Help Center/ ModelArts/ Model Inference/ Deploying an AI Application as a Service/ Deploying AI Applications as Real-Time Services/ Maintaining Real-Time Services/ Scaling/ Manual Scaling
Updated on 2024-06-12 GMT+08:00
View PDF

Manual Scaling

Manual scaling allows you to manually change the number of instances of a single AI application.

Prerequisites

The service status is Running, Abnormal, or Alarm.

Procedure

  1. Log in to the ModelArts management console. In the navigation pane on the left, choose Service Deployment > Real-Time Services. The Real-Time Services page is displayed.
  2. Click the check box next to the service name to display the hidden view at the bottom of the list. (If the view is not displayed, click in the bottom right corner.)
  3. Click Resize Compute Resources in the Operation column of the target AI application version.
    Figure 1 Resize Compute Resources

  4. Set the following parameters. Other parameters cannot be modified.
    • Auto Stop: This parameter is displayed if auto stop is enabled for the service. The service will automatically stop upon the specified time. You can click Modify to change the auto stop time.
    • Resize Type: Select Manual.
    • Compute Nodes: Set the number of required compute nodes. The minimum value is 1.
  5. Click Next and then Submit. Return to the real-time service list.
Parent topic: Scaling