Skip to content

Clean up deprecated tile_tokens_dim for next flashinfer#13341

Merged
hnyls2002 merged 1 commit intosgl-project:mainfrom
bzhng-development:vz/cleanup-deprecation
Nov 15, 2025
Merged

Clean up deprecated tile_tokens_dim for next flashinfer#13341
hnyls2002 merged 1 commit intosgl-project:mainfrom
bzhng-development:vz/cleanup-deprecation

Conversation

@vincentzed
Copy link
Contributor

Motivation

When flashinfer 0.5.3 out, it will no longer be accepted
flashinfer-ai/flashinfer#2086
It already does nothing, and is passed as None (and unused flashinfer side)

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

Signed-off-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>
@vincentzed vincentzed marked this pull request as ready for review November 15, 2025 16:25
@github-actions github-actions bot added the quant LLM Quantization label Nov 15, 2025
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @vincentzed, 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 cleaning up the codebase by removing the tile_tokens_dim parameter from several function calls. This parameter is being deprecated in future versions of FlashInfer (specifically 0.5.3 and beyond) and is currently passed as None without any functional impact. The change ensures forward compatibility with the FlashInfer library and streamlines the code by removing an unnecessary argument.

Highlights

  • Code Cleanup: Removed the deprecated tile_tokens_dim parameter from various function calls across the codebase.
  • FlashInfer Compatibility: Ensured compatibility with upcoming FlashInfer 0.5.3+ releases, where this parameter will no longer be accepted.
  • Unused Parameter Removal: Eliminated a parameter that was already being passed as None and was unused on the FlashInfer side, simplifying the code.
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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request performs a clean-up by removing the deprecated tile_tokens_dim argument from calls to FlashInfer's MoE kernels across four different files. The changes are consistent and correctly applied, preparing the codebase for future updates of the FlashInfer library. The modifications are straightforward and I have no concerns.

@hnyls2002 hnyls2002 merged commit 0d116b9 into sgl-project:main Nov 15, 2025
2 checks passed
Qiaolin-Yu added a commit to Qiaolin-Yu/sglang that referenced this pull request Nov 15, 2025
Kangyan-Zhou added a commit that referenced this pull request Nov 16, 2025
)

Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
wenscarl added a commit to wenscarl/sglang that referenced this pull request Nov 18, 2025
wenscarl added a commit to wenscarl/sglang that referenced this pull request Nov 18, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

quant LLM Quantization

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants