[AMD] CI - enable test case for amd ci : triton_attention_kernels , torch_compile_moe

[yctseng0211]

Motivation

Add :
test/registered/attention/test_triton_attention_kernels.py : https://github.com/sgl-project/sglang/actions/runs/20906743511/job/60062078516?pr=16559#step:6:13504
test/registered/moe/test_torch_compile_moe.py : https://github.com/sgl-project/sglang/actions/runs/20906743511/job/60062078523?pr=16559#logs

Modifications

test/registered/attention/test_triton_attention_kernels.py - enable
test/registered/moe/test_torch_compile_moe.py - enable
test/registered/lora/test_lora_qwen3.py - add the disabled message
test/srt/test_deepseek_r1_mxfp4_8gpu.py - adjust the server launch timout (1000 -> 1200) for the timeout error : TimeoutError: Server failed to start within the timeout period, see unit-test-backend-8-gpu-amd-mi35x (linux-mi35x-gpu-8)

Accuracy Tests

https://github.com/sgl-project/sglang/actions/runs/20906743511/job/60062078516?pr=16559#step:6:13504
https://github.com/sgl-project/sglang/actions/runs/20906743511/job/60062078523?pr=16559#logs

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 expands the project's Continuous Integration (CI) coverage by integrating two key test suites into the AMD CI pipeline. By registering the LoRA Qwen3 and Torch Compile MoE tests for execution on AMD hardware, this change aims to enhance the overall stability and compatibility of the project across different GPU architectures, ensuring that these critical functionalities are validated on AMD platforms.

Highlights

• AMD CI Integration: Two existing test suites, test_lora_qwen3.py and test_torch_compile_moe.py, have been updated to include registration for the AMD Continuous Integration (CI) pipeline.
• Test Registration Details: The test_lora_qwen3 test is registered with an estimated time of 97 seconds, and the test_torch_compile_moe test with 210 seconds, both targeting the 'stage-b-test-small-1-gpu' suite on AMD CI.

🧠 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 adds AMD CI test registrations for test_lora_qwen3 and test_torch_compile_moe. The changes are straightforward and look correct. My main feedback is about the pull request title, which states 'add disabled test', while the added tests are enabled. This could be misleading and should probably be updated to reflect the actual changes. I've also left a couple of suggestions to improve maintainability by using constants for duplicated values in the test registrations.

[gemini-code-assist]

To improve maintainability, consider defining a constant for the shared est_time value. This will make it easier to update in the future if needed.

For example:

EST_TIME = 97
register_cuda_ci(est_time=EST_TIME, suite="nightly-1-gpu", nightly=True)
register_amd_ci(est_time=EST_TIME, suite="stage-b-test-small-1-gpu")

[gemini-code-assist]

To improve maintainability and reduce redundancy, consider defining constants for the shared est_time and suite values. This will make it easier to update them in the future.

For example:

EST_TIME = 210
SUITE = "stage-b-test-small-1-gpu"

register_cuda_ci(est_time=EST_TIME, suite=SUITE)
register_amd_ci(est_time=EST_TIME, suite=SUITE)