Skip to content

Fix Gemma3 and Gemma2 flops computation. #2009

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

Merged
merged 1 commit into from
Jul 23, 2025
Merged

Conversation

gagika
Copy link
Collaborator

@gagika gagika commented Jul 22, 2025

Description

  • Add correct local attention flops for Gemma3
  • Change both gemma2 and gemma3 to use causal attention flops (total attention flops / 2).

Checklist

Before submitting this PR, please make sure (put X in square brackets):

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have run end-to-end tests tests and provided workload links above if applicable.
  • I have made or will make corresponding changes to the doc if needed.

Copy link
Collaborator

@gobbleturk gobbleturk left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks gagik!

@copybara-service copybara-service bot merged commit 6da8ede into main Jul 23, 2025
20 checks passed
@copybara-service copybara-service bot deleted the gemma3-flops branch July 23, 2025 19:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants