Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

flash-attn2: [XPU] Refactor Code & Add PagedKV #66

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

Merged
danieldk merged 13 commits into main from fa2-xpu-refactor-pagedkv
Nov 6, 2025

Conversation

@danieldk
Copy link
Member

@danieldk danieldk commented Nov 6, 2025

This PR:

  1. Refactored the code to improve performance.
  2. Added support for PagedKV functionality.
  3. Test results in transformers' UTs are consistent with CUDA.

I have successfully built this PR locally using nix.

Original PR: #65

Copy link
Collaborator

@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.

Niiice !

Copy link
Member Author

danieldk commented Nov 6, 2025

The macOS error is unrelated. Let's fix that separately to avoid the expensive flash-attn2 build times.

MekkCyber reacted with thumbs up emoji

Copy link
Collaborator

Yes perfect!

@danieldk danieldk merged commit b760047 into main Nov 6, 2025
2 of 3 checks passed
@danieldk danieldk deleted the fa2-xpu-refactor-pagedkv branch November 6, 2025 13:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@MekkCyber MekkCyber MekkCyber approved these changes

@drbh drbh Awaiting requested review from drbh drbh is a code owner

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

AltStyle によって変換されたページ (->オリジナル) /