[Core] Allow vLLM to stream n tokens at a time

[rohingarg-c]

This PR allows vLLM to stream n tokens at a time, improving potential network bandwidth issues. It stores this stream_n param as a field in a new StreamingParams class, created to store other parameters related to how the model streams tokens back.

[github-actions[bot]]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @rohingarg-c.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[hypnopump]

Like this feature

[rohingarg-c]

I updated the PR to reflect some of the comments. In particular

• removed the feature from the v0 engine
• added an additional test to ensure that the parameter is working correctly
• removed the extra buffer and instead modified the RequestOutputCollector to handle the stream_n logic

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @rohingarg-c.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[rohingarg-c]

I’ve fixed all the build errors, and everything should now be ready to merge. Would appreciate a review!

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @rohingarg-c.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[mergify[bot]]

This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @rohingarg-c.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[hmellor]

Closing as duplicate