TensorRT is a software development kit (SDK) and inference optimization runtime developed by Nvidia for deploying trained deep learning and machine learning models on graphics processing units (GPUs). It can import models from frameworks such as PyTorch, TensorFlow, and ONNX, and compile them into optimized runtime engines for low-latency and high-throughput inference.
TensorRT is a software development kit (SDK) and inference optimization runtime developed by Nvidia for deploying trained deep learning and machine learning models on graphics processing units (GPUs). It can import models from frameworks such as PyTorch, TensorFlow, and ONNX, and compile them into optimized runtime engines for low-latency and high-throughput inference.
Source: Wikipedia "TensorRT" · CC BY-SA 4.0
Share this article: X · Bluesky