perf: vLLM metrics optimization

[yinggeh]

What does the PR do?

Optimize vLLM by reporting metrics in a separate thread.

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.

• perf

Related PRs:

triton-inference-server/python_backend#379

Where should the reviewer start?

n/a

Test plan:

L0_backend_vllm/metrics_test

• CI Pipeline ID:
  18506139

Caveats:

n/a

Background

n/a

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

n/a

[kthui]

LGTM! Thanks for optimizing the metrics reporting performance!