[Misc][Platform]enable model runner v2 by default via whitelists

[wxsIcey]

What this PR does / why we need it?

Replace the use_v2_model_runner monkey-patch with an Ascend-native property on VllmConfig, applied in NPUPlatform.check_and_update_config.

• Model whitelist: default-V2 architectures (Qwen3ForCausalLM) .
• Feature whitelist: whitelisted models may stack eagle/mtp/dflash spec decoding.
• V2 requires Triton; fall back to V1 otherwise.

Does this PR introduce any user-facing change?

N/A

How was this patch tested?

CI passed with new added/existing test.

Co-authored-by: zouzy

• vLLM main: vllm-project/vllm@e6bfe03

[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 refactors how the V2 model runner is enabled for Ascend NPU devices. Instead of relying on a simple environment variable override, the system now dynamically evaluates model architecture compatibility, Triton availability, and feature support (such as speculative decoding or parallel execution modes) to determine if the V2 runner can be safely used. This approach improves stability by preventing crashes on unsupported configurations while allowing the V2 runner to be utilized where it is fully compatible.

Highlights

• Model Runner V2 Enablement: Replaced the static monkey-patch for V2 model runner enablement with a dynamic, feature-aware logic implementation in the NPU platform configuration.
• Feature Compatibility Checks: Introduced comprehensive compatibility checks to verify if the V2 model runner supports specific model architectures and features, falling back to V1 when necessary.
• Cleanup of Legacy Patches: Removed redundant monkey-patch files and initialization imports that were previously used to force-enable or gate the V2 model runner.

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.

[gemini-code-assist]

Code Review

This pull request refactors how the V2 model runner is enabled on Ascend NPU by removing legacy monkey-patches and implementing robust, Ascend-specific heuristics directly in vllm_ascend/platform.py. The review feedback suggests formatting the PR title and summary according to the repository style guide, using existing helper functions (is_moe_model and enable_sp) to improve configuration checks, and addressing a Python 3.9 compatibility issue with importlib.metadata.entry_points.

[github-actions]

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

[wxsIcey]

cc @wangxiyuan This pr enable model runner v2 for specific models and features. These models and features have e2e tests. PTAL.

[github-actions]

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

[github-actions]

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

[github-actions]

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

[wxsIcey]

/rerun
[Bot]: rerun completed.

Rerun (failed jobs only):

• E2E

[github-actions]

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