Amazon SageMaker Batch Transform adds support for G6e instances
Amazon SageMaker Batch Transform now supports Amazon EC2 G6e instances for offline inference. These instances, powered by NVIDIA L40S Tensor Core GPUs, deliver enhanced performance for GPU-intensive workloads such as large language models and diffusion models. This allows users to efficiently process large datasets stored in Amazon S3 for predictions without requiring a persistent endpoint. The new instance types are available in select AWS regions including US East (N. Virginia), US East (Ohio), and US West (Oregon).
Features (1) ›
- SageMaker Batch Transform supports G6e instances
Amazon SageMaker Batch Transform now supports Amazon EC2 G6e instances, enabling enhanced performance for GPU-intensive offline inference workloads. These instances utilize NVIDIA L40S Tensor Core GPUs and are suitable for large language models and diffusion models, processing datasets from Amazon S3.
https://aws.amazon.com/about-aws/whats-new/2026/09/sagemaker-batch-transform-g6e-instances/
Related releases
- AWS MCP Server adds serverless diagnostics for Lambda functions with AI agents AWS What's New ·
- AWS guide to CloudTrail investigation for multi-stage Bedrock attacks AWS Security Blog ·
- Amazon S3 Adds PrivateLink Support for FIPS Endpoints AWS What's New ·
- SageMaker Unified Studio CI/CD adds notebook promotion and AI-assisted manifest generation AWS What's New ·
- Amazon EMR Trino Now Integrates with S3 Tables via Iceberg REST Endpoint AWS Big Data Blog ·
- AWS Tools for PowerShell Introduces S3 PowerShell Drive AWS Developer Tools Blog ·