Keep routing replay target prep out of Dynamo#723
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Why
Routing replay target preparation mutates Python replay cursors and Megatron RouterReplay state. When this runs inside a compiled router frame, Dynamo guards on changing replay state and recompiles across router/lifecycle calls.
Validation
Additional local investigation: the shared 3-step Qwen3.5 Megatron smoke that reproduced the SIGSEGV on PR720+721 passed with this boundary applied, and the routing-replay Dynamo signatures disappeared.