fix: missing header include in decode kernel jit binding

[MasterJH5574]

📌 Description

This commit adds the missing include of the header decode.cuh in the JIT binding csrc/batch_decode.cu, without this fix, there will be linking error when linking batch_decode.o, batch_decode_kernel.o and batch_decode_jit_binding.o.

The reason is that, csrc/batch_decode.cu relies on scheduler.cuh for decoding attention planning. scheduler.cuh declares the decode kernel of BatchDecodeWithPagedKVCacheKernel, which is implemented in decode.cuh, but does not include decode.cuh. Therefore, if csrc/batch_decode.cu does not include decode.cuh, the decode kernel will be a symbol that is declared but not implemented.

🔍 Related Issues

N/A

🚀 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

N/A

[gemini-code-assist]

Summary of Changes

Hello @MasterJH5574, 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 addresses a specific build-time linking error by introducing a necessary header inclusion in csrc/batch_decode.cu. The change ensures that a kernel function's implementation is correctly linked, resolving a dependency chain where a declaration was present but its definition was not accessible to the compilation unit, thus preventing compilation failures.

Highlights

• Linking Error Fix: Resolved a linking error that occurred during the compilation of JIT binding components (batch_decode.o, batch_decode_kernel.o, batch_decode_jit_binding.o) by ensuring all necessary header dependencies are met.
• Header Inclusion: Added the missing #include <flashinfer/attention/decode.cuh> to csrc/batch_decode.cu. This ensures that the implementation of BatchDecodeWithPagedKVCacheKernel, declared in scheduler.cuh and relied upon by csrc/batch_decode.cu, is properly available during linking.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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 correctly addresses a linking error by adding the missing #include <flashinfer/attention/decode.cuh> in csrc/batch_decode.cu. The change is straightforward and effective. My review includes one suggestion for a potential follow-up to improve code maintainability by moving the include to a more appropriate location to better reflect the dependency between headers.