------------+------------------------+----------------------+ | 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 NVIDIA GeForce RTX 4060 Ti Off | 00000000:01:00.0 On | N/A | | 0% 37C P8 13W / 165W | 786MiB / 16380MiB | 36% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| +-----------------------------------------------------------------------------------------+ ```
GiteaMirror commented 2026-05-04 14:08:32 -05:00
Author
Owner
Copy Link

@yongjer commented on GitHub (Mar 17, 2025):

solve it by running sudo nvidia-ctk runtime configure --runtime=docker then restart

<!-- gh-comment-id:2729201869 --> @yongjer commented on GitHub (Mar 17, 2025): solve it by running ```sudo nvidia-ctk runtime configure --runtime=docker``` then restart
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#68485
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?