feat: add mlu mooncake pd push support.#1246
Merged
phantomlei3 merged 3 commits intojd-opensource:mainfrom Apr 14, 2026
Merged
Conversation
Collaborator
phantomlei3
commented
Apr 10, 2026
phantomlei3
commented
- add backend-agnostic layer synchronizer wiring for layer-wise push overlap
- enable mooncake push on mlu with descriptor-based memory registration
- enforce mlu pd push flag validation and reject unsupported pull mode
phantomlei3
requested review from
DongheJin,
JimHsiung,
RobbieLeung,
XuZhang99,
liutongxuan,
walsonyang and
yq33victor
as code owners
![gemini-code-assist[bot]](https://avatars.gh.lumenfield.work/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces support for the MLU backend in the KV cache transfer mechanism, including necessary updates to the Mooncake transfer engine, synchronization logic, and model input parameters. The review comment regarding the spin-wait loop in the MLU layer synchronizer was addressed by suggesting the use of thread yielding to improve efficiency.
phantomlei3
force-pushed
the
feat/pd-support-mlu-push
branch
from
d196113 to
f33ce54
Compare
phantomlei3
commented
Apr 11, 2026
Collaborator
Author
phantomlei3
left a comment
phantomlei3
left a comment
There was a problem hiding this comment.
fixed for current reviews
phantomlei3
force-pushed
the
feat/pd-support-mlu-push
branch
from
f33ce54 to
fcab1ad
Compare
Clement-Wang26
approved these changes
Apr 14, 2026
JimHsiung
approved these changes
Apr 14, 2026
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.