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 #12815] AMD MI50 cann't load qwen3-vl into GPU VRM on docker ollama/ollama:0.12.7-rc0-rocm #70551

New Issue
Open
opened 2026-05-04 21:56:53 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-05-04 21:56:53 -05:00
Owner
Copy Link

Originally created by @tinyadam on GitHub (Oct 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12815

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

MI50 Only load successfully on CPU mode this version，please fix this

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @tinyadam on GitHub (Oct 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12815 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? MI50 Only load successfully on CPU mode this version，please fix this ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the amdbugdocker labels 2026-05-04 21:56:54 -05:00
GiteaMirror commented 2026-05-04 21:56:58 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 29, 2025):

As of 0.12.5 MI50 is not supported by ROCm. The soon-to-be-released Vulkan support will work with this GPU. If you would like to try it out, clone the repo and build the project. Otherwise stick with 0.12.4 and wait for the Vulkan support.

<!-- gh-comment-id:3460588479 --> @rick-github commented on GitHub (Oct 29, 2025): As of [0.12.5](https://github.com/ollama/ollama/releases/tag/v0.12.5) MI50 is not supported by ROCm. The soon-to-be-released Vulkan support will work with this GPU. If you would like to try it out, clone the repo and build the project. Otherwise stick with 0.12.4 and wait for the Vulkan support.
GiteaMirror commented 2026-05-04 21:56:59 -05:00
Author
Owner
Copy Link

@tinyadam commented on GitHub (Oct 29, 2025):

As of 0.12.5 MI50 is not supported by ROCm. The soon-to-be-released Vulkan support will work with this GPU. If you would like to try it out, clone the repo and build the project. Otherwise stick with 0.12.4 and wait for the Vulkan support.

how to know Vulkan already supported on future？

<!-- gh-comment-id:3461987938 --> @tinyadam commented on GitHub (Oct 29, 2025): > As of [0.12.5](https://github.com/ollama/ollama/releases/tag/v0.12.5) MI50 is not supported by ROCm. The soon-to-be-released Vulkan support will work with this GPU. If you would like to try it out, clone the repo and build the project. Otherwise stick with 0.12.4 and wait for the Vulkan support. how to know Vulkan already supported on future？
GiteaMirror commented 2026-05-04 21:57:01 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 29, 2025):

It will be in the release notes.

<!-- gh-comment-id:3461999294 --> @rick-github commented on GitHub (Oct 29, 2025): It will be in the release notes.
GiteaMirror commented 2026-05-04 21:57:02 -05:00
Author
Owner
Copy Link

@tinyadam commented on GitHub (Oct 29, 2025):

very well，best to make some docker image in docker hub

<!-- gh-comment-id:3462435655 --> @tinyadam commented on GitHub (Oct 29, 2025): very well，best to make some docker image in docker hub
GiteaMirror commented 2026-05-04 21:57:03 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 29, 2025):

If you are using docker, it is very simple to build an image that you can use:

$ git clone https://github.com/ollama/ollama.git
$ docker build -f ollama/Dockerfile -t ollama/ollama:vulkan ollama
<!-- gh-comment-id:3462480545 --> @rick-github commented on GitHub (Oct 29, 2025): If you are using docker, it is very simple to build an image that you can use: ```console $ git clone https://github.com/ollama/ollama.git $ docker build -f ollama/Dockerfile -t ollama/ollama:vulkan ollama ```
GiteaMirror commented 2026-05-04 21:57:04 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 14, 2025):

In 0.12.11 Vulkan is now included in the official binaries, but still experimental. To enable, set OLLAMA_VULKAN=1 for the server. https://github.com/ollama/ollama/blob/main/docs/docker.mdx#vulkan-support

<!-- gh-comment-id:3530361226 --> @dhiltgen commented on GitHub (Nov 14, 2025): In 0.12.11 Vulkan is now included in the official binaries, but still experimental. To enable, set OLLAMA_VULKAN=1 for the server. https://github.com/ollama/ollama/blob/main/docs/docker.mdx#vulkan-support
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 bug docker
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#70551
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?