Delivery and Deployments Overview

​

Introduction

The Applications and delivery section of Edge Infrastructure Services is where you manage the full deployment lifecycle for edge applications. From this area, you deploy application instances to individual nodes or to a fleet, automate rollouts using Application Profiles, manage running applications, and monitor deployment activity.

​

Prerequisites

• You have the SysManager or SysAdmin role in your enterprise. See Manage Roles.
• At least one node onboarded to Edge Infrastructure Services.
• At least one application image added to Build and Library.

​

How It Works

Every application that runs on a node starts as an application image in your Build and Library catalog. When you deploy an image to a node, Edge Infrastructure Services creates an application instance on that node. You can deploy instances one at a time or in bulk across multiple nodes. For fleets that require consistent application configuration across many nodes, Application Profiles let you define a deployment specification once and apply it automatically. When a node joins a project or its profile assignment changes, Edge Infrastructure Services applies the matching profile and deploys or updates the configured applications without further manual steps. This is the recommended approach for zero-touch deployment scenarios where new nodes should receive applications automatically. The deployment lifecycle for an application instance moves through several states: Downloading (the image is being fetched), Starting, Running, and Stopped. You can start, stop, restart, and delete instances from the application operations controls.

​

Key Deployment Workflows

Deploy a single application instance. Deploy one application image to a specific node. Use this for targeted rollouts, testing, or one-off deployments. See Deploy an Application Instance. Automate deployment with Application Profiles. Define a profile that specifies which applications deploy to nodes in a project, and Edge Infrastructure Services applies it automatically. This replaces manual per-node deployment for standard fleet configurations. See Automate Deployments with Application Profiles. Deploy to a fleet. Roll out an AI application across multiple nodes in a project simultaneously. See Deploy AI Applications to a Fleet. Submit an AI model deployment request. Deploy an AI model to a Kubernetes cluster or cluster group through a GitOps-based approval pipeline. Each request routes through a pull request review before the model is deployed. See Submit Model Deployment Requests. Docker Compose deployments. Run multi-container applications using the Compose Runtime. See Deploy the Compose Runtime Application.

​

Next Steps