Welcome to the TorchPipe Documentation!

TorchPipe is a multi-instance pipeline parallel library that provides a seamless integration between lower-level acceleration libraries (such as TensorRT and OpenCV) and RPC frameworks. It achieves strict decoupling from these libraries, offering a thread-safe function interface for the PyTorch frontend at a higher level. At the same time, it enables users to extend the backend capabilities at a lower level. TorchPipe's design ensures high service throughput while meeting latency requirements.

This document is continuously updated to reflect code changes, allowing you to:

• Quickly get started with the TorchPipe library by learning from the TorchPipe documentation.
• Become a contributor to the TorchPipe documentation by tracking updates and participating in open source development.
• Join the TorchPipe community to meet peers, engage in discussions, and exchange knowledge.

Let's begin exploring the official TorchPipe documentation.