[Feat] Implement kv cache broadcast in MLA #367
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
harrisonyhq
requested review from
hek14,
mag1c-h,
qyh111 and
ygwpz
as code owners
harrisonyhq
requested review from
flesher0813
and removed request for
hek14 and
mag1c-h
harrisonyhq
force-pushed
the
dev-ucm-v1
branch
from
56497f1 to
dc9aada
Compare
harrisonyhq
changed the title
ygwpz
reviewed
Nov 18, 2025
harrisonyhq
force-pushed
the
dev-ucm-v1
branch
from
dc9aada to
16cae41
Compare
harrisonyhq
changed the title
ygwpz
approved these changes
Nov 19, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Purpose
Implement kv cache broadcast in MLA scenario, support only load on rank 0 and broadcast to other gpus in tp group.
Modifications
Skip load and wait in tp > 0.
Test