A medical imaging company needs to run inference on high-resolution MRI scan payloads up to 1 GB each using a SageMaker endpoint. Processing takes up to 15 minutes per scan. Real-time response is not required and results can be retrieved later. Which endpoint type should they use?

Question

Accepted Answer

C. SageMaker Async Inference. SageMaker Async Inference is designed for large payload sizes (up to 1 GB) and long processing times. Requests are placed in an S3 queue; the endpoint processes them and writes results to S3. Notifications can be sent via SNS upon completion.

A medical imaging company needs to run inference on high-resolution MRI scan payloads up to 1 GB each using a SageMaker endpoint. Processing takes up to 15 minutes per scan. Real-time response is not required and results can be retrieved later. Which endpoint type should they use?

Related Questions

Discussion