Amazon SageMaker customers can now select ml.G4dn instances to run Batch Transform and Processing Jobs. Amazon SageMaker Batch Transform enables you to run predictions on datasets stored in Amazon S3. It is ideal for scenarios where you are working with large batches of data and don’t need sub-second latency. Amazon SageMaker Processing enables you to run your pre- or post-processing workloads, such as feature engineering, data validation, model evaluation, and model interpretation with a fully managed experience.
Source:: Amazon AWS