Skip to content

[Misc] Drop vlllm 0.19.1 support#8855

Open
wangxiyuan wants to merge 1 commit intovllm-project:mainfrom
wangxiyuan:drop_019
Open

[Misc] Drop vlllm 0.19.1 support#8855
wangxiyuan wants to merge 1 commit intovllm-project:mainfrom
wangxiyuan:drop_019

Conversation

@wangxiyuan
Copy link
Copy Markdown
Collaborator

@wangxiyuan wangxiyuan commented May 1, 2026

What this PR does / why we need it?

This PR removes legacy version-specific logic and checks related to vLLM v0.19.1 across the repository, including Dockerfiles, core scheduling logic, attention implementations, and end-to-end tests. It also updates the Docker build process to fetch vLLM using a specific commit hash. Critical issues were identified in all modified Dockerfiles where the VLLM_REPO argument was commented out while still being used in the RUN command, which will lead to build failures.

Does this PR introduce any user-facing change?

No. This is an internal cleanup and build configuration update.

How was this patch tested?

The changes involve removing version-specific skips in existing tests and updating build scripts. Testing should be verified via CI build pipelines.

@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented May 1, 2026

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

  • A PR should do only one thing, smaller PRs enable faster reviews.
  • Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
  • Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request removes support for vLLM version 0.19.1 to streamline the codebase and focus on newer versions. It involves cleaning up conditional checks, updating Docker build configurations to pin a specific commit, and removing legacy import paths and logic that were previously required for compatibility.

Highlights

  • Deprecation of vLLM 0.19.1: Removed support for vLLM version 0.19.1 across the codebase, including conditional logic, imports, and version checks.
  • Docker Configuration Update: Updated Dockerfiles to use a specific git commit hash for vLLM instead of relying on the 0.19.1 tag.
  • Code Cleanup: Simplified logic in schedulers, attention mechanisms, and model runners by removing legacy compatibility paths.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Ignored Files
  • Ignored by pattern: .github/workflows/** (4)
    • .github/workflows/pr_test_full.yaml
    • .github/workflows/pr_test_light.yaml
    • .github/workflows/schedule_update_estimated_time.yaml
    • .github/workflows/schedule_vllm_e2e_test.yaml
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Copy Markdown
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 PR removes legacy vLLM v0.19.1 version checks and logic from Dockerfiles, tests, and core components, while updating Docker builds to use a specific commit hash. Feedback highlights a critical bug in all Dockerfiles where the VLLM_REPO argument was accidentally commented out, which will break the build process.

Suggested PR Title:

[Misc][BugFix] Remove legacy v0.19.1 version checks and fix Dockerfile build arguments

Suggested PR Summary:

### What this PR does / why we need it?
This PR removes legacy version-specific logic and checks related to vLLM v0.19.1 across the repository, including Dockerfiles, core scheduling logic, attention implementations, and end-to-end tests. It also updates the Docker build process to fetch vLLM using a specific commit hash. Critical issues were identified in all modified Dockerfiles where the VLLM_REPO argument was commented out while still being used in the RUN command, which will lead to build failures.

### Does this PR introduce _any_ user-facing change?
No. This is an internal cleanup and build configuration update.

### How was this patch tested?
The changes involve removing version-specific skips in existing tests and updating build scripts. Testing should be verified via CI build pipelines.

Comment thread Dockerfile Outdated
Comment on lines +50 to +56
# ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
# ARG VLLM_TAG=v0.19.1
# RUN git clone --depth 1 -b $VLLM_TAG $VLLM_REPO /vllm-workspace/vllm
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
git -C /vllm-workspace/vllm checkout FETCH_HEAD
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

critical

The VLLM_REPO build argument is commented out, but it's used in the RUN command. This will cause the Docker build to fail. This suggestion restores the VLLM_REPO definition and removes the other obsolete commented-out code for better readability.

ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
    git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
    git -C /vllm-workspace/vllm checkout FETCH_HEAD

Comment thread Dockerfile.310p Outdated
Comment on lines +35 to +41
# ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
# ARG VLLM_TAG=v0.19.1
# RUN git clone --depth 1 -b $VLLM_TAG $VLLM_REPO /vllm-workspace/vllm
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
git -C /vllm-workspace/vllm checkout FETCH_HEAD
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

critical

The VLLM_REPO build argument is commented out, but it's used in the RUN command. This will cause the Docker build to fail. This suggestion restores the VLLM_REPO definition and removes the other obsolete commented-out code for better readability.

ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
    git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
    git -C /vllm-workspace/vllm checkout FETCH_HEAD

Comment thread Dockerfile.310p.openEuler Outdated
Comment on lines +34 to +40
# ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
# ARG VLLM_TAG=v0.19.1
# RUN git clone --depth 1 -b $VLLM_TAG $VLLM_REPO /vllm-workspace/vllm
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
git -C /vllm-workspace/vllm checkout FETCH_HEAD
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

critical

The VLLM_REPO build argument is commented out, but it's used in the RUN command. This will cause the Docker build to fail. This suggestion restores the VLLM_REPO definition and removes the other obsolete commented-out code for better readability.

ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
    git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
    git -C /vllm-workspace/vllm checkout FETCH_HEAD

Comment thread Dockerfile.a3 Outdated
Comment on lines +52 to +58
# ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
# ARG VLLM_TAG=v0.19.1
# RUN git clone --depth 1 -b $VLLM_TAG $VLLM_REPO /vllm-workspace/vllm
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
git -C /vllm-workspace/vllm checkout FETCH_HEAD
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

critical

The VLLM_REPO build argument is commented out, but it's used in the RUN command. This will cause the Docker build to fail. This suggestion restores the VLLM_REPO definition and removes the other obsolete commented-out code for better readability.

ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
    git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
    git -C /vllm-workspace/vllm checkout FETCH_HEAD

Comment thread Dockerfile.a3.openEuler Outdated
Comment on lines +51 to +57
# ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
# ARG VLLM_TAG=v0.19.1
# RUN git clone --depth 1 -b $VLLM_TAG $VLLM_REPO /vllm-workspace/vllm
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
git -C /vllm-workspace/vllm checkout FETCH_HEAD
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

critical

The VLLM_REPO build argument is commented out, but it's used in the RUN command. This will cause the Docker build to fail. This suggestion restores the VLLM_REPO definition and removes the other obsolete commented-out code for better readability.

ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
    git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
    git -C /vllm-workspace/vllm checkout FETCH_HEAD

Comment thread Dockerfile.openEuler Outdated
Comment on lines +51 to +57
# ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
# ARG VLLM_TAG=v0.19.1
# RUN git clone --depth 1 -b $VLLM_TAG $VLLM_REPO /vllm-workspace/vllm
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
git -C /vllm-workspace/vllm checkout FETCH_HEAD
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

critical

The VLLM_REPO build argument is commented out, but it's used in the RUN command. This will cause the Docker build to fail. This suggestion restores the VLLM_REPO definition and removes the other obsolete commented-out code for better readability.

ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_COMMIT=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
RUN git init /vllm-workspace/vllm && \
    git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
    git -C /vllm-workspace/vllm checkout FETCH_HEAD

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
@wangxiyuan wangxiyuan added ready read for review ready-for-test start test by label for PR labels May 1, 2026
@gcanlin
Copy link
Copy Markdown
Collaborator

gcanlin commented May 2, 2026

tests/e2e/multicard/2-cards/test_qwen3_moe.py seems to be breaking. #8864 is fixing it. And this bug also happened in other PRs. It could be a bug in current main branch.

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 module:core module:ops module:tests ready read for review ready-for-test start test by label for PR

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants