-
-
Notifications
You must be signed in to change notification settings - Fork 11.8k
[ROCM][CI] Fix AMD Examples Test Group #30276
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
3784787 to
241d964
Compare
|
Documentation preview: https://vllm--30276.org.readthedocs.build/en/30276/ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This pull request fixes a CI issue for AMD examples by setting the attention backend to FLEX_ATTENTION on ROCm platforms. While the use of os.environ is a valid approach, I've suggested a safer and more explicit alternative that modifies the parsed arguments locally. This avoids modifying global state and improves the code's clarity and robustness.
|
Hi @Concurrensee, the pre-commit checks have failed. Please run: uv pip install pre-commit
pre-commit install
pre-commit run --all-filesThen, commit the changes and push to your branch. For future commits, Tip Is
|
abb1d8a to
40790e0
Compare
Signed-off-by: Yida Wu <yida.wu@amd.com>
40790e0 to
48907c7
Compare
| open-clip-torch==2.32.0 | ||
|
|
||
| # Required for Examples test | ||
| vllm[audio]==0.11.0 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is this safe? will it override the vllm version?
I suggest following test.txt by specifying the packages directly, avoid using vllm[audio]==0.11.0
This PR fixes AMD Examples Test Group