Skip to content

Refactor pagedAttention transpose #33102

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.

Sign up for GitHub

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

Jump to bottom
Open
mangguo321 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Refactor pagedAttention transpose #33102

mangguo321 wants to merge 1 commit into from
+104 −145

Conversation

@mangguo321
Copy link
Contributor

@mangguo321 mangguo321 commented Dec 3, 2025

Details:

  • Move transpose functions from executor_pa.cpp to transpose.hpp to reuse in xattention and executor_pa.cpp. Modify transpose_16NxK logic to handle tails

Tickets:

@mangguo321 mangguo321 requested review from a team as code owners December 3, 2025 03:31
@github-actions github-actions bot added the category: CPU OpenVINO CPU plugin label Dec 3, 2025
zhangYiIntel
zhangYiIntel approved these changes Dec 5, 2025
View reviewed changes
Copy link
Contributor

@zhangYiIntel zhangYiIntel left a comment

Choose a reason for hiding this comment

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

LGTM

@mangguo321
Copy link
Contributor Author

mangguo321 commented Dec 9, 2025 •
edited
Loading

Test on EMR, no regression in performance and accuracy.
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@zhangYiIntel zhangYiIntel zhangYiIntel approved these changes

Assignees

No one assigned

Labels

category: CPU OpenVINO CPU plugin

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@mangguo321 @zhangYiIntel