perf: Release GIL during cancellation check #372
Merged
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Outdated suggestions cannot be applied.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.
What does the PR do?
Release the GIL while checking for cancellation. Another Python thread can be performing useful work while the cancellation status is being checked.
Checklist
<commit_type>: <Title>
Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
triton-inference-server/vllm_backend#54
Where should the reviewer start?
Can start by verifying the cancellation function, where the GIL is released during its execution, does not access any Python objects.
Test plan:
This is a performance improvement, so any issue should be covered by existing test cases.
Caveats:
N/A
Background
Need to improve the performance on vLLM backend.
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
N/A