Amazon SageMaker expanded its AI Batch Transform service by supporting Amazon EC2 G6e instances, which feature up to eight NVIDIA L40S Tensor Core GPUs and third-generation AMD EPYC processors. Batch Transform is suited for offline inference on large datasets stored in S3, including workloads involving large language and diffusion models that generate complex media outputs.
The introduction of G6e instances improves performance for GPU-intensive workloads without requiring persistent inference endpoints. Support is currently available in select AWS regions including US East, US West, and Asia Pacific (Mumbai and Hyderabad). This enables customers to leverage enhanced compute power for scalable offline model predictions through SageMaker Batch Transform APIs and interfaces.
Source & further reading
Amazon SageMaker AI Batch Transform now supports G6e instances ↗Source published 2026-09-04. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.