fix _block_scaled_block_gemm kernel, remove config class

[hiworldwzj]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello, 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 streamlines the fp8w8a8_block_gemm_kernel by eliminating a complex dynamic configuration class and its associated autotuning logic. The change replaces the previous configuration lookup with a fixed set of parameters, simplifying the kernel's execution path and potentially resolving issues related to dynamic configuration selection. The primary impact is a reduction in code complexity and a more predictable kernel setup for FP8 block matrix multiplication.

Highlights

• Configuration Class Removal: The Fp8BlockMMKernelConfig class, responsible for dynamically determining optimal kernel configurations, has been entirely removed. This includes its methods for trying to get the best configuration and saving configurations.
• Static Kernel Configuration: The dynamic lookup for kernel run_config within the w8a8_block_fp8_matmul function has been replaced with a hardcoded, static configuration dictionary. This simplifies the kernel's setup by removing the autotuning logic.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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.

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 kernel configuration logic by removing the Fp8BlockMMKernelConfig class and relying on the @autotune decorator for performance tuning. This is a good simplification that centralizes configuration management. However, I've identified a potential bug in the new fallback configuration where the block sizes for N and K dimensions appear to be swapped. This could lead to suboptimal performance or errors when non-square block sizes are used. Please see the specific comment for details.

[gemini-code-assist]

There seems to be a mix-up in assigning BLOCK_N and BLOCK_K from block_size. block_size[0] is block_k (for the K dimension) and block_size[1] is block_n (for the N dimension). However, BLOCK_N is being assigned block_size[0] and BLOCK_K is being assigned block_size[1]. This should be swapped to align the tiling dimensions correctly with the quantization block dimensions.

Suggested change

	"BLOCK_N": block_size[0],
	"BLOCK_K": block_size[1],
	"BLOCK_N": block_size[1],
	"BLOCK_K": block_size[0],