[ROCm] Fix intranode queue ordering for shared buffers#18
Open
AndreasKaratzas wants to merge 1 commit into
Open
[ROCm] Fix intranode queue ordering for shared buffers#18AndreasKaratzas wants to merge 1 commit into
AndreasKaratzas wants to merge 1 commit into
Conversation
Signed-off-by: Andreas Karatzas <[email protected]>
AndreasKaratzas
marked this pull request as ready for review
July 24, 2026 00:13
charlifu
approved these changes
Jul 24, 2026
Collaborator
|
Do you have test suite results after this change? |
Contributor
Author
|
@kudomcho For vLLM you mean? |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The Distributed Tests / DBO test group on ROCm vLLM CI fails in build 11147 when successive DBO microbatches share one ROCm DeepEP buffer. The intranode path can publish queue progress without a complete producer/consumer ownership chain, while whole-workgroup barriers can pair unrelated per-rank rounds. This change uses per-rank wave barriers and release/acquire ordering for dispatch and combine tail publication, queue-slot reuse, receiver progress, retirement, and shared tail fan-out. It also adds a two-rank regression test that drives asymmetric and randomized microbatches through repeated queue wraparound on the same buffer.