Описание тега tensorrt
NoneQuestions pertaining to NVIDIA's TensorRT system, used for Deep Learning Inference Optimization on GPUs
TensorRT is a system provided by NVIDIA to optimize a trained Deep Learning model, produced from one of a variety of different training frameworks, for optimized inference execution on GPUs. TensorRT can optimize both the latency of execution, as well as the throughput (inferences/sec) of a trained model.