Add AMD GPU support for HunyanOCR

[amd-asalykov]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello, 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 HunyuanOCR by integrating support for AMD GPUs. It provides clear, step-by-step guides for both installing the vLLM dependency and deploying the HunyuanOCR model, ensuring users with AMD hardware can successfully set up and utilize the system.

Highlights

• AMD GPU Support: Added comprehensive instructions for installing vLLM and deploying HunyuanOCR on systems with AMD GPUs, including specific uv pip install commands and environment variables.
• Documentation Structure: Refactored the installation and deployment sections to clearly separate instructions for NVIDIA and AMD environments, improving clarity for users.

🧠 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.

Changelog

• Tencent-Hunyuan/HunyuanOCR.md
  • Introduced a new "AMD" subsection under "Installing vLLM" with specific installation commands and important notes regarding Python, ROCm, and glibc requirements.
  • Added a new "AMD" subsection under "Deploying HunyuanOCR" detailing the necessary environment variables (VLLM_USE_TRITON_FLASH_ATTN, VLLM_ROCM_USE_AITER) and vllm serve command with --trust-remote-code.
  • Organized existing NVIDIA-specific instructions into "NVIDIA" subsections for both installation and deployment for better clarity.

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

The pull request updates the Tencent-Hunyuan/HunyuanOCR.md documentation to include detailed installation and deployment instructions for AMD GPUs, alongside the existing NVIDIA instructions. This involves adding specific uv pip install commands for ROCm-compatible vLLM wheels, noting system requirements for AMD, and providing environment variables and vllm serve commands tailored for AMD deployments.