Introduction

NVIDIA Fleet Command brings secure edge AI to enterprises of any size. Transform NVIDIA-Certified Systems into secure edge appliances and connect them to the cloud in minutes. From the cloud, users can deploy and manage applications from the NGC Catalog or NGC Private Registry, update system software over the air, and manage systems remotely with nothing but a browser and internet connection.

This user guide details the process from getting started to deploying applications at the edge using NVIDIA Fleet Command. Readers will learn about the necessary prerequisites to get started, configure edge systems at the edge, and set up and deploy applications across the entire edge infrastructure. Also, this guide provides an end-to-end application deployment example for users to follow and ensure they have correctly set up Fleet Command.

Note

This user guide assumes the user is already set up with an NGC account.

Fleet Command Terms and Concepts

  • Application: An application compatible with Fleet Command designed to run on an edge location.

  • NGC Catalog: A curated set of GPU-optimized software maintained by NVIDIA and accessible to the general public.

  • Deployment: A deployment consists of an application running on an edge location.

  • Location: A location represents a real-world edge location where your physical systems are installed.

  • Org: The enterprise organization with its own registry space. Users are assigned (or belong) to an org.

  • NGC Private Registry: The NGC private registry provides you with a secure space to store and share custom containers, models, resources, and Helm charts within your enterprise.

  • System: A system represents those physical edge systems within a location.

  • Team: A sub-unit within an organization with its own registry space. Only members of the same team have access to that team’s registry space.

  • Users: Anyone with a Fleet Command account. Users are assigned to an org.