Equimonet · Source-linked explainer

Amazon SageMaker Batch Transform adds GPU‑rich G6e instance support

SageMaker’s offline inference service now runs on Amazon EC2 G6e instances, which pack up to eight NVIDIA L40S Tensor Core GPUs and third‑generation AMD EPYC CPUs. The update targets large language and diffusion models and is available in several AWS regions.

By Equimonet Research Desk · Published 2026-09-07

Evidence frame

Based on the dated Amazon Web Services announcement linked below. Company statements are not independently verified outcomes. General information, no recommendation.

Primary sources

  1. Amazon Web Services — Amazon SageMaker AI Batch Transform now supports G6e instances Issued 2026-09-04T08:00:00.000Z

General market information only. No investment recommendation.