refactor: Remove explicit callings to garbage collect

[kthui]

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

• PR title reflects the change and is of format <commit_type>: <Title>
• Changes are described in the pull request.
• Related issues are referenced.
• Populated github labels field
• Added test plan and verified test passes.
• Verified that the PR passes existing CI.
• Verified copyright is correct on all changed files.
• Added succinct git squash message before merging ref.
• All template sections are filled out.
• Optional: Additional screenshots for behavior/output changes with before/after.

Commit Type:

Check the conventional commit type
box here and add the label to the github PR.

• build
• ci
• docs
• feat
• fix
• perf
• refactor
• revert
• style
• test

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.

• CI Pipeline ID: 17156719

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

[nnshah1]

left some suggestions for logging

[oandreeva-nv]

LGTM!

[kthui]

Merging the refactor changes first, so the cancellation on response thread can be rebased on top. The test enhancement can be merged separately.