[None][fix] Make disagg timeout cancellation rank-consistent#14746
Draft
Shixiaowei02 wants to merge 2 commits into
Draft
[None][fix] Make disagg timeout cancellation rank-consistent#14746Shixiaowei02 wants to merge 2 commits into
Shixiaowei02 wants to merge 2 commits into
Conversation
Describe it as a per-check, non-fatal back-off bound on waiting for a context KV send to complete, not a bound on total transfer time, and mark it advanced. Keep C++ and Python descriptions in sync. Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
The timeout was detected per rank by wall-clock and acted on directly, bypassing the per-rid consensus used by every other disagg transfer-state transition. Clock skew let ranks cancel a request in different iterations, diverging req.state and deadlocking a later collective. Detect the timeout locally, then union the timed-out request ids across ranks at the existing per-iteration lockstep hook and promote a single actionable flag together, so all ranks cancel the same set in the same iteration. The wall-clock check is now derived from the existing transfer start time, so no request field is added. Add a unit test for the union consensus. Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Collaborator
Author
|
/bot run --add-multi-gpu-test --disable-fail-fast |
Collaborator
|
PR_Github #51033 [ run ] triggered by Bot. Commit: |
Collaborator
|
PR_Github #51033 [ run ] completed with state |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
@coderabbitai summary
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.