feat: add AsyncRolloutManager for native async per-prompt rollouts#2566
Draft
yuki-97 wants to merge 8 commits into
Draft
feat: add AsyncRolloutManager for native async per-prompt rollouts#2566yuki-97 wants to merge 8 commits into
yuki-97 wants to merge 8 commits into
Conversation
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
… support for now Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
…nc and cleanup unused Signed-off-by: Yuki Huang <yukih@nvidia.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue
Part of RL-729. Based on #2528.
Summary
Adds
AsyncRolloutManagertorollout_manager.pyto support native async per-prompt multi-turn rollouts.run_rolloutfans outnum_generations_per_promptconcurrent_run_single_rolloutcoroutines viaasyncio.gatherand returns aPromptGroupRecord._run_single_rolloutis a pure mirror ofrun_sample_multi_turn_rollout(multi-reward support dropped for now)._generate_responsemirrorsasync_generate_response_for_sample_turn+generate_responses_async, with simplified logic (single-sample path, no batching indirection).Tests
tests/unit/experience/test_rollouts.pywith unit tests forAsyncRolloutManager.