Request Mode

Description

Request mode defining request service type that a model can be deployed as

• Synchronization Request

  One-off inference with results returned synchronously (shorter than 60s). This mode is suitable for images and small video files.

• Asynchronous Request

  One-off inference with results returned asynchronously (longer than 60s). This mode is suitable for real-time video inference and large video files.

Asynchronous Request is only available when the deployment type is Real-Time Services.

Asynchronous Request is only available only when Meta Model Source is set to OBS and AI Engine is set to Custom, or Meta Model Source is set to Container image.