Amazon SageMaker AI Batch Transform now supports G6e instances
News
This article announces support for Amazon EC2 G6e instances in Amazon SageMaker AI Batch Transform for offline inference workloads.
- G6e instances powered by up to eight NVIDIA L40S Tensor Core GPUs with 48 GB memory per GPU
- Enables GPU-intensive batch predictions on S3 datasets without persistent endpoints
- Supports large language models and diffusion models for image, video, and audio generation
- Available in US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), and Asia Pacific (Hyderabad)
- Select ml.g6e instance types via AWS SDKs, AWS CLI, or CreateTransformJob API
G6e support enhances Batch Transform capabilities for large-scale offline inference workloads requiring high GPU performance.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.