Skip to content

[V0 deprecation] Deprecate V0 Neuron backend #21159

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

WoosukKwon
Copy link
Collaborator

@WoosukKwon WoosukKwon commented Jul 18, 2025

In vLLM V1, Neuron will be supported as a plugin.

See #21082

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Copy link

👋 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 mergify bot added documentation Improvements or additions to documentation ci/build speculative-decoding labels Jul 18, 2025
@WoosukKwon WoosukKwon added the ready ONLY add when PR is ready to merge/full CI is needed label Jul 18, 2025
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request cleanly deprecates and removes the V0 Neuron backend. The changes are comprehensive, covering not only the core implementation files but also associated tests, examples, CI/CD pipeline configurations, and dependency management files. The removal appears to be thorough, with no obvious leftover code or broken references. I found no issues of high or critical severity. The changes align well with the stated objective of moving Neuron support to a plugin for vLLM V1.

@WoosukKwon
Copy link
Collaborator Author

WoosukKwon commented Jul 18, 2025

@aarondou Could you please take a look? I'm actually not sure which part will still be needed for your proposal #21082

@hmellor hmellor moved this to In Progress in V0 Deprecation Jul 18, 2025
@aarondou
Copy link

Thank you for putting up the changes @WoosukKwon . Will review.

@aarondou
Copy link

We will pull the changes down to integrate with our V1 internal implementation to test the changes. The changes to support Neuron on vLLM V1 will be published as PRs at the same time.

@mrinalks
Copy link
Contributor

@WoosukKwon #21082 proposes Neuron as an in-tree implementation (not plugin) on V1 Engine. Please see Change 1 and Change 2 (various options) there. @aarondou let us review the files here and ensure nothing required is actually deleted.

Copy link

mergify bot commented Jul 21, 2025

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

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

@mergify mergify bot added the needs-rebase label Jul 21, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ci/build documentation Improvements or additions to documentation needs-rebase ready ONLY add when PR is ready to merge/full CI is needed speculative-decoding
Projects
Status: In Progress
Development

Successfully merging this pull request may close these issues.

3 participants