Skip to content

[draft] test torch 2.11#155

Open
jikunshang wants to merge 1 commit intovllm-project:mainfrom
jikunshang:kunshang/torch211
Open

[draft] test torch 2.11#155
jikunshang wants to merge 1 commit intovllm-project:mainfrom
jikunshang:kunshang/torch211

Conversation

@jikunshang
Copy link
Collaborator

Essential Elements of an Effective PR Description Checklist

  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS ABOVE HAVE BEEN CONSIDERED.

Purpose

Test Plan

Test Result

(Optional) Documentation Update

BEFORE SUBMITTING, PLEASE READ https://docs.vllm.ai/en/latest/contributing (anything written below this line will be removed by GitHub Actions)

Copilot AI review requested due to automatic review settings February 23, 2026 01:08
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

This PR updates the repo’s pinned PyTorch XPU dependency to Torch 2.11 and adjusts CI to install from the PyTorch XPU test wheel index, seemingly to validate compatibility ahead of a stable release.

Changes:

  • Switch Torch pin from 2.10.0+xpu to 2.11.0+xpu in both requirements.txt and pyproject.toml.
  • Change the PyTorch wheel source from the stable XPU index to the whl/test/xpu index.
  • Update the unit test workflow to build/run using a xpu-kernel-ci-image:test-211 Docker tag and install with the test XPU index.

Reviewed changes

Copilot reviewed 2 out of 3 changed files in this pull request and generated 3 comments.

File Description
requirements.txt Moves default install to Torch 2.11 XPU and the PyTorch test XPU wheel index.
pyproject.toml Updates build-system Torch requirement to 2.11 XPU.
.github/workflows/ut.yaml Updates CI docker tag to test-211 and switches install to the test XPU wheel index.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +35 to +37
docker build -t xpu-kernel-ci-image:test-211 -f Dockerfile.xpu .
docker tag xpu-kernel-ci-image:test-211 ${{ env.REGISTRY }}/xpu-kernel-ci-image:test-211
docker push ${{ env.REGISTRY }}/xpu-kernel-ci-image:test-211
Copy link

Copilot AI Feb 23, 2026

Choose a reason for hiding this comment

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

The workflow no longer tags/pushes xpu-kernel-ci-image:latest (it now only produces :test-211). Downstream workflows (e.g. wheel-per-commit.yaml) still run in localhost:5000/xpu-kernel-ci-image:latest, so they’ll keep using a stale image or fail if :latest doesn’t exist on the runner. Consider continuing to tag/push :latest as well, or update all dependent workflows to use :test-211 consistently.

Copilot uses AI. Check for mistakes.
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants