[WIP][EPLB] Enable Llama4 EPLB

[b8zhong]

Purpose

As a part of #20468, support EPLB for Llama4

Test Plan

WIP,

Test Result

vllm serve /models/Llama4-Scout-17B --tensor-parallel-size 8 --enable-eplb

vllm serve /fp8-llama/llama4scout-fp8/ \
  --tensor-parallel-size 8 \
  --max-model-len 2048 \
  --enable-expert-parallel \
  --enable-eplb \
  --num-redundant-experts 16 \
  --eplb-window-size 1000 \
  --eplb-step-interval 3000 \
  --trust-remote-code \
  --enforce-eager

WIP

(Optional) Documentation Update

WIP

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Summary of Changes

Hello @b8zhong, 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 is a work-in-progress effort to integrate Expert Parallel Load Balancing (EPLB) capabilities into the Llama4 model within vLLM. My changes involve extending the model's architecture to support EPLB configuration, implementing a standardized interface for MoE management, and ensuring proper propagation of EPLB settings throughout the model's layers.

Highlights

• Enable Expert Parallel Load Balancing (EPLB) for Llama4: I've introduced an enable_eplb boolean parameter across various Llama4 model components (Llama4MoE, Llama4DecoderLayer, Llama4Model) to control the activation of Expert Parallel Load Balancing. This flag is propagated from the top-level model configuration down to individual MoE layers.
• MixtureOfExperts Interface Implementation: The Llama4ForCausalLM class now inherits from a new MixtureOfExperts interface. This involves implementing several properties (expert_weights, num_moe_layers, num_logical_experts, etc.) and methods (set_eplb_state, get_expert_weights) to provide a standardized way to query and manage the state of Mixture-of-Experts layers for EPLB.
• MoE Layer Tracking and Management: I've added logic within Llama4Model and Llama4ForCausalLM to identify and track all Mixture-of-Experts (MoE) layers. This tracking is crucial for the MixtureOfExperts interface to correctly manage and expose information about the model's expert configuration and state for load balancing.
• Dependency Updates and Model Layer Creation Override: I've added new imports for the MixtureOfExperts interface and PPMissingLayer from internal vLLM modules, indicating integration with existing MoE and pipeline parallelism infrastructure. Additionally, the make_layers method in Llama4Model has been overridden to ensure the enable_eplb parameter is correctly passed to the decoder layers during their creation.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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. ↩

[gemini-code-assist]

Code Review

This pull request introduces changes to enable EPLB for the Llama4 model. The changes involve propagating an enable_eplb flag through the model's layers and implementing the MixtureOfExperts interface. There are opportunities for code improvement to enhance maintainability and correctness.

[mergify]

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @b8zhong.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

[mergify]

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @b8zhong.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork