vLLM model handler efficiency improvements#32687
Merged
Conversation
Contributor
|
Assigning reviewers. If you would like to opt out of this review, comment R: @tvalentyn for label python. Available commands:
The PR bot will only process comments in the main thread (not review comments). |
tvalentyn
approved these changes
Oct 15, 2024
3 tasks
reeba212
pushed a commit
to reeba212/beam
that referenced
this pull request
Dec 4, 2024
* vLLM model handler efficiency improvements * fmt * Remove bad exceptions * lint * lint
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Because of how vLLM does batching, it is much more efficient if you're able to push as many requests to it as possible so that it can make the appropriate batching decision. Right now, per worker thread we send requests serially; this fixes that inefficiency by sending all data asynchronously to the vLLM server and then awaiting the response.
Fixes #32528
Thank you for your contribution! Follow this checklist to help us incorporate your contribution quickly and easily:
addresses #123), if applicable. This will automatically add a link to the pull request in the issue. If you would like the issue to automatically close on merging the pull request, commentfixes #<ISSUE NUMBER>instead.CHANGES.mdwith noteworthy changes.See the Contributor Guide for more tips on how to make review process smoother.
To check the build health, please visit https://github.com/apache/beam/blob/master/.test-infra/BUILD_STATUS.md
GitHub Actions Tests Status (on master branch)
See CI.md for more information about GitHub Actions CI or the workflows README to see a list of phrases to trigger workflows.