Tools · AWS ML Blog ·

Amazon SageMaker AI Async Inference now supports inline request payloads

Amazon SageMaker AI Async Inference now supports inline request payloads

Amazon SageMaker AI Async Inference now supports inline request payloads in the InvokeEndpointAsync API. Customers can send input data directly in the request body instead of uploading it to Amazon S3 before each invocation.

Read the full story at AWS ML Blog →