Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Return the usage info in stream response.

Modification

1. add usage: Optional[UsageInfo] in ChatCompletionStreamResponse
2. return usage in completion_stream_generator while res.finish_reason is not None

BC-breaking (Optional)

No.

Use cases (Optional)

No.

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.