Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

@wizeng23
Copy link
Contributor

@wizeng23 wizeng23 commented Apr 11, 2025

Description

It claims to make GRPO 6x faster: github. Tested all e2e tests

Related issues

Fixes OPE-1157

Before submitting

  • This PR only changes documentation. (You can ignore the following checks in that case)
  • Did you read the contributor guideline Pull Request guidelines?
  • Did you link the issue(s) related to this PR in the section above?
  • Did you add / update tests where needed?

@wizeng23 wizeng23 marked this pull request as draft April 11, 2025 01:22
@wizeng23 wizeng23 requested a review from oelachqar April 11, 2025 06:12
@wizeng23 wizeng23 changed the title [WIP] Update trl to 0.16 Update trl to 0.16 Apr 11, 2025
@wizeng23 wizeng23 requested a review from taenin April 11, 2025 06:12
@wizeng23 wizeng23 marked this pull request as ready for review April 11, 2025 06:12
@wizeng23 wizeng23 merged commit d009c2d into main Apr 11, 2025
2 checks passed
@wizeng23 wizeng23 deleted the wizeng/o1157-trl branch April 11, 2025 20:25
penfever pushed a commit that referenced this pull request Aug 27, 2025
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