Skip to content

[Pipeline RL] GRPO sample, streaming dataset improvements #458

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
Open
jlamypoirier wants to merge 4 commits into
base: jlp_pipeline_rl
Choose a base branch
from
Open

[Pipeline RL] GRPO sample, streaming dataset improvements #458

jlamypoirier wants to merge 4 commits into from

Conversation

@jlamypoirier
Copy link
Collaborator

@jlamypoirier jlamypoirier commented Jan 23, 2026 •
edited
Loading

✨ Description

  • Add GRPO support to language model data (advantages and old log probs)
  • Optimize sending tensor-valued data through redis (send as plain byte buffers)
  • Add model testing config for GRPO.

@jlamypoirier jlamypoirier changed the title GRPO sample GRPO sample, streaming dataset improvements Jan 23, 2026
@jlamypoirier jlamypoirier changed the title GRPO sample, streaming dataset improvements [Pipeline RL] GRPO sample, streaming dataset improvements Jan 27, 2026
@jlamypoirier jlamypoirier marked this pull request as ready for review January 27, 2026 20:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@bigximik bigximik Awaiting requested review from bigximik

@rafapi rafapi Awaiting requested review from rafapi

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@jlamypoirier