SageMaker AI supports inline inference payloads

Amazon SageMaker has enhanced its AI Async Inference capabilities by introducing support for inline request payloads. This significant update allows users to submit inference data directly within the API request body, eliminating the previous requirement to upload data to Amazon S3. This streamlines the machine learning workflow, reducing latency and operational overhead for developers utilizing SageMaker for their AI model deployments. The change simplifies the process of invoking asynchronous inference endpoints, making it more efficient for a wide range of applications.