Deployment Example

This section shows how to deploy an application to an edge system.

This deployment uses the application DeepStream - Intelligent Video Analytics Demo. The application is hosted in the NGC Accelerated Software catalog for this exercise. This Intelligent Video Analytics demo showcases Fleet Command’s management capabilities and the capabilities of GPU-enabled systems for real-time AI-based video and image understanding and multi-sensor processing. This demo combines the Deepstream SDK with a sample model and video source. A media server provides a web interface for viewing the analyzed video.

The application is packaged as a single Helm chart that you can easily deploy with Fleet Command. For more information, refer to the DeepStream - Intelligent Video Analytics Demo.

Before you begin, ensure that you performed the following prerequisites:

• Created a Location in Fleet Command.

• Successfully added a System to the location.

• The system is paired with Fleet Command and has a status of online.

To begin, find the application in the NGC Accelerated Software section.

1. Navigate to the NGC Accelerated Software Section and search for the application.

   

   

   

   Note

   Confirm you are searching for the application Helm chart and not the container, model, or collections.

   
   

2. After you have found the application, click on the application name for additional information.

   

   
   

3. Here you will find the required information to add this application into Fleet Command. Be sure to record the application Name, Version, and Helm Chart URL.

   

   
   

4. When you click on the Fetch Version, the helm fetch command is copied and looks like below. Extract the Helm fields from the fetch URL as per below.

   

   • Helm Chart Name: video-analytics-demo

   • Helm Chart Version: 0.1.7

   • Helm Repo URL: https://helm.ngc.nvidia.com/nvidia

5. After you have the information listed above, select Fleet Command > Applications and click Add Application.

   

   
   

6. Enter the Helm chart information and then click Add Application.

   

   
   

After you add the application, it appears on the Fleet Command application page.

1. Select Fleet Command > Deployments and click Create Deployment.

   

2. Enter the application information on the deployment page, select the Before Deploy checkbox, and then click Deploy.

   

Additional Configuration for Multi-Instance GPU

The following YAML shows a sample application configuration to request one 3g.20gb MIG partition.

            

            
resources:
  limits:
    nvidia.com/mig-3g.20gb: 1
        

Additional configuration might be required for MIG. Refer to Multi-Instance GPU configuration for more details.

After the application is deployed, you can access the application using the remote application access feature from Fleet Command. For more information on using this feature, refer to Remote Application Access.

• Remove the deployment and application to clean up from this demo exercise.

• Refer to the Application Developer Guide section of the documentation for help with running your own applications on Fleet Command.