Skip to content

Conversation

@yao-matrix
Copy link
Contributor

@yao-matrix yao-matrix commented May 16, 2025

for some fused test cases, since in autoawq, they are using flash_attn_func from flash_attn, XPU hasn't support flash attention yet, and since autoawq already archived, we don't have ways to upstream ipex kernel to autoawq.
So, i put these cases back to gpu with require_flash_attn decorator. Will re-enable it after we upstreamed flash-attn succesfully.

@ydshieh @IlyasMoutawwakil , pls help review, thx.

Signed-off-by: Matrix Yao <[email protected]>
Signed-off-by: Matrix Yao <[email protected]>
@github-actions github-actions bot marked this pull request as draft May 16, 2025 00:19
@github-actions
Copy link
Contributor

Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the Ready for review button (at the bottom of the PR page). This will assign reviewers and trigger CI.

@yao-matrix yao-matrix marked this pull request as ready for review May 16, 2025 00:22
@github-actions github-actions bot requested a review from ydshieh May 16, 2025 00:22
Copy link
Collaborator

@ydshieh ydshieh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, but would like @MekkCyber or @SunMarc have another approval

Thank you

Copy link
Contributor

@MekkCyber MekkCyber left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

works for me ! no concerns

@ydshieh ydshieh merged commit 7f28da2 into huggingface:main May 16, 2025
10 checks passed
Copy link
Member

@SunMarc SunMarc left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thx !

@yao-matrix yao-matrix deleted the quantization-xpu branch May 18, 2025 22:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants