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

Overview

ModelArts provides manual scaling and auto scaling to meet different user requirements. Only the number of instances of a single AI application can be changed.

  • Manual scaling allows you to manually change the number of instances of a single AI application.
  • Auto scaling allows you to configure scaling policies to add instances when the traffic is high, and reduce them when the traffic is low. This helps you use your resources more efficiently.
    Table 1 Comparison between manual scaling and auto scaling

    Scaling Type

    Manual Scaling

    Auto Scaling

    Method

    Manual

    Auto

    Operation

    Change the number of compute nodes.

    Configure scaling policies.

    Execution

    Executed after manual configuration

    Periodically triggered or triggered by metrics

    Result after scaling failed

    The number of instances reverts to the previous value.

    The number of instances changes to a specific value.
Parent topic: Scaling