class Aws::SageMaker::Types::AsyncInferenceConfig

Specifies configuration for how an endpoint performs asynchronous inference.

@note When making an API call, you may pass AsyncInferenceConfig

data as a hash:

    {
      client_config: {
        max_concurrent_invocations_per_instance: 1,
      },
      output_config: { # required
        kms_key_id: "KmsKeyId",
        s3_output_path: "DestinationS3Uri", # required
        notification_config: {
          success_topic: "SnsTopicArn",
          error_topic: "SnsTopicArn",
        },
      },
    }

@!attribute [rw] client_config

Configures the behavior of the client used by Amazon SageMaker to
interact with the model container during asynchronous inference.
@return [Types::AsyncInferenceClientConfig]

@!attribute [rw] output_config

Specifies the configuration for asynchronous inference invocation
outputs.
@return [Types::AsyncInferenceOutputConfig]

@see docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/AsyncInferenceConfig AWS API Documentation

Constants

SENSITIVE