Mnnvl memory with custom communicator

[wenscarl]

📌 Description

🔍 Related Issues

🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.

✅ Pre-commit Checks

• I have installed pre-commit by running pip install pre-commit (or used your preferred method).
• I have installed the hooks with pre-commit install.
• I have run the hooks manually with pre-commit run --all-files and fixed any reported issues.

If you are unsure about how to set up pre-commit, see the pre-commit documentation.

🧪 Tests

• Tests have been added or updated as needed.
• All tests are passing (unittest, etc.).

Reviewer Notes

[gemini-code-assist]

Summary of Changes

Hello @wenscarl, 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 significantly refactors the MNNVL memory management system by introducing an extensible architecture for its communication layer. The core change involves abstracting the communication primitives, allowing for the integration of various communication libraries beyond the default MPI. This enhances the modularity and adaptability of the system, particularly for distributed computing scenarios.

Highlights

• Pluggable Communication Backend: I've introduced an abstract CommBackend interface and a MnnvlConfig dataclass, enabling the MnnvlMemory module to support custom communication backends. This decouples the memory management from a specific communication library.
• Backward Compatibility: To ensure existing functionality remains untouched, I've implemented a LegacyMPIBackend adapter. This adapter wraps the original mpi4py communication logic, making it conform to the new CommBackend interface and serving as the default communication method.
• Configurable MoE Workspaces: The MnnvlMoe class now accepts an optional MnnvlConfig when retrieving MoE workspaces. This allows users to specify and utilize a custom communication backend for Mixture-of-Experts (MoE) related operations, enhancing flexibility in distributed setups.

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 a communication backend abstraction for MnnvlMemory to allow for custom communicators, decoupling it from a hard dependency on mpi4py. The review identified a critical bug in the LegacyMPIBackend's Split method that would cause incorrect behavior in multi-GPU settings. There are also several debug statements that should be removed before merging.