GLM-4.5 and GLM-4.5V

[zRzRzRzRzRzRzR]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @zRzRzRzRzRzRzR, 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 introduces comprehensive usage guides for the GLM-4.5 and GLM-4.5V models, detailing how to run them efficiently with vLLM using FP8 and BF16 precision. It also updates the .gitignore and README.md to reflect these new additions.

Highlights

• New GLM Model Guides: Added GLM/GLM-4.5.md and GLM/GLM-4.5V.md providing detailed instructions for installing vLLM, running the models with FP8/BF16, configuring parallelization (tensor-parallel and data-parallel), and benchmarking.
• FP8/BF16 Optimization: The guides emphasize using FP8 for cost efficiency due to minimal accuracy loss, while also providing options for BF16.
• vLLM Configuration: Instructions include setting --max-model-len, --max-num-batched-tokens, and --gpu-memory-utilization for optimal performance and memory management.
• Benchmarking Recipes: Comprehensive benchmarking configurations are provided, allowing users to test different workloads (prompt-heavy, decode-heavy, balanced) and batch sizes.
• Repository Maintenance: The .gitignore file is updated to exclude venv and .idea directories, and the README.md is modified to include links to the new GLM model guides.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 new recipe documents for running GLM-4.5 and GLM-4.5V models with vLLM. The changes include adding .gitignore entries, creating two new markdown files with usage guides, and updating the main README.md to link to them.

My review focuses on the new documentation. I've found a few issues that could confuse users:

• In GLM-4.5.md, there's a contradiction between a comment and a command regarding the number of GPUs.
• Both new guides use a non-standard vllm bench serve command for benchmarking, which needs clarification.

Overall, this is a great addition, and with these small corrections, the guides will be very helpful for the community.