Update Qwen3-Coder-480B-A35B.md for AMD GPU

[haic0]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @haic0, 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 significantly enhances the documentation for the Qwen3-Coder-480B-A35B-Instruct model by integrating comprehensive instructions for its deployment and performance evaluation on AMD MI300X GPUs. The added guide covers the entire process from Docker environment preparation to running benchmarks, ensuring users can effectively leverage AMD hardware for this model.

Highlights

• AMD GPU Support Documentation: Added a new section to the Qwen3-Coder-480B-A35B.md file detailing the steps required to install and run the Qwen3-Coder-480B-A35B-Instruct models on AMD MI300X GPUs.
• Docker Environment Setup: Provided instructions for pulling the rocm/vllm-dev:nightly Docker image and launching it with the necessary privileges and device mappings for AMD GPUs.
• vLLM Server Configuration: Included a sample command for starting the vLLM online serving with specific environment variables and parameters tailored for the Qwen3-Coder model, including SAFETENSORS_FAST_GPU=1 and NCCL_MIN_NCHANNELS=112.
• Benchmarking Instructions: Detailed steps for running a benchmark script inside the Docker container using vllm bench serve with parameters like random-input-len, random-output-len, and request-rate.

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 a helpful guide for running the Qwen3-Coder model on AMD GPUs. The instructions are clear and cover the necessary steps from environment setup to benchmarking. My review focuses on improving the formatting and readability of the new documentation, including suggestions for breaking up long commands, ensuring consistent terminology, and removing excessive whitespace. These changes will make the guide easier for users to follow.

[gemini-code-assist]

There are three consecutive blank lines here. To improve formatting and make the document more compact, please reduce this to a single blank line by removing two of them.

[gemini-code-assist]

This blank line within the shell command block is unnecessary and can be removed to make the code block more compact.

[gemini-code-assist]

There are multiple blank lines here. Please remove the extra one to improve formatting.

[gemini-code-assist]

The model name is quoted here, but it's not quoted in the vllm serve command in Step 3. For consistency, it's better to remove the quotes as they are not necessary in this case.

Suggested change

	--model "Qwen/Qwen3-Coder-480B-A35B-Instruct" \
	--model Qwen/Qwen3-Coder-480B-A35B-Instruct \

[gemini-code-assist]

These extra blank lines at the end of the document can be removed.

[gemini-code-assist]

This line contains trailing whitespace, which should be removed.