In this webinar, we demonstrate how to install and configure Kubernetes on Jetson Mate to build a 4-node cluster. With the cloud native infrastructure in place, we will then configure NVIDIA Triton Inference Server in a scalable and highly available mode. Finally, you will learn how to deploy computer vision and conversational AI models to perform inference at scale at the edge powered by Jetson Mate, Kubernetes, and NVIDIA Triton Inference Server.
WACOCA: People, Life, Style.