vllm
vllm copied to clipboard
[Feat][whisper] add more sampling parameters to whisper endpoint
This PR adds the following sampling parameters to the whisper endpoint:
seed, frequency_penalty, repetition_penalty, presence_penalty
👋 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.
🚀
Added documentation and updated the example
Streaming PR landed, would you mind rebasing your work on current main?
any estimate when this might land?
I am currently not working on that. As the key feature for us would be beam search implementation. Which is currently in a heavy limbo state due to the migration to V1. Once V1 is a bit more set in stone, I will probably reconsider vllm with a "quick" beam search implementation. So feel free to rebase this again.
I will rebase this if that's ok with you @joennlae . This might actually be already useful for benchmarking parameters. Thanks for your contribution!
This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @joennlae.
https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork