This document described how to use provides a detailed description of the MXNet-TensorRT runtime integration to accelerate model inference. feature. This document covers advanced techniques, contains a roadmap reflecting the current state of the feature and future directions, and also contains up-to-date benchmarks. If you'd like a quick overview of the feature please refer to this tutorial. For more information you may also visit the original design proposal page.
Why is TensorRT integration useful?
...