Add links to new TPU recipes

[karan]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @karan, 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 project's documentation by reorganizing the README.md to better categorize hardware-specific guides. It introduces a new section for TPU-related content and provides external links to Qwen model recipes optimized for vLLM inference on TPUs, thereby expanding the scope of supported hardware and improving guide discoverability.

Highlights

• Documentation Restructuring: The main 'Guides' section in the README.md has been renamed to 'GPU Guides' to provide clearer categorization for hardware-specific documentation.
• New TPU Guides Section: A dedicated 'TPU Guides' section has been introduced to house recipes and documentation relevant to Tensor Processing Units.
• Qwen TPU Recipes Added: Links to Qwen model recipes (Qwen3-32B, Qwen3-4B, Qwen2.5-VL) for vLLM inference on TPUs have been added under the new 'TPU Guides' section, directing users to an external AI-Hypercomputer/tpu-recipes repository.

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 introduces a new 'TPU Guides' section in the main README file and renames the existing 'Guides' section to 'GPU Guides' for better organization. The changes are clear and improve the structure of the documentation. I have one suggestion to enhance the clarity of the newly added links.

[youkaichao]

hmm you can add them inside Llama/Llama3.3-70B.md ?

[anthonsu]

The Llama3.3-70B.md file targets GPUs. The second file's title indicates its distinct focus on TPU Trillium support.

[youkaichao]

The Llama3.3-70B.md file should target at this model. TPU support should be listed in this file.

We don't want the flat directory to explode into {model} x {hardware} matrix.

[karan]

TPU recipes are maintained in a separate repo and it's a lot of easier to keep them up to date there (the repo has other frameworks and hardware supported there too).

@simon-mo thoughts in @youkaichao's proposal of moving TPU links within the model file?

[karan]

Closing in favor of #86