Support custom rollout-proxy TIS hooks in bypass mode#1912
Open
sjtushenhai wants to merge 1 commit into
Open
Conversation
b4efd31 to
32ca4f9
Compare
Allow use_rollout_logprobs and use_tis to be combined through a custom TIS hook, while keeping the builtin decoupled TIS semantics unchanged. Expose current_log_probs and advantages to custom TIS hooks so rollout-proxy corrections can rebuild PPO/GRPO pg_loss directly without double-applying the same ratio. Add a reference helper in examples/train_infer_mismatch_helper, update the customization docs, and fix the train-vs-rollout mismatch metric so it still reflects training-engine logprobs in bypass mode.
01608aa to
79efcf9
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR keeps the builtin TIS behavior unchanged, but makes
use_rollout_logprobs + use_tisavailable through a custom hook.Changes:
custom_tis_function_pathwhenuse_rollout_logprobsanduse_tisare enabled togethercurrent_log_probsandadvantagesto custom TIS hooksexamples.train_infer_mismatch_helper.mis.compute_rollout_proxy_pg_loss_with_cpMotivation
The builtin TIS path assumes train-vs-rollout decoupled correction semantics.
In bypass mode, the main PPO/GRPO ratio is already computed against rollout logprobs. Reusing the builtin post-hoc TIS weighting in that setting can unintentionally apply the same rollout ratio twice.
This change does not alter the default path. It only opens an explicit extension point for users who want rollout-proxy correction behavior in asynchronous or stale-rollout settings.
Notes