vllm-project
Make stream include usage as optional
Pull Request Description
Make stream include usage as optional parameter. If request is for a user (user has default tpm limit, if not configured) then stream's include usage is mandatory.
Heterogeneous GPU use case is not supported with stream option right now. Once the support is added, include_usage need to be enabled as well.
Related Issues
Resolves: #[Insert issue number(s)]
Important: Before submitting, please complete the description above and review the checklist below.
Contribution Guidelines (Expand for Details)
We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:
Pull Request Title Format
Your PR title should start with one of these prefixes to indicate the nature of the change:
[Bug]: Corrections to existing functionality[CI]: Changes to build process or CI pipeline[Docs]: Updates or additions to documentation[API]: Modifications to aibrix's API or interface[CLI]: Changes or additions to the Command Line Interface[Misc]: For changes not covered above (use sparingly)
Note: For changes spanning multiple categories, use multiple prefixes in order of importance.
Submission Checklist
- [ ] PR title includes appropriate prefix(es)
- [ ] Changes are clearly explained in the PR description
- [ ] New and existing tests pass successfully
- [ ] Code adheres to project style and best practices
- [ ] Documentation updated to reflect changes (if applicable)
- [ ] Thorough testing completed, no regressions introduced
By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.
After that, any feature relies on statistics won't work out of box and they have to append the stream options right? If that case, Let's update the docs as well. just an attention under feature page would be great, as well as the streaming option configuration. If you do not want to include those changes in this PR, let's create a new issue to track it
@varungup90 the change looks good to me, feel free to merge it if there's no further change
After that, any feature relies on statistics won't work out of box and they have to append the stream options right? If that case, Let's update the docs as well. just an attention under feature page would be great, as well as the streaming option configuration. If you do not want to include those changes in this PR, let's create a new issue to track it
I will create a new issue to add new feature flag to enable heterogenous features and also add support for streaming. Update documentation.