Fix FusedMoeRunner does not exist error

[nvpohanh]

Fix AttributeError: FusedMoeRunner does not exist error when running cutlass MoE.

Broken by #1201

📌 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 @nvpohanh, 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!

I've addressed an AttributeError that was preventing the FusedMoeRunner from being correctly initialized within the MoE system. This fix ensures that the FusedMoeRunner is properly accessed, resolving a recent regression and allowing MoE operations to function as expected.

Highlights

• Fixing FusedMoeRunner Instantiation: I've updated the instantiation of FusedMoeRunner within the MoERunner class. Previously, it was attempting to access module.FusedMoeRunner, which led to an AttributeError. The fix changes this to torch.classes.fused_moe_sm100.FusedMoeRunner, ensuring the correct class is loaded and assigned to the runner_dict.

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 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 or fill out our survey 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 fixes an AttributeError: FusedMoeRunner does not exist that occurred when running cutlass MoE. The fix correctly changes how the FusedMoeRunner class is instantiated. My review includes a suggestion to simplify the implementation for better code clarity and conciseness.

[gemini-code-assist]

While the current change correctly fixes the AttributeError, it can be simplified. The module variable, which holds the loaded FusedMoeRunner class, is already available in the scope. You can directly instantiate it using module(...) instead of referencing it through torch.classes. This would make the code more concise and avoid introducing an unnecessary temporary variable.

Suggested change

	runner = torch.classes.fused_moe_sm100.FusedMoeRunner(
	x_dtype,
	weight_dtype,
	output_dtype,
	use_deepseek_fp8_block_scale,
	use_w4a8_group_scaling,
	use_mxfp8_act_scaling,
	)
	MoERunner.runner_dict[instance_key] = runner
	MoERunner.runner_dict[instance_key] = module(
	x_dtype,
	weight_dtype,
	output_dtype,
	use_deepseek_fp8_block_scale,
	use_w4a8_group_scaling,
	use_mxfp8_act_scaling,
	)

[yzh119]

Appended some changes for ruff compiliance.