[main][Quant] Remove unused rotation functions and parameters from W4A4 LAOS quantization

[SlightwindSec]

Summary

• Remove unused set_rotation_config and apply_rotation methods from AscendW4A4LaosDynamicLinearMethod
• Remove unused rotation_type field and associated conditional quantization parameters (heads_rotation, kronecker_rotation_n, kronecker_rotation_m)

These rotation-related functions and parameters are never called in the current W4A4 LAOS dynamic quantization workflow.

• vLLM version: v0.15.0
• vLLM main: vllm-project/vllm@d7e17aa

[gemini-code-assist]

Summary of Changes

Hello @SlightwindSec, 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 focuses on refining the W4A4 LAOS dynamic quantization implementation by excising dead code. The changes streamline the codebase and improve efficiency by removing functions and parameters related to rotation that were never invoked in the current workflow, thereby also reducing memory footprint.

Highlights

• Code Cleanup: Removed the set_rotation_config and apply_rotation methods from AscendW4A4LaosDynamicLinearMethod as they were unused.
• Parameter Removal: Eliminated the rotation_type field and associated conditional quantization parameters (heads_rotation, kronecker_rotation_n, kronecker_rotation_m) which were never utilized.
• Memory Optimization: Reduced unnecessary memory allocation by removing the unused rotation matrices, which could be up to 160x160 float32.

🧠 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.

Changelog

• vllm_ascend/quantization/methods/w4a4_laos_dynamic.py
  • Removed the rotation_type attribute initialization from the __init__ method.
  • Deleted the set_rotation_config method.
  • Eliminated conditional initialization of heads_rotation, kronecker_rotation_n, and kronecker_rotation_m parameters within get_perchannel_param.
  • Removed the apply_rotation method.

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.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

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]

👋 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]

Code Review

This pull request removes unused rotation-related functions and parameters from the AscendW4A4LaosDynamicLinearMethod. The changes simplify the codebase by removing dead code, which is a good improvement for maintainability. The changes are correct and I have no further comments on the code.

Following the repository's style guide, I've provided suggestions for the PR title and summary:

Suggested PR Title:

[main][Quant][Refactor] Remove unused rotation logic in W4A4 LAOS quantization

Suggested PR Summary:

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

This PR refactors the `AscendW4A4LaosDynamicLinearMethod` by removing unused rotation-related code. The following components are removed:
- The `set_rotation_config` and `apply_rotation` methods.
- The `rotation_type` instance variable.
- Unused quantization parameters: `heads_rotation`, `kronecker_rotation_n`, and `kronecker_rotation_m`.

These components are not utilized in the current W4A4 LAOS dynamic quantization workflow. Their removal simplifies the codebase and eliminates unnecessary memory allocation for large rotation matrices, improving maintainability and efficiency.

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

No, this is an internal refactoring and does not introduce any user-facing changes.

### How was this patch tested?

CI is expected to pass with existing unit tests.