NVIDIA Fleet Command — a cloud service for deploying, managing and scaling AI applications at the edge — today introduced new features that enhance the seamless management of edge AI deployments around the world.
With the scale of edge AI deployments, organizations can have up to thousands of independent edge locations that must be managed by IT teams — sometimes in far-flung locations like oil rigs, weather gauges, distributed retail stores or industrial facilities.
NVIDIA Fleet Command offers a simple, managed platform for container orchestration that makes it easy to provision and deploy AI applications and systems at thousands of distributed environments, all from a single cloud-based console.
But deployment is just the first step in managing AI applications at the edge. Optimizing these applications is a continuous process that involves applying patches, deploying new applications and rebooting edge systems.
To make these workflows seamless in a managed environment, Fleet Command now offers advanced remote management, multi-instance GPU provisioning and additional integrations with tools from industry collaborators.
Advanced Remote Management
IT administrators now can access systems and applications with sophisticated security features. Remote management on Fleet Command offers access controls and timed sessions, eliminating vulnerabilities that come with traditional VPN connections. Administrators can securely monitor activity and troubleshoot issues at remote edge locations from the comfort of their offices.
Edge environments are extremely dynamic — which means administrators responsible for edge AI deployments need to be highly nimble to keep up with rapid changes and ensure little deployment downtime. This makes remote management a critical feature for every edge AI deployment.
Check out a complete walkthrough of the new remote management features and how they can be used to help administrators maintain and optimize even the largest edge deployments.
Multi-Instance GPU Provisioning
Multi-Instance GPU, or MIG, partitions an NVIDIA GPU into several independent instances. MIG is now available on Fleet Command, letting administrators easily assign applications to each instance from the Fleet Command user interface. By allowing organizations to run multiple AI applications on the same GPU, MIG lets organizations right-size their deployments and get the most out of their edge infrastructure.
Learn more about how administrators can use MIG in Fleet Command to better optimize edge resources to scale new workloads with ease.
Working Together to Expand AI
New Fleet Command collaborations are also helping enterprises create a seamless workflow, from development to deployment at the edge.
Domino Data Lab provides an enterprise MLOps platform that allows data scientists to collaboratively develop, deploy and monitor AI models at scale using their preferred tools, languages and infrastructure. The Domino platform’s integration with Fleet Command gives data science and IT teams a single system of record and consistent workflow with which to manage models deployed to edge locations.
Milestone Systems, a leading provider of video management systems and NVIDIA Metropolis elite partner, created AI Bridge, an application programming interface gateway that makes it easy to give AI applications access to consolidated video feeds from dozens of camera streams. Now integrated with Fleet Command, Milestone AI Bridge can be easily deployed to any edge location.
IronYun, an NVIDIA Metropolis elite partner and top-tier member of the NVIDIA Partner Network, with its Vaidio AI platform applies advanced AI, evolved over multiple generations, to security, safety and operational applications worldwide. Vaidio is an open platform that works with any IP camera and integrates out of the box with dozens of market-leading video management systems. Vaidio can be deployed on premises, in the cloud, at the edge and in hybrid environments. Vaidio scales from one to thousands of cameras. Fleet Command makes it easier to deploy Vaidio AI at the edge and simplifies management at scale.
With these new features and expanded collaborations, Fleet Command ensures that the day-to-day process of maintaining, monitoring and optimizing edge deployments is straightforward and painless.
Test Drive Fleet Command
To try these features on Fleet Command, check out NVIDIA LaunchPad for free.
LaunchPad provides immediate, short-term access to a Fleet Command instance to easily deploy and monitor real applications on real servers using hands-on labs that walk users through the entire process — from infrastructure provisioning and optimization to application deployment for use cases like deploying vision AI at the edge of a network.