refactor: unify autotuner for fp4 gemm backends

[ttyio]

📌 Description

unify autotuner for fp4 backends: trtllm and cutlass.

🔍 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 @ttyio, 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 refactored the FP4 GEMM autotuner to unify the logic for both TRTLLM and Cutlass backends. This change introduces a new centralized function, fp4_gemm_sm100, that handles the autotuning process, allowing for automatic selection of the optimal backend.

Highlights

• Unified Autotuner: I've introduced a new fp4_gemm_sm100 function that centralizes the autotuning logic for FP4 GEMM operations, supporting both TRTLLM and Cutlass backends.
• Refactored Runner Instantiation: The cutlass_fp4_gemm and trtllm_fp4_gemm functions have been refactored into _runner variants that now solely return instances of their respective GEMM runners, decoupling the runner creation from the autotuning process.
• "Auto" Backend Option: The mm_fp4 function now accepts an "auto" backend option, which leverages the new unified autotuner to automatically select the best performing FP4 GEMM backend (TRTLLM or Cutlass).

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 refactors the autotuner for FP4 GEMM backends (trtllm and cutlass) by unifying their logic into a single function fp4_gemm_sm100. This is a good improvement that reduces code duplication and simplifies the overall structure. The changes are well-implemented and consistent. I have one suggestion to make the autotuner cache key more robust by using a dynamic name for the custom operation, reflecting the configuration being tuned.

[nvpohanh]

cc @nvjullin