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

Add llama3 405b attention shapes. #29

Merged
merged 1 commit into from
Oct 28, 2024
Merged

Add llama3 405b attention shapes. #29

merged 1 commit into from
Oct 28, 2024

Conversation

saienduri
Copy link
Contributor

@saienduri saienduri commented Oct 24, 2024

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

@saienduri saienduri requested a review from Groverkss October 24, 2024 22:22
@saienduri saienduri merged commit 982eb72 into main Oct 28, 2024
1 check passed
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.

1 participant