[MOE Refactor] Remove QuantType in prepare_finalize.py

[shenchuxiaofugui]

What this PR does / why we need it?

To prevent confusion between different QuantType classes, we remove** QuantType in prepare_finalize.py

Does this PR introduce any user-facing change?

How was this patch tested?

Of course! Here is a comprehensive explanation of deep learning, broken down for clarity.\n\n### The Simple Analogy: A Child Learning to Recognize a Cat\n\nImagine teaching a child what a cat is. You don't give them a rulebook with instructions like "has pointy ears, whiskers, and a tail." Instead, you show them many pictures, saying "this is a cat" or "this is not a cat." The child's brain gradually learns to identify the complex patterns—the combination of shapes, colors, and textures—that define "cat-ness."\n\nDeep learning is essentially this, but for computers. It's a method for teaching computers to learn from examples and recognize patterns directly from data (like images, sound, or text) without being explicitly programmed with rigid rules.\n\n---\n\n### The Technical Definition\n\nDeep Learning is a subfield of machine learning, which itself is a subfield of artificial intelligence (AI). It uses artificial neural networks with many layers ("deep" networks) to model and understand complex patterns in data.\n\nHere are the key concepts in that definition:\n\n1. Artificial Intelligence (AI): The broad science of making machines smart and capable of performing tasks that typically require human intelligence.\n2. Machine Learning (ML): A subset of AI that gives computers the ability to learn from data without being explicitly programmed for every single rule.\n3. Deep Learning (DL): A specific, powerful

• vLLM version: v0.15.0
• vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0

[gemini-code-assist]

Summary of Changes

Hello @shenchuxiaofugui, 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 refactors the QuantType enum by centralizing its definition within the vllm_ascend.quantization.methods.base module. This change eliminates redundant definitions and ensures a single, authoritative source for quantization types across the codebase, thereby preventing potential confusion and streamlining the logic that interacts with these types.

Highlights

• QuantType Enum Centralization: The QuantType enum definition has been removed from vllm_ascend/ops/fused_moe/prepare_finalize.py to centralize its definition.
• Unified QuantType Import: All files referencing QuantType now import it from the single, authoritative location: vllm_ascend/quantization/methods/base.
• Simplified QuantType Retrieval Logic: The _get_quant_type method in vllm_ascend/ops/fused_moe/fused_moe.py has been simplified, leveraging the consistent QuantType definition and using getattr for safer attribute access.

🧠 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

• tests/ut/ops/test_moe_comm_method.py
  • Updated the import path for QuantType to reference the centralized definition.
• vllm_ascend/ops/fused_moe/fused_moe.py
  • Updated the import path for QuantType.
  • Simplified the _get_quant_type method by removing redundant checks and direct mappings, relying on the unified QuantType enum.
• vllm_ascend/ops/fused_moe/moe_comm_method.py
  • Updated the import path for QuantType.
• vllm_ascend/ops/fused_moe/prepare_finalize.py
  • Removed the local definition of the QuantType enum.
  • Added an import for QuantType from vllm_ascend/quantization/methods/base.

Activity

• No human activity (comments, reviews, etc.) has been recorded on this pull request yet.

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 is a refactoring effort to remove a duplicate QuantType enum definition from vllm_ascend/ops/fused_moe/prepare_finalize.py. By centralizing the QuantType enum in vllm_ascend/quantization/methods.base, the changes improve code clarity, reduce redundancy, and prevent potential confusion. The implementation of _get_quant_type in fused_moe.py is also simplified as part of this refactoring. The changes are well-executed and improve the overall code quality.

As per the repository's style guide, I've provided a suggested pull request title and summary below. The current summary is incomplete and contains placeholder text.

Suggested PR Title:

[MoE][Refactor] Remove duplicate QuantType from prepare_finalize.py

Suggested PR Summary:

### What this PR does / why we need it?
This pull request refactors the codebase to eliminate a duplicate `QuantType` enum definition in `vllm_ascend/ops/fused_moe/prepare_finalize.py`.

All modules that previously used the local definition now import `QuantType` from a single source of truth: `vllm_ascend.quantization.methods.base`. This change prevents confusion between different `QuantType` classes and improves code maintainability.

As a result of this refactoring, the `_get_quant_type` method in `vllm_ascend/ops/fused_moe/fused_moe.py` has also been simplified.

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

### How was this patch tested?
CI passed.

[whx-sjtu]

cc @SlightwindSec

[github-actions]

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