[AMD] Fix CI - unit-test-backend-1-gpu-amd-mi35x and unit-test-backend-2-gpu-amd, stage-b-test-small-1-gpu-amd

[yctseng0211]

Motivation

Fix the ci failures:
https://github.com/sgl-project/sglang/actions/runs/20802527047/job/59750995718?pr=16529
https://github.com/sgl-project/sglang/actions/runs/20802527047/job/59750995708?pr=16529
https://github.com/sgl-project/sglang/actions/runs/20802527047/job/59750995712?pr=16529
https://github.com/sgl-project/sglang/actions/runs/20809567649/job/59771596544

Modifications

Accuracy Tests

AMD CI all green : https://github.com/sgl-project/sglang/actions/runs/20811570421?pr=16675

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.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments (/tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci) or contact authorized users to do so.
4. After green CI and required approvals, ask Merge Oncalls to merge.

[gemini-code-assist]

Summary of Changes

Hello @yctseng0211, 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 aims to resolve a Continuous Integration (CI) failure, specifically targeting AMD environments. It achieves this by adjusting the configuration passed to a Triton-based fused Mixture-of-Experts (MoE) kernel, ensuring compatibility and preventing errors during execution.

Highlights

• CI Fix for AMD: This pull request addresses a Continuous Integration (CI) failure, likely specific to AMD environments, by modifying the configuration passed to a Triton fused Mixture-of-Experts (MoE) kernel.
• Triton Kernel Configuration Adjustment: The config dictionary for the fused_moe_kernel now explicitly removes the "swap_ab" parameter before execution, 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 addresses a potential TypeError in the invoke_fused_moe_kernel function. The fused_moe_kernel is called with swap_ab as an explicit keyword argument, but the config dictionary, also passed as keyword arguments, could potentially contain the same key. This would cause a runtime error due to a duplicate argument. The fix correctly removes the swap_ab key from a copy of the config dictionary before the kernel invocation. This is a clean and safe solution that improves the robustness of the kernel invocation.

[Kangyan-Zhou]

Need to fix https://github.com/sgl-project/sglang/actions/runs/20808440544

[Kangyan-Zhou]

You can always install pre-commit in this repo so that you don't need to fix lint after push