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

Add llama3 405b attention shapes. #29

Merged

saienduri merged 1 commit into main from llama3_405b

Oct 28, 2024

Contributor

saienduri commented Oct 24, 2024 •

edited

Loading

This PR adds the llama3 405b attention shapes that we see in the sharktank export (https://gist.github.com/KyleHerndon/a9c60ce93264d6ba7ec9e878c879f218). We make sure the dynamic sequence length is always a multiple of 16


          add llama problems

ba29da3

saienduri requested a review from Groverkss

October 24, 2024 22:22

saienduri merged commit 982eb72 into main

1 check passed

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

Labels

None yet