add visual_send_bs args

[SangChengC]

[gemini-code-assist[bot]]

Summary of Changes

Hello @SangChengC, I'm Gemini Code Assist[^1]! 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 efficiency of multimodal processing by introducing a configurable visual_send_batch_size parameter. This new setting allows for the batching of image embeddings before they are sent from the visual processing module to the language model, thereby optimizing data transfer and reducing overhead. The visual server's forwarding logic has been updated to incorporate this batching mechanism, alongside a minor adjustment in image preprocessing to streamline device handling.

Highlights

• New Configuration Argument: Introduced a new command-line argument, --visual_send_batch_size, and a corresponding field in StartArgs, to control the batch size of image embeddings sent from the visual processing module to the LLM process.
• Optimized Image Embedding Transfer: The visual server manager has been refactored to implement a new batching mechanism for sending processed image embeddings. This uses the newly introduced visual_send_batch_size to group embeddings, improving transfer efficiency.
• Image Preprocessing Adjustment: Removed the immediate transfer of image data to CUDA (.to("cuda", non_blocking=True)) during preprocessing in vision_process.py, potentially allowing for more flexible device management or deferred placement.

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 :thumbsup: and :thumbsdown: 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.

[^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.