A company has trained a SageMaker model and needs to run inference on 10 million records stored in Amazon S3. They do not need a persistent endpoint; they simply need the inference results written back to S3. Which SageMaker inference option is most appropriate?

Question

Accepted Answer

B. SageMaker Batch Transform. SageMaker Batch Transform is designed for running inference on large datasets from S3 and writing results back to S3 without maintaining a persistent endpoint. It is cost-effective for one-time or scheduled offline inference.

A company has trained a SageMaker model and needs to run inference on 10 million records stored in Amazon S3. They do not need a persistent endpoint; they simply need the inference results written back to S3. Which SageMaker inference option is most appropriate?

Related Questions

Discussion