NVIDIA announced the latest version of the TensorRT’s high-performance deep learning inference optimizer and runtime. Today we are releasing the general availability TensorRT.  TensorRT 5 supports the new Turing architecture, provides new optimizations, and INT8 APIs achieving up to 40x faster inference over CPU-only platforms. This latest version also dramatically speeds up inference of recommenders, neural

The post TensorRT 5 GA Now Available appeared first on NVIDIA Developer News Center.