Make sure that all workers are notified about end of execution loop #730
Conversation
This file contains 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
kdamaszk
requested review from
kzawora-intel,
madamczykhabana,
michalkuligowski,
mgawarkiewicz,
vivekgoe and
afierka-intel
as code owners
kzawora-intel
approved these changes
Jan 23, 2025
|
@michalkuligowski @madamczykhabana please review |
michalkuligowski
approved these changes
Jan 24, 2025
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Outdated suggestions cannot be applied.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.
Currently we will have a hang at the end of script when using TP>1 and multistep scheduling. This is caused by lack of notification from driver worker about ending the execution loop.
This is a workaround for this issue, by making sure that all workers are notified at the end of
llm_engineloop.Other possible workaround could be modification of this check: https://github.com/HabanaAI/vllm-fork/blob/habana_main/vllm/engine/llm_engine.py#L1379 with
or not self.has_unfinished_requests().