Story
aws_ml_blog · Nov 6, 2026 · news
Source brief
SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints
aws.amazon.comNov 6, 2026
original source linked
In brief
Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so you can run a different model in each or take a right-sized fra...