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.

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

Enable flash attention by default #690

Merged
merged 3 commits into from
Dec 13, 2024

Conversation

rsuderman
Copy link
Contributor

No description provided.

@rsuderman rsuderman changed the title Enable flash attention by default and make block size 32 Enable flash attention by default Dec 12, 2024
@aviator19941
Copy link
Collaborator

aviator19941 commented Dec 13, 2024

@rsuderman Can you also add the block_seq_stride flag defaulted to 32 for export_paged_llm_v1.py like in https://github.com/rsuderman/sharktank/tree/configure_blocking?

EDIT: nvm seems like Archana made the change here: #692

@rsuderman rsuderman merged commit 77ca02f into nod-ai:main Dec 13, 2024
8 checks passed
IanNod pushed a commit to IanNod/SHARK-Platform that referenced this pull request Dec 17, 2024
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.

2 participants