Repository navigation
Check Motor PD roles and rank health before routing - #36
Draft
huangxinV587 wants to merge 4 commits into
Draft
huangxinV587 wants to merge 4 commits into
huangxinV587 wants to merge 4 commits into
Conversation
huangxinV587
changed the title
huangxinV587
changed the title
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motor exposes readiness on a separate management port and can report healthy instances even when a registered rank is unreachable. For a strict P/D deployment, the gateway checks management readiness and requires healthy, active, available prefill and decode instances for the configured model. An additional endpoint-probe option checks every rank in a candidate instance; other backend health behavior is unchanged.
Validation:
python -m unittest discover -s tests -v(232 tests, 8 skipped); isolated Coordinator tests covered a P-only registry and a registered unreachable decode, both of which Motor still reported ready. With endpoint probing enabled, the candidate gateway routed a synthetic streaming session to the other Coordinator. This does not prove full physical failure recovery or continuation of an already-started stream.