Modifying a Real-Time Service

Prerequisites

The service has been deployed. The service in the Deploying state cannot be upgraded by modifying the service information.

Constraints

Improper upgrade operations will interrupt services during the upgrade.

Modifying Service Information on the Service Management Page

1. Log in to the ModelArts console and choose Model Inference > Real-Time Inference.
2. Choose More > Modify in the Operation column of the target service, modify the basic information about the service based on Procedure, and click Confirm Modification to submit the modification task.

   When some parameters are modified, the system automatically restarts the service for the modification to take effect. When you submit a service modification task, if a restart is required, a dialog box will be displayed.

Modifying the Request Timeout Interval

In the service list, choose More > Modify in the Operation column for the target service. When modifying the basic information of a real-time service, you can change the request timeout interval.

The request timeout interval is the maximum time to wait for the system to return the first token after a request is sent. If no response is received within this period, the request is automatically terminated. The valid input range is 1–1,200 seconds.

The request timeout resets every time a response is received during streaming transmission. The system's default end-to-end response timeout is 3,600 seconds. To change this value, use the proxy plug-in. For details, see ModelArts Infers Proxy.