Add NVIDIA H200 GPU support

[hamishivi]

Summary

• Add NVIDIA H200 to the GPU_SPECS dictionary in utils.py
• H200 specs: 989 TFLOPS (BF16), 141GB HBM3e memory, 4.8 TB/s memory bandwidth

UW compute uses h200, so this is needed for that.

[gemini-code-assist]

Summary of Changes

Hello @hamishivi, 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 enhances the system's hardware compatibility by integrating support for the NVIDIA H200 GPU. By adding its detailed specifications to the GPU_SPECS configuration, the system can now accurately identify and leverage the capabilities of this new hardware, which is crucial for applications that rely on precise GPU resource management and performance tuning.

Highlights

• NVIDIA H200 GPU Support: Added the NVIDIA H200 GPU to the GPU_SPECS dictionary in open_instruct/utils.py.
• GPU Specifications: Included detailed specifications for the H200, such as 989 TFLOPS (BF16), 141GB HBM3e memory, and 4.8 TB/s memory bandwidth.
• Automatic Device Recognition: The existing get_device_name function is designed to automatically recognize "h200" in device name strings, ensuring seamless integration.

🧠 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 correctly adds support for the NVIDIA H200 GPU by including its specifications in the GPU_SPECS dictionary. The change is straightforward and the values are accurate. I've included one comment regarding the dictionary's structure, which could be improved for better long-term maintainability and to prevent potential future bugs.

[gemini-code-assist]

The specs for H200 are correct. However, the current implementation of get_device_name relies on the iteration order of the GPU_SPECS dictionary to find the correct GPU. This is fragile and can lead to bugs. For example, if a device name could match multiple keys (e.g., "pro 6000" and "6000"), the first one encountered is used.

While your placement is logical, to make this more robust for the future, we should consider modifying get_device_name to find the longest matching key. This would make the dictionary order-independent and prevent future errors when new GPUs are added.