[Minor] Remove deprecated tile_tokens_dim kwargs

[DarkSharpness]

Motivation

This arg is default as None and marked as deprecated in flashinfer v0.5.3, which will soon be removed in the upcoming release v0.6.0. Let's just remove them.

Related PR: flashinfer-ai/flashinfer#2086

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.
• Work with maintainers to merge your PR. See the PR Merge Process

[gemini-code-assist]

Summary of Changes

Hello @DarkSharpness, 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 focuses on maintaining forward compatibility with the flashinfer library by removing a deprecated argument. The tile_tokens_dim argument, which was previously marked for deprecation and set to None, has been eliminated from relevant function calls. This ensures that the system remains robust and avoids potential breakage when flashinfer updates to version 0.6.0, where this argument will no longer exist.

Highlights

• Deprecated Argument Removal: The tile_tokens_dim keyword argument, which was already marked as deprecated and set to None, has been removed from function calls in fp8.py and modelopt_quant.py.
• Future Compatibility: This change proactively updates the codebase to align with upcoming flashinfer v0.6.0, where the tile_tokens_dim argument will be completely removed, preventing potential compatibility issues.

🧠 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.

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 removes the deprecated tile_tokens_dim keyword argument from trtllm_fp8_block_scale_moe and trtllm_fp8_per_tensor_scale_moe function calls. The changes are good and align with the goal of cleaning up deprecated code.

For completeness, you might want to consider removing this argument from other places as well. I found another instance in python/sglang/srt/layers/moe/fused_moe_triton/layer.py within the FlashInferFP4MoE.forward method (line 1229), where trtllm_fp4_block_scale_moe is called with tile_tokens_dim=None. Based on the related flashinfer PR, this argument is also deprecated in trtllm_fp4_block_scale_moe. Removing it there would make this cleanup more comprehensive.

[b8zhong]

@DarkSharpness #13535 (just FYI)

[Fridge003]

Covered by #15551