-
Notifications
You must be signed in to change notification settings - Fork 16
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
refactor: Remove explicit callings to garbage collect #55
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
left some suggestions for logging
Co-authored-by: Neelay Shah <neelays@nvidia.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
Merging the refactor changes first, so the cancellation on response thread can be rebased on top. The test enhancement can be merged separately. |
What does the PR do?
Remove the explicit calling to garbage collector. The lifecycle of response_sender and response_factory are expected to be handled by the Python backend internally.
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/server#7504
triton-inference-server/python_backend#373
Where should the reviewer start?
N/A
Test plan:
The PR refactors how the response_sender object lifecycle is handled, it is neither a feature nor a bug fix, so existing tests should be sufficient to cover any regression.
Caveats:
When parallel tensors > 1, the stub process can fail to unload (with finalize() called and returned successfully), so it is necessary to manually call garbage collect once at the end of finalize().
Background
N/A
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
N/A