[1/3]refactor mesh worker registry into layered pools#1448
Draft
Yuechguo wants to merge 1 commit into
Draft
Conversation
Rework the worker registry from a flat model index into a layered model -> framework -> role pool structure. This keeps lock-free snapshot reads while allowing direct lookup of regular, PD prefill, and PD decode workers per framework. Introduce Framework and PoolRole as first-class worker metadata, replacing the older RuntimeType naming. Worker creation now derives framework from discovered or configured runtime metadata, with HTTP workers defaulting to Anonymous and gRPC workers defaulting to Sglang when unspecified. Update worker builders, update flows, config mapping, and placement test support to preserve framework metadata through worker lifecycle operations. Add registry tests covering direct bucket access, anonymous defaults, and pool cleanup after worker removal.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Rework the worker registry from a flat model index into a layered model -> framework -> role pool structure. This keeps lock-free snapshot reads while allowing direct lookup of regular, PD prefill, and PD decode workers per framework.
Introduce Framework and PoolRole as first-class worker metadata, replacing the older RuntimeType naming. Worker creation now derives framework from discovered or configured runtime metadata, with HTTP workers defaulting to Anonymous and gRPC workers defaulting to Sglang when unspecified. Update worker builders, update flows, config mapping, and placement test support to preserve framework metadata through worker lifecycle operations. Add registry tests covering direct bucket access, anonymous defaults, and pool cleanup after worker removal.
Test Plan
for atomesh mocker test
