Fix triton_kernels import error on some hardwares

[fzyzcjy]

Motivation

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.

[gemini-code-assist]

Summary of Changes

Hello @fzyzcjy, 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 implements a fix for an import error related to triton_kernels that occurred on certain hardware setups. The core change involves refining the logic for conditionally importing these kernels, making the decision dependent on an explicit configuration parameter. This enhances the robustness and compatibility of the system by ensuring Triton kernels are only loaded when intended and supported by the environment.

Highlights

• Triton Kernel Import Logic: The conditional import of triton_kernels_moe has been updated to rely on the use_triton_kernels parameter passed to the constructor, rather than a potentially global or module-level has_triton_kernels flag. This change makes the import decision explicit and configurable.
• Hardware Compatibility Fix: This modification directly addresses import errors for Triton kernels that were observed on specific hardware configurations, ensuring that the system can correctly initialize and run across a wider range of environments.

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 fixes a potential import error for triton_kernels on certain hardware. The change makes the import conditional on the use_triton_kernels flag, which is the intended behavior. I have one minor suggestion to improve code style by consolidating two import statements into one, located near the modified line.

[gemini-code-assist]

While you are modifying this block, you can consolidate the two separate imports from sglang.srt.layers.moe.fused_moe_triton.triton_kernels_moe on lines 147-152 into a single statement. This improves readability and follows standard Python style (PEP 8).

from sglang.srt.layers.moe.fused_moe_triton.triton_kernels_moe import (
    triton_kernel_moe_forward as _tk_forward,
    triton_kernel_moe_with_bias_forward as _tk_with_bias_forward,
)