github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12622] Ollama fails to detect GPU after upgrading to 0.12.5 (WSL) #8378

New Issue
Closed
opened 2026-04-12 21:01:24 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 21:01:24 -05:00
Owner
Copy Link

Originally created by @Railway9784 on GitHub (Oct 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12622

What is the issue?

After upgrading Ollama to 0.12.5 Ollama serve won't detect GPU and runs CPU only.
Downgrading to 0.12.3 fixes the issue.

In both versions OLLAMA_LLM_LIBRARY is unset.

Relevant log output

OS

WSL2

GPU

Nvidia

CPU

AMD

Ollama version

0.12.5

Originally created by @Railway9784 on GitHub (Oct 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12622 ### What is the issue? After upgrading Ollama to 0.12.5 Ollama serve won't detect GPU and runs CPU only. Downgrading to 0.12.3 fixes the issue. - Here's 0.12.5 log with `OLLAMA_DEBUG=2` - [ollama.v0.12.5.log](https://github.com/user-attachments/files/22873999/ollama.v0.12.5.log) - And here's 0.12.3 log with `OLLAMA_DEBUG=2` - [ollama.v0.12.3.log](https://github.com/user-attachments/files/22873998/ollama.v0.12.3.log) showing GPU properly detected. In both versions `OLLAMA_LLM_LIBRARY` is unset. ### Relevant log output ```shell ``` ### OS WSL2 ### GPU Nvidia ### CPU AMD ### Ollama version 0.12.5
GiteaMirror added the bug label 2026-04-12 21:01:24 -05:00
GiteaMirror commented 2026-04-12 21:01:26 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 15, 2025):

//ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:329: GGML_ASSERT(ggml_cuda_has_arch(info.devices[id].cc) && "ggml was not compiled with support for this arch") failed

Try limiting the GPU probe to just v12 by setting OLLAMA_LLM_LIBRARY=cuda_v12.

<!-- gh-comment-id:3405895108 --> @rick-github commented on GitHub (Oct 15, 2025): ``` //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:329: GGML_ASSERT(ggml_cuda_has_arch(info.devices[id].cc) && "ggml was not compiled with support for this arch") failed ``` Try limiting the GPU probe to just v12 by setting `OLLAMA_LLM_LIBRARY=cuda_v12`.
GiteaMirror commented 2026-04-12 21:01:27 -05:00
Author
Owner
Copy Link

@Railway9784 commented on GitHub (Oct 15, 2025):

Set OLLAMA_LLM_LIBRARY=cuda_v12 and still no GPU detection - here is the log - 0.12.5-cuda12.log

<!-- gh-comment-id:3408344459 --> @Railway9784 commented on GitHub (Oct 15, 2025): Set `OLLAMA_LLM_LIBRARY=cuda_v12` and still no GPU detection - here is the log - [0.12.5-cuda12.log](https://github.com/user-attachments/files/22936531/0.12.5-cuda12.log)
GiteaMirror commented 2026-04-12 21:01:28 -05:00
Author
Owner
Copy Link

@Railway9784 commented on GitHub (Oct 17, 2025):

After updating to 0.12.6 GPU is properly detected. Thank you!

<!-- gh-comment-id:3413731375 --> @Railway9784 commented on GitHub (Oct 17, 2025): After updating to 0.12.6 GPU is properly detected. Thank you!
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#8378
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?