[AMD] Add 8-GPU MX35X test running DSR1-MXFP4 model for AMD CI

[hubertlu-tw]

Motivation

Add an 8-GPU MI35X test to AMD CI which uses amd/DeepSeek-R1-MXFP4-Preview with and without speculative decoding (MTP).

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

CC: @HaiShaw @saienduri

[gemini-code-assist[bot]]

Summary of Changes

Hello @hubertlu-tw, I'm Gemini Code Assist[^1]! 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 introduces a crucial new 8-GPU test suite for AMD MI35X hardware into the continuous integration system. This suite is dedicated to thoroughly evaluating the DeepSeek-R1-MXFP4-Preview model, assessing its performance and accuracy under both standard and speculative decoding conditions. The primary objective is to enhance the robustness of validation for this model on powerful AMD GPU configurations, ensuring consistent and reliable operation.

Highlights

• New 8-GPU Test Suite: A new test suite, per-commit-8-gpu-amd-mi35x, has been added to the AMD CI, specifically designed for 8-GPU MI35X configurations.
• DeepSeek-R1-MXFP4 Model Testing: The new test suite focuses on evaluating the amd/DeepSeek-R1-MXFP4-Preview model, ensuring its performance and accuracy on high-end AMD hardware.
• Speculative Decoding (MTP) Evaluation: The tests include scenarios for both standard inference and inference with speculative decoding (MTP) enabled, using the EAGLE algorithm, to assess its impact on performance and acceptance length.
• Performance and Accuracy Benchmarks: The added tests include assertions for GSM8K accuracy and batch size 1 speed, with specific thresholds to validate the model's expected behavior.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/pr-test-amd.yml

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 :thumbsup: and :thumbsdown: 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.

[^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.

[hubertlu-tw]

@saienduri could you please help set up the gpu runners?