SageMaker AI Batch Transform Gets Serious GPU Power with G6e Instances

Amazon SageMaker AI now supports EC2 G6e instances for batch transform jobs, letting you run GPU-intensive offline inference on massive datasets without spinning up persistent endpoints. Perfect for heavy lifters like large language models and diffusion models, G6e instances pack up to eight NVIDIA L40S GPUs with 48GB memory each—available across five regions including US East, US West, and Asia Pacific.