The input tensors to the original PyTorch function are modified to have an attribute _trt, which is the TensorRT counterpart to the PyTorch tensor. The conversion function uses this _trt to add layers to the TensorRT network, and then sets the _trt attribute for relevant output tensors.
Install TensorRT on Google Colab NVIDIA TensorRT is a high performance deep learning inference platform. It includes a deep learning inference optimizer and runtime that provides low latency and high throughput for deep learning inference applications. When inferring, TensorRT-based applications perform 40 times faster than CPU-only platforms.
volksdep: volksdep is an open-source toolbox for deploying and accelerating PyTorch, Onnx and Tensorflow models with TensorRT. Tutorials, books, & examples. Practical Pytorch: Tutorials explaining different RNN models; DeepLearningForNLPInPytorch: An IPython Notebook tutorial on deep learning, with an emphasis on Natural Language Processing.