Getting Started with NVIDIA Torch-TensorRT

Torch-TensorRT is an integration for PyTorch that leverages inference optimizations of NVIDIA TensorRT on NVIDIA GPUs. With just one line of code, it provides a simple API that gives up to 6x performance speedup on NVIDIA GPUs. The integration also offers a fallback to native PyTorch when segments of the model aren't supported by TensorRT. This video will help you get started with Torch-TensorRT.