NVIDIA Fleet Command

NVIDIA Fleet Command is a hybrid-cloud platform for securely and remotely deploying, managing, and scaling AI across dozens or up to thousands of servers or edge devices. It is currently in early access, see the link to apply. Jarvis can be deployed into a Fleet Command environment using the Jarvis Helm Chart located in NGC.

Application Setup

  1. Setup the application within Fleet Command by selecting APPLICATIONS from the Fleet Command UI.

  2. Select Add Application from the top left menu.

  3. Fill out the modal popup:

  1. Display Name: Jarvis Speech

  2. Description: Jarvis Fleet Command deployment

  3. Helm Name: jarvis-api

  4. Helm version: |VersionNum|

  5. Helm URL: https://helm.ngc.nvidia.com/|NgcOrgTeam|

  1. select Add.

Deployment Setup

  1. Create the deployment within Fleet Command by selecting Deployments > Create Deployment from the UI.

  2. Fill out the Name, Display Name, and select the location to deploy.

  3. Select from the application drop-down box the name from “Display Name” from the Application Setup. For example, “Jarvis Speech”.

  4. Copy and paste the following into the “Application Configuration” dialog box (execute the shell snippet next to password to create your encoded password). This will deploy all three services with the default models:

ngcCredentials:
  registry: nvcr.io
  username: $oauthtoken
  password: $(echo -n $NGC_API_KEY | base64 -w0)
  email: your@email.com
modelRepoGenerator:
  modelDeployKey: $(echo -n tlt_encode | base64 -w0)

to install just one type of service add the following and adjust as needed.

jarvis:
  speechServices:
    asr: true
    tts: false
    nlp: false

  1. Check the box I understand…

  2. Click the Deploy button in the top right of the page. Based on the models and services to be deployed, the installation can take more than 60 minutes.