Add CUDA arch 12.0 to installation guide

[mgoin]

📌 Description

There are several kernels available for 12.0, including quantized gemm

🔍 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 @mgoin, 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 updates the FlashInfer installation guide to officially support CUDA architecture 12.0. By modifying the FLASHINFER_CUDA_ARCH_LIST environment variable in the documentation, users can now correctly configure their build environment to compile FlashInfer with the latest NVIDIA GPU architectures, ensuring access to optimized kernels like quantized GEMM.

Highlights

• CUDA Arch 12.0 Support: The installation guide has been updated to include CUDA architecture 12.0 in the FLASHINFER_CUDA_ARCH_LIST environment variable. This enables users to build FlashInfer with support for newer NVIDIA GPUs.
• Kernel Availability: The addition of CUDA arch 12.0 support is motivated by the availability of several kernels, including quantized GEMM, for this architecture, enhancing performance on compatible hardware.

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 adds the CUDA architecture 12.0 to the installation guide for AOT compilation. The change is straightforward and reflects newly added support for this architecture. My review includes a suggestion to ensure consistency in the architecture naming (e.g., using 12.0a instead of 12.0 if applicable), which could be important for correct compilation and performance.

[gemini-code-assist]

For consistency with other architectures in this list like 9.0a and 10.0a, 12.0 should likely be 12.0a. The a suffix is often important for enabling specific hardware features (like Tensor Cores) during compilation. Using an incorrect identifier could lead to build failures or suboptimal performance.

Suggested change

	export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0"
	export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0a"

[yzh119]

ditto

[gemini-code-assist]

For consistency with other architectures in this list like 9.0a and 10.0a, 12.0 should likely be 12.0a. The a suffix is often important for enabling specific hardware features (like Tensor Cores) during compilation. Using an incorrect identifier could lead to build failures or suboptimal performance.

Suggested change

	export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0"
	export FLASHINFER_CUDA_ARCH_LIST="7.5 8.0 8.9 9.0a 10.0a 12.0a"

[yzh119]

ditto