Skip to content

Conversation

WoosukKwon
Copy link
Collaborator

@WoosukKwon WoosukKwon commented Jul 17, 2025

In vLLM V1, HPU is supported as a plugin.

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
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 the ci/build label Jul 17, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
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 effectively removes the V0 HPU backend, which is a significant and welcome cleanup. The changes are mostly removals of HPU-specific files and code paths, and they appear to be correct and self-contained.

I've identified one piece of dead code that was left behind in setup.py and have commented on it directly.

Additionally, my review of the entire codebase (not just the changed files) revealed a few other HPU-related leftovers that were not part of this pull request's diff. Since I cannot comment on files that were not modified, I'm listing them here for your consideration in a follow-up PR:

  • In vllm/config.py, the Device type hint still includes "hpu".
  • In vllm/envs.py, HPU-specific environment variables like VLLM_USE_HPU_CONTIGUOUS_CACHE_FETCH and VLLM_HPU_USE_DELAYED_SAMPLING are still defined.

Addressing these will complete the removal of the HPU backend. Overall, great work on this large-scale refactoring!

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

Please make corresponding update to docs.

@WoosukKwon WoosukKwon added the ready ONLY add when PR is ready to merge/full CI is needed label Jul 17, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
@xuechendi
Copy link
Contributor

@kzawora-intel , please take a look.

@WoosukKwon WoosukKwon enabled auto-merge (squash) July 17, 2025 20:30
@hmellor hmellor moved this to In Progress in V0 Deprecation Jul 17, 2025
@WoosukKwon WoosukKwon disabled auto-merge July 17, 2025 23:37
@WoosukKwon WoosukKwon merged commit 4de7146 into main Jul 17, 2025
98 of 104 checks passed
@WoosukKwon WoosukKwon deleted the woosuk/remove-neuron-hpu branch July 17, 2025 23:37
@github-project-automation github-project-automation bot moved this from In Progress to Done in V0 Deprecation Jul 17, 2025
WorldExplored pushed a commit to nadathurv/vllm that referenced this pull request Jul 19, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
WorldExplored pushed a commit to nadathurv/vllm that referenced this pull request Jul 19, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: WorldExplored <srreyansh.sethi@gmail.com>
hj-mistral pushed a commit to hj-mistral/vllm that referenced this pull request Jul 19, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Himanshu Jaju <hj@mistral.ai>
LyrisZhong pushed a commit to LyrisZhong/vllm that referenced this pull request Jul 23, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
avigny pushed a commit to avigny/vllm that referenced this pull request Jul 31, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
x22x22 pushed a commit to x22x22/vllm that referenced this pull request Aug 5, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: x22x22 <wadeking@qq.com>
Pradyun92 pushed a commit to Pradyun92/vllm that referenced this pull request Aug 6, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
npanpaliya pushed a commit to odh-on-pz/vllm-upstream that referenced this pull request Aug 6, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
jinzhen-lin pushed a commit to jinzhen-lin/vllm that referenced this pull request Aug 9, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
paulpak58 pushed a commit to paulpak58/vllm that referenced this pull request Aug 13, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Paul Pak <paulpak58@gmail.com>
taneem-ibrahim pushed a commit to taneem-ibrahim/vllm that referenced this pull request Aug 14, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
diegocastanibm pushed a commit to diegocastanibm/vllm that referenced this pull request Aug 15, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Diego-Castan <diego.castan@ibm.com>
epwalsh pushed a commit to epwalsh/vllm that referenced this pull request Aug 27, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
googlercolin pushed a commit to googlercolin/vllm that referenced this pull request Aug 29, 2025
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ci/build ready ONLY add when PR is ready to merge/full CI is needed
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

3 participants