SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints
· AI-assisted summary · reviewed by Reinventy Solutions Corp.
Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU, dividing one GPU into hardware-isolated partitions for running different models or right-sized accelerator fractions.

Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU, dividing one GPU into hardware-isolated partitions for multiple model endpoints.
