github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7035] Support AMD GPUs via WSL #66518

New Issue
Closed
opened 2026-05-04 07:15:49 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 07:15:49 -05:00
Owner
Copy Link

Originally created by @vignessh on GitHub (Sep 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7035

Hello,

I'm running a Windows 11 workstation based on an AMD RX 7900XTX GPU. I installed the latest Ollama for Windows and with that I can see the GPU getting used for any queries. I also tried the Linux install for WSL following this guide. With WSL however, even after installing ROCm as mentioned in the guide, I can see Ollama not making use of the GPU. I tried following this issue to build Olama locally with the fix mentioned, but no success there either. The ollama server keeps crashing when I attempt to run any model like llama2 or llama3.2.

Please can someone help with this. I really don't want to switch to a Nvidia just for this purpose.

Thanks,
Vignessh

Originally created by @vignessh on GitHub (Sep 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7035 Hello, I'm running a Windows 11 workstation based on an AMD RX 7900XTX GPU. I installed the latest Ollama for Windows and with that I can see the GPU getting used for any queries. I also tried the Linux install for WSL following [this](https://community.amd.com/t5/ai/running-llms-locally-on-amd-gpus-with-ollama/ba-p/713266) guide. With WSL however, even after installing ROCm as mentioned in the guide, I can see Ollama not making use of the GPU. I tried following [this](https://github.com/ollama/ollama/issues/5275) issue to build Olama locally with the fix mentioned, but no success there either. The ollama server keeps crashing when I attempt to run any model like `llama2` or `llama3.2`. Please can someone help with this. I really don't want to switch to a Nvidia just for this purpose. Thanks, Vignessh
GiteaMirror added the amdwslwindowsfeature request labels 2026-05-04 07:15:51 -05:00
GiteaMirror commented 2026-05-04 07:15:56 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 30, 2024):

We're tracking this with #5275

<!-- gh-comment-id:2383714881 --> @dhiltgen commented on GitHub (Sep 30, 2024): We're tracking this with #5275
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 amd feature request windows wsl
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#66518
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?