Pr1 coro rpc core

[JasonZhang517]

Description

This is a sub-PR of coro rpc communicator. https://github.com/kvcache-ai/Mooncake/pull/795 This PR includes the core part of Coro_rpc. Header and implementation of the PR.

Type of Change

• Types
  • [ ] Bug fix
  • [ ] New feature
    • [x ] Transfer Engine
    • [ ] Mooncake Store
    • [ ] Mooncake EP
    • [ ] Integration
    • [ ] P2P Store
    • [ ] Python Wheel
  • [ ] Breaking change
  • [ ] CI/CD
  • [ ] Documentation update
  • [ ] Other

How Has This Been Tested?

Checklist

• [ x ] I have performed a self-review of my own code.
• [ ] I have updated the documentation.
• [ x ] I have added tests to prove my changes are effective.

[gemini-code-assist[bot]]

Summary of Changes

Hello @JasonZhang517, 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 integrates the foundational Coro_rpc communication core into the Mooncake Transfer Engine. It establishes a robust, high-performance RPC mechanism capable of handling both general data and specialized tensor transfers, with a focus on asynchronous operations and zero-copy data handling. The changes include a C++ implementation (CoroRPCCommunicator) and a Python-friendly wrapper (CoroRPCInterface), along with necessary build system updates and a dedicated bandwidth testing utility. This enhancement aims to significantly improve the efficiency and flexibility of inter-process communication within the system.

Highlights

• Core Coroutine RPC Implementation: Introduces CoroRPCCommunicator in C++ for efficient, asynchronous RPC communication using coroutines, supporting both data and tensor transfers.
• Python Bindings and Interface: Provides CoroRPCInterface with pybind11 to expose the C++ RPC functionalities to Python, enabling seamless integration with Python-based workflows.
• RDMA Support with TCP Fallback: The RPC system is designed to leverage RDMA for high-performance communication when available, with a robust fallback to TCP if RDMA initialization fails or is not configured.
• Asynchronous Data and Tensor Transfer: Supports asynchronous sendDataAsync and sendTensorAsync methods, allowing non-blocking operations and efficient handling of large data payloads using zero-copy attachments.
• Build System Integration: Updates CMake files to properly build the new coro_rpc_connector module, manage pybind11 dependencies (including fetching it if needed), and link required libraries.
• Bandwidth Testing Utility: Includes a new Python test script (communicator_bandwidth_test.py) to measure and report the bandwidth of the RPC communication for both server and client modes.

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.