Skip to content
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

[Performance] Improve register spill size for flash attention kernel when D_HEAD >=128 #3084

Open
chengjunlu opened this issue Jan 3, 2025 · 0 comments
Open

[Performance] Improve register spill size for flash attention kernel when D_HEAD >=128 #3084

chengjunlu opened this issue Jan 3, 2025 · 0 comments
Assignees
@chengjunlu
Labels
enhancement New feature or request performance
Milestone
4.0 [Performance]...

Comments

@chengjunlu
Copy link
Contributor

Describe the issue

There is register spilling when D_HEAD >=128.

Improve the register spilling issue.

Environment details

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

@chengjunlu chengjunlu

Labels
enhancement New feature or request performance
Projects
None yet
Milestone
4.0 [Performance] Core
Development

No branches or pull requests
2 participants
@chengjunlu @vlad-penkin