Motivation

• Improve the timeout limit of backend runtime unittest from 15 min -> 18 min due to we added mixed chunked prefill before.
• mmlu accuracy: 0.71 -> 0.705.

Modification

Checklist

• Before submitting a PR for review, make sure it has passed verification in your local development environment at least.
• Ensure pre-commit pre-commit run --all-files or other linting tools are used to fix potential lint issues.
• Confirm that modifications are covered by complete unit tests. If not, please add more unit tests for correctness.
• Modify documentation as needed, such as docstrings or example tutorials.