Skip to content

Navigation Menu

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

huggingface / trl Public

generated from fastai/nbdev_template

Notifications You must be signed in to change notification settings
Fork 1.6k
Star 11.9k

Code
Issues 239
Pull requests 65
Discussions
Actions
Projects
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Security
Insights

🐦‍🔥 6x faster GRPO with multi-step optimization#2899

Merged

qgallouedec merged 16 commits intomainhuggingface/trl:mainfrom multi-step-grpihuggingface/trl:multi-step-grpiCopy head branch name to clipboard

Feb 20, 2025

+316-39

Conversation Commits16 (16)Checks Files changed

Commits

Commits on Feb 19, 2025

Add num_updates and epsilon parameters to GRPOConfig and GRPOTrainer
qgallouedec
committed
test sampler
qgallouedec
committed
update the loss computation
qgallouedec
committed
fix eval sampler
qgallouedec
committed
should work now
qgallouedec
committed

Commits on Feb 20, 2025

buffer inputs with grad accum
qgallouedec
committed
Merge branch 'main' into multi-step-grpi
qgallouedec
authored
optimize when num_iterations == 1
qgallouedec
committed
Merge branch 'multi-step-grpi' of https://github.com/huggingface/trl into multi-step-grpi
qgallouedec
committed
test
qgallouedec
committed
minor comment removal and fix log metric
qgallouedec
committed
beta position
qgallouedec
committed
clarify comment [ci skip]
qgallouedec
committed
clarify sampler doc [ci skip]
qgallouedec
committed
fix collision with eval logging
qgallouedec
committed
clarify
qgallouedec
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.