add doc for #14386

[liusy58]

Motivation

Add docs for #14386

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.
• Work with maintainers to merge your PR. See the PR Merge Process

[gemini-code-assist]

Summary of Changes

Hello @liusy58, 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 primarily focuses on enhancing the documentation and clarifying the implementation of a multi-modal feature hashing optimization. It introduces and documents the SGLANG_MM_BUFFER_SIZE_MB environment variable, which allows users to configure a GPU buffer for faster hash computations while efficiently managing GPU memory. Additionally, explanatory comments have been added to the relevant Python file to provide better insight into this optimization's functionality.

Highlights

• Documentation Update: Added documentation for a new environment variable, SGLANG_MM_BUFFER_SIZE_MB, which controls the size of a preallocated GPU buffer for multi-modal feature hashing optimization.
• Multi-modal Feature Hashing Optimization: Introduced an optimization where feature tensors are temporarily moved to the GPU for faster hash computation when SGLANG_MM_BUFFER_SIZE_MB is set to a positive value, helping to avoid out-of-memory issues.
• Code Clarity: Added inline comments in schedule_batch.py to explain the mechanism and benefits of the multi-modal feature hashing optimization.

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 documentation and a code comment for a new feature that optimizes multi-modal feature hashing by using a pre-allocated GPU buffer. The changes are clear and help explain the functionality of the SGLANG_MM_BUFFER_SIZE_MB environment variable. My review includes a suggestion to improve the readability of the new documentation.

[gemini-code-assist]

The description for SGLANG_MM_BUFFER_SIZE_MB is quite long, which can make the table cell difficult to read. Breaking the description into multiple lines using <br> tags would improve readability.

Suggested change

	| `SGLANG_MM_BUFFER_SIZE_MB` | Size of preallocated GPU buffer (in MB) for multi-modal feature hashing optimization. When set to a positive value, temporarily moves features to GPU for faster hash computation, then moves them back to CPU to save GPU memory. Larger features benefit more from GPU hashing. Set to `0` to disable. | `0` |
	| `SGLANG_MM_BUFFER_SIZE_MB` | Size of preallocated GPU buffer (in MB) for multi-modal feature hashing optimization.<br>When set to a positive value, it temporarily moves features to GPU for faster hash computation, then moves them back to CPU to save GPU memory.<br>Larger features benefit more from GPU hashing.<br>Set to `0` to disable. | `0` |

[yhyang201]

/tag-and-rerun-ci