NVIDIA’s software library and SDK together create a scalable solution that enables customers to deploy inference and AI capabilities in the cloud, on the server, or at the edge. This software investment is aimed at accelerating customer deployment while reducing overall development costs.

These SDK investments include JetPack™ for embedded devices, DeepStream for IVA, Isaac™ for robots, TensorRT™ for inference, TAO toolkit for tuning DNN, and NVIDIA GPU Cloud for containers and AI software etc.

NVIDIA is also working closely with an extensive partner ecosystem to deploy out-of-the-box solutions that customers can use for their applications.