SageMaker Batch Transform adds G6e GPU instances

Amazon SageMaker AI now supports EC2 G6e instances for Batch Transform jobs, AWS said. The addition lets customers use the GPU-equipped instances for offline inference on data stored in Amazon S3, including large language models and image, video and audio diffusion models. G6e instances can include up to eight NVIDIA L40S GPUs with 48 GB of memory each. Support is available in five AWS regions: Northern Virginia, Ohio, Oregon, Mumbai and Hyderabad. Batch Transform is intended for large datasets that do not require a persistent inference endpoint.