[Misc][Quantization] Remove kvcache quant weight related patches.

[menogrey]

What this PR does / why we need it?

After vllm-project/vllm#43167 vllm-project/vllm#44589, we can remove our two patches about kvcache quant weight.

Does this PR introduce any user-facing change?

How was this patch tested?

• vLLM version: v0.25.1
• vLLM main: vllm-project/vllm@54503ec

[gemini-code-assist]

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 streamlines the KV cache quantization weight loading process by replacing legacy monkey-patches with a structured WeightsMapper implementation. This change improves maintainability, reduces code complexity, and aligns the quantization configuration with standard vLLM patterns.

Highlights

• Refactored KV Cache Mapping: Replaced the manual get_cache_scale method with a more flexible get_cache_scale_mapper in AscendModelSlimConfig to support dynamic mapping for C8, FA, and Indexer quantization.
• Removal of Legacy Patches: Deleted patch_gqa_c8.py and patch_weight_utils.py, cleaning up technical debt and removing reliance on monkey-patching for weight loading.
• Improved Test Coverage: Added comprehensive unit tests in test_modelslim_config.py to verify the new mapper logic across different quantization configurations.

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]

👋 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.

[github-actions]

This pull request has conflicts, please resolve those before we can evaluate the pull request.

[gemini-code-assist]

Code Review

Suggested PR Title:

[Ops][Misc] Refactor cache scale mapping to use WeightsMapper and remove obsolete patches

Suggested PR Summary:

### What this PR does / why we need it?
This PR refactors the cache scale mapping mechanism in `AscendModelSlimConfig` by replacing the custom `get_cache_scale` method with `get_cache_scale_mapper()`, which returns a `WeightsMapper`. This aligns with upstream vLLM's design.
As a result, the custom patches `patch_weight_utils.py` and `patch_gqa_c8.py` (which were previously used to intercept and remap C8/FA/indexer quantization scales) are no longer needed and have been removed.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
Added unit tests in `tests/ut/quantization/test_modelslim_config.py` covering:
- Default mapper behavior
- C8 KV cache type mapper
- FA quantization mapper
- Indexer quantization mapper

I have no additional feedback to provide as there are no review comments.

[menogrey]

/rerun
[Bot]: rerun completed.

Rerun:

• E2E

[menogrey]

/weekly multi-node-glm4.7-w8a8c8-layerwise
weekly command triggered.

• Weekly-A3: workflow run