bugfix: Add guard for fp4/fp8 related include headers

[yzh119]

📌 Description

Fix compilation issue of cutlass_utils.cuh

🔍 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 @yzh119, 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 a compilation issue within cutlass_utils.cuh by adding a crucial header file. This ensures that the project can correctly compile code that utilizes FP8 data types, preventing build failures. The change is straightforward and primarily focuses on resolving this specific compilation problem.

Highlights

• Compilation Fix for FP8: I've added the #include <cuda_fp8.h> directive to include/flashinfer/cutlass_utils.cuh. This change directly addresses a compilation issue by ensuring that the necessary definitions for FP8 related functionalities are available during the build process.
• Code Cleanliness: I've removed an unnecessary blank line in include/flashinfer/cutlass_utils.cuh, contributing to minor code cleanliness.

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 a compilation error in cutlass_utils.cuh by including <cuda_fp8.h>. While this resolves the immediate issue, the change introduces an inconsistency. The FP8-related code is now included unconditionally, whereas the FP4 code in the same file is guarded by a preprocessor macro. For better maintainability and to avoid potential compilation failures on older CUDA toolkits, I've recommended wrapping the new include and the corresponding FP8 type specializations with a preprocessor guard, which also seems to be the intention based on the pull request title.

[gemini-code-assist]

While adding this include fixes the compilation error, it should be guarded to ensure compatibility with older CUDA toolkits and for consistency with how FP4 types are handled in this file. The pull request title, "Add guard for fp4/fp8 related include headers", also suggests this was the intention.

Please consider wrapping this include and the cutlass_dtype specializations for __nv_fp8_e4m3 and __nv_fp8_e5m2 (on lines 66-73) with a preprocessor macro, for example #if defined(FLASHINFER_ENABLE_FP8).

This would make the code more robust and align the handling of FP8 with FP4.