fix: Include garbage collect for non streaming and improve triggering logic

[kthui]

What does the PR do?

Fix:

• Garbage collect when the request count drops to zero.
• Include garbage collect for non-streaming case.
• Fix improper placement of decrement_ongoing_request_count = True.
• Fix missing lora_request argument into llm_engine.add_request().

for #46 PR.

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:

#46

Where should the reviewer start?

N/A

Test plan:

This PR is to fix some issues on the performance improvement #46 PR, so any issues should be covered by existing tests.

• CI Pipeline ID: 16926866

N/A

Caveats:

N/A

Background

N/A

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

N/A