NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
From the document I found that RNNv2 is deprecated. Since the document does not metion much about it (replacing rnnv2 layer with loop API), may I ask a few questions?
What is the motivation behind? Or, how will I benefit from it?
Is it expected with better performance (inference speed)?
From the document I found that RNNv2 is deprecated. Since the document does not metion much about it (replacing rnnv2 layer with loop API), may I ask a few questions?