github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12352] cuda driver library init failure: 205 #54718

New Issue
Closed
opened 2026-04-29 07:05:13 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 07:05:13 -05:00
Owner
Copy Link

Originally created by @srshkmr on GitHub (Sep 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12352

What is the issue?

Ollama not using GPU but devices are visible for the container

Relevant log output

docker logs ollama_gpu
time=2025-09-20T07:16:49.203Z level=INFO source=routes.go:1466 msg="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:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false 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: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 ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-09-20T07:16:49.203Z level=INFO source=images.go:518 msg="total blobs: 0"
time=2025-09-20T07:16:49.204Z level=INFO source=images.go:525 msg="total unused blobs removed: 0"
time=2025-09-20T07:16:49.204Z level=INFO source=routes.go:1519 msg="Listening on [::]:11434 (version 0.12.0)"
time=2025-09-20T07:16:49.204Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-09-20T07:16:49.255Z level=INFO source=gpu.go:631 msg="Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01: cuda driver library init failure: 205"
time=2025-09-20T07:16:49.259Z level=INFO source=gpu.go:396 msg="no compatible GPUs were discovered"
time=2025-09-20T07:16:49.259Z level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="503.8 GiB" available="493.7 GiB"


docker exec -it ollama_gpu bash -lc 'ls -l /dev/nvidia* && nvidia-smi -L'
crw-rw-rw- 1 root root 509,   0 Aug  6 07:23 /dev/nvidia-uvm
crw-rw-rw- 1 root root 509,   1 Aug  6 07:23 /dev/nvidia-uvm-tools
crw-rw-rw- 1 root root 195,   0 Aug  6 07:23 /dev/nvidia0
crw-rw-rw- 1 root root 195,   1 Aug  6 07:23 /dev/nvidia1
crw-rw-rw- 1 root root 195,   2 Aug  6 07:23 /dev/nvidia2
crw-rw-rw- 1 root root 195,   3 Aug  6 07:23 /dev/nvidia3
crw-rw-rw- 1 root root 195,   4 Aug  6 07:23 /dev/nvidia4
crw-rw-rw- 1 root root 195,   5 Aug  6 07:23 /dev/nvidia5
crw-rw-rw- 1 root root 195,   6 Aug  6 07:23 /dev/nvidia6
crw-rw-rw- 1 root root 195,   7 Aug  6 07:23 /dev/nvidia7
crw-rw-rw- 1 root root 195, 255 Aug  6 07:23 /dev/nvidiactl
GPU 0: Tesla V100-SXM2-32GB (UUID: GPU-23e1acaf-bad8-ccca-b9f3-bcee5fc188a6)
GPU 1: Tesla V100-SXM2-32GB (UUID: GPU-b68f1f98-65b7-5328-f3ee-63fa5448f0b0)
GPU 2: Tesla V100-SXM2-32GB (UUID: GPU-41e7ab21-5bc3-b454-300f-440c1ba8c243)
GPU 3: Tesla V100-SXM2-32GB (UUID: GPU-8794b9db-bb90-3c4c-b58c-a570796dc18f)
GPU 4: Tesla V100-SXM2-32GB (UUID: GPU-6ba4155a-d237-0b4d-2f3c-809c1ad67836)
GPU 5: Tesla V100-SXM2-32GB (UUID: GPU-458332e0-3d9a-d412-b15d-55d861ce24cd)
GPU 6: Tesla V100-SXM2-32GB (UUID: GPU-07603db3-907c-4310-ed95-cd189718135e)
GPU 7: Tesla V100-SXM2-32GB (UUID: GPU-fcb0be32-9b66-3191-0583-ac0477006346)

OS

Linux, Docker

GPU

Nvidia

CPU

Intel

Ollama version

0.12.0

Originally created by @srshkmr on GitHub (Sep 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12352 ### What is the issue? Ollama not using GPU but devices are visible for the container ### Relevant log output ```shell docker logs ollama_gpu time=2025-09-20T07:16:49.203Z level=INFO source=routes.go:1466 msg="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:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false 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: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 ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-09-20T07:16:49.203Z level=INFO source=images.go:518 msg="total blobs: 0" time=2025-09-20T07:16:49.204Z level=INFO source=images.go:525 msg="total unused blobs removed: 0" time=2025-09-20T07:16:49.204Z level=INFO source=routes.go:1519 msg="Listening on [::]:11434 (version 0.12.0)" time=2025-09-20T07:16:49.204Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-09-20T07:16:49.255Z level=INFO source=gpu.go:631 msg="Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01: cuda driver library init failure: 205" time=2025-09-20T07:16:49.259Z level=INFO source=gpu.go:396 msg="no compatible GPUs were discovered" time=2025-09-20T07:16:49.259Z level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="503.8 GiB" available="493.7 GiB" docker exec -it ollama_gpu bash -lc 'ls -l /dev/nvidia* && nvidia-smi -L' crw-rw-rw- 1 root root 509, 0 Aug 6 07:23 /dev/nvidia-uvm crw-rw-rw- 1 root root 509, 1 Aug 6 07:23 /dev/nvidia-uvm-tools crw-rw-rw- 1 root root 195, 0 Aug 6 07:23 /dev/nvidia0 crw-rw-rw- 1 root root 195, 1 Aug 6 07:23 /dev/nvidia1 crw-rw-rw- 1 root root 195, 2 Aug 6 07:23 /dev/nvidia2 crw-rw-rw- 1 root root 195, 3 Aug 6 07:23 /dev/nvidia3 crw-rw-rw- 1 root root 195, 4 Aug 6 07:23 /dev/nvidia4 crw-rw-rw- 1 root root 195, 5 Aug 6 07:23 /dev/nvidia5 crw-rw-rw- 1 root root 195, 6 Aug 6 07:23 /dev/nvidia6 crw-rw-rw- 1 root root 195, 7 Aug 6 07:23 /dev/nvidia7 crw-rw-rw- 1 root root 195, 255 Aug 6 07:23 /dev/nvidiactl GPU 0: Tesla V100-SXM2-32GB (UUID: GPU-23e1acaf-bad8-ccca-b9f3-bcee5fc188a6) GPU 1: Tesla V100-SXM2-32GB (UUID: GPU-b68f1f98-65b7-5328-f3ee-63fa5448f0b0) GPU 2: Tesla V100-SXM2-32GB (UUID: GPU-41e7ab21-5bc3-b454-300f-440c1ba8c243) GPU 3: Tesla V100-SXM2-32GB (UUID: GPU-8794b9db-bb90-3c4c-b58c-a570796dc18f) GPU 4: Tesla V100-SXM2-32GB (UUID: GPU-6ba4155a-d237-0b4d-2f3c-809c1ad67836) GPU 5: Tesla V100-SXM2-32GB (UUID: GPU-458332e0-3d9a-d412-b15d-55d861ce24cd) GPU 6: Tesla V100-SXM2-32GB (UUID: GPU-07603db3-907c-4310-ed95-cd189718135e) GPU 7: Tesla V100-SXM2-32GB (UUID: GPU-fcb0be32-9b66-3191-0583-ac0477006346) ``` ### OS Linux, Docker ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.0
GiteaMirror added the bug label 2026-04-29 07:05:13 -05:00
GiteaMirror commented 2026-04-29 07:05:20 -05:00
Author
Owner
Copy Link

@srshkmr commented on GitHub (Sep 24, 2025):

didnt have the correct arguments passed to the docker compose file. works now

<!-- gh-comment-id:3326526313 --> @srshkmr commented on GitHub (Sep 24, 2025): didnt have the correct arguments passed to the docker compose file. works now
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#54718
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?