vllm
vllm copied to clipboard
Deepseek MTP for V1
👋 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.
🚀
This pull request has merge conflicts that must be resolved before it can be merged. Please rebase the PR, @sroy745.
https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork
@sroy745 Thanks for this work, is there any update of this codes? and any performance gain when enable mtp=1?
Will this PR have further updates? It seems like there are still some bugs in the code, and the accuracy testing hasn’t been done yet, right?
any update? What is the current status of this PR? It seems like the functionality isn’t implemented correctly, and there are some bugs. After I fixed the bugs, I found that the output was incorrect. Could you help verify this? @sroy745
any update?