SageMaker Inference adds NVIDIA MIG GPU partitioning
What happened
On 7 November 2026, the AWS Machine Learning Blog reported that Amazon SageMaker Inference has added GPU partitioning: based on NVIDIA Multi-Instance GPU (MIG) technology, a single physical GPU is split into up to seven hardware-isolated partitions, each able to host a different model. The report says the capability targets inference workloads, with the aim of serving multiple model endpoints from one GPU. This is currently the only report on the development, with no follow-up coverage or contradictions with earlier reporting.
Written by AI from the reports · updated 2 h ago
Timeline
Follow the reports to see the event from each side.
- AWS Machine Learning BlogSageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints
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 fraction of a newer accelerator. This post shows how two optional API fields place one model per partition, and what we measured against a whole older GPU.
Heat of this event
Not enough continuous observations yet to draw a trend.