[EPLB][Bugfix] Set parallel_config.enable_eplb to true to load redundant experts

[shenchuxiaofugui]

What this PR does / why we need it?

pr: vllm-project/vllm#37136 break eplb because it filters out redundant experts.
pr: vllm-project/vllm#37322 fix it due to use parallel_config.enable_eplb to determine whether to skip the weight loading filter.
But in vllm-ascend, parallel_config.enable_eplb is always false. When we use eplb, we temporarily set it to true.

Does this PR introduce any user-facing change?

How was this patch tested?

dataset	version	metric	mode	vllm-api-stream-chat
aime2024	604a78	accuracy	gen	86.67

[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 addresses a bug where the system was not correctly loading redundant experts due to the enable_eplb configuration not being properly set. By introducing a dedicated flag to determine EPLB enablement and using it to conditionally update the parallel configuration before model loading, this change ensures that the system correctly initializes and utilizes expert parallelism as intended, allowing for the proper loading of redundant experts.

Highlights

• EPLB Enablement Logic: Introduced a new instance variable self.eplb_enable in ModelRunnerV1 to consolidate the logic for determining if Expert Parallelism Load Balancing (EPLB) should be active. This flag is set to true if dynamic EPLB is enabled or if an expert map path is provided.
• Conditional enable_eplb Configuration: Modified the load_model method to conditionally set self.vllm_config.parallel_config.enable_eplb to True based on the newly introduced self.eplb_enable flag. This ensures that the parallel configuration correctly reflects the need to load redundant experts when EPLB is active.

🧠 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.

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.

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

The pull request correctly addresses the bug by introducing self.eplb_enable to centralize the EPLB enablement logic and then using this flag to set self.vllm_config.parallel_config.enable_eplb = True during model loading. This ensures that redundant experts are loaded when EPLB is active, aligning with the PR's objective.