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

fix bugs in llama flash attention #681

Merged

research4pan merged 2 commits into OptimalScale:main from yaoguany:main

Nov 27, 2023

Collaborator

yaoguany commented Nov 27, 2023

fix bugs in llama2-70b multi-query attention

yaoguany added 2 commits

November 26, 2023 16:30


          fix bugs in llama flash attention

ae0cd54


          Update llama_flash_attention.py

9280a0b

research4pan approved these changes

View reviewed changes

Contributor

research4pan left a comment

LGTM, thanks! (This should support llama models with multi-query attention, such as Llama-2-70b, whose num_heads != num_key_value_heads)

research4pan merged commit 4124102 into OptimalScale:main

1 check failed

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

Labels

None yet