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

Update model implementations to use flash attention #2046

Open
divyashreepathihalli opened this issue Jan 16, 2025 · 0 comments
Open

Update model implementations to use flash attention #2046

divyashreepathihalli opened this issue Jan 16, 2025 · 0 comments
Labels
team-created Issues created by Keras Hub team as part of development roadmap.

Comments

@divyashreepathihalli
Copy link
Collaborator

Flash attention support has been added to Keras 3.
https://github.com/keras-team/keras/blob/25d6d80a6ecd31f0da52c325cd16dbe4a29b7329/keras/src/layers/attention/multi_head_attention.py#L55

However, some of the models implemented in KerasHub is overriding def _compute_attention() function which has the flash attention enabling mechanism. The implementations need to be updated
@divyashreepathihalli divyashreepathihalli added the team-created Issues created by Keras Hub team as part of development roadmap. label Jan 16, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
team-created Issues created by Keras Hub team as part of development roadmap.
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@divyashreepathihalli