Skip to content

[BugFix]A2G3 adapted for the CH version of HDK - #11504

Merged
zzzzwwjj merged 1 commit into
vllm-project:releases/v0.23.0from
ZT-AIA:chhdk_v0.23.0
Jul 6, 2026
Merged

zzzzwwjj merged 1 commit into
vllm-project:releases/v0.23.0from
ZT-AIA:chhdk_v0.23.0

Conversation

@ZT-AIA

@ZT-AIA ZT-AIA commented Jul 6, 2026 •

Copy link
Copy Markdown
Collaborator

What this PR does / why we need it?

VLLM ASCEND is adapted for the overseas version of HDK A2G3. To ensure that VLLM ASCEND can be properly installed and used in scenarios where the overseas version of HDK is being used.

Does this PR introduce any user-facing change?

No

How was this patch tested?

the installation and operation of VLLM ASCEND in the environment of the overseas version of HDK must be carried out. After self-verification confirms no issues, the results still need to be provided by the testers.

Signed-off-by: ZT-AIA <1028681969@qq.com>
@ZT-AIA
ZT-AIA requested a review from wangxiyuan as a code owner July 6, 2026 12:33
@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 updates the chip detection logic in setup.py to support the A2G3 variant of the HDK. This ensures that VLLM ASCEND can be correctly configured and installed in environments utilizing the overseas version of the HDK.

Highlights

  • Chip identification update: Added support for the A2G3 chip variant in the get_chip_type function to map it to ascend910b1.
New Features

🧠 You can now enable Memory (public preview) 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.

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 the 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 counterproductive. 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. ↩

@github-actions

github-actions Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

👋 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.


Tip

💡 Consider Linking a Related Issue or RFC

Your PR title contains the [BugFix] tag, indicating a bug fix or new feature.

Linking a related issue or RFC in the PR description is strongly encouraged — it gives reviewers helpful context and speeds up the review. You can use any of these keywords:

  • Fixes #<issue_number>
  • Closes #<issue_number>
  • Resolves #<issue_number>
  • Refs #<rfc_or_issue_number> (for RFCs)

🙏 Thanks for helping us keep the project well-organized!

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

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.

Code Review

This pull request adds support for identifying the 'a2g3' chip name in setup.py and mapping it to 'ascend910b1'. The reviewer pointed out a contradiction in the code comment, which refers to the 'CH version of the HDK' instead of the 'overseas version of HDK A2G3' as described in the PR, and suggested a correction.

Comment thread setup.py
Comment on lines +121 to +123
elif "a2g3" in chip_name.lower():
# A2 case: CH version of the HDK
return "ascend910b1"

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.

high

The comment on line 122 refers to the "CH version of the HDK", but the PR description states that this change is specifically to adapt for the "overseas version of HDK A2G3". This contradiction is misleading and could cause confusion for future maintainers. Please update the comment to refer to the "overseas version" to align with the actual intent of this PR.


Following the Repository Style Guide (Pull Request Summary Style Guide), here are the suggested PR Title and PR Summary:

Suggested PR Title:

[Ops][BugFix] Adapt A2G3 for the overseas version of HDK

Suggested PR Summary:

### What this PR does / why we need it?

This PR adds support for automatically identifying the chip type on environments using the overseas version of HDK A2G3. When the chip name contains "a2g3", it correctly identifies and returns "ascend910b1" as the SOC version, ensuring that vLLM Ascend can be properly installed and run.

### Does this PR introduce _any_ user-facing change?

No

### How was this patch tested?

The installation and operation of vLLM Ascend in the environment of the overseas version of HDK must be carried out. After self-verification confirms no issues, the results still need to be provided by the testers.
Suggested change
elif "a2g3" in chip_name.lower():
# A2 case: CH version of the HDK
return "ascend910b1"
elif "a2g3" in chip_name.lower():
# A2 case: overseas version of the HDK
return "ascend910b1"
References
  1. The PR Title and PR Summary must follow the specific format defined in the Repository Style Guide. (link)

@zzzzwwjj
zzzzwwjj merged commit cabfbf8 into vllm-project:releases/v0.23.0 Jul 6, 2026
6 checks passed
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