Add num_generators field to RLTrainer.Config#3624
Open
pzhan9 wants to merge 1 commit into
Open
Conversation
meta-cla
Bot
added
the
CLA Signed
tianyu-l
approved these changes
Jun 10, 2026
| ], | ||
| "RL GRPO 2 generators TP=1 no compile", | ||
| "rl_grpo_2gen_tp1_no_compile", | ||
| ngpu=4, |
Contributor
There was a problem hiding this comment.
We should make this 8 GPU, and use trainer 4, 2 generator each TP2. Seems fine to land this first, with TODO
Contributor
There was a problem hiding this comment.
i would do 3 generator TP2. Rollout is the bottleneck
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
GeneratorRouterwas added in #3583, but we currently do not have a way to spawn multiple generators. Subsequently router cannot be tested in CI with an integration test.In order to unblock, this PR adds a
num_generatorsfield toRLTrainer.Config. This field can only be used in the single-host mode.This field is meant to be temporary just to unblock the integration test (suggested by this comment). For the long run, we need to have a "placement" config, which contains the information regarding how to map gpus/hosts to different RL roles, such as trainer and generators. The
num_generatorsshould be there too. Hopefully we can get that done in the next few weeks.