SageMaker Inference 支持 NVIDIA MIG，可将单张 GPU 分区部署多个模型
SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints
AWS 给 SageMaker 加了 GPU 分区功能，一张卡能跑多个模型，小模型部署终于不用浪费整张卡了。
AWS 宣布 Amazon SageMaker Inference 支持 NVIDIA Multi-Instance GPU（MIG）技术，能把一张 GPU 划分成多个硬件隔离的分区，每个分区可以独立运行一个模型。通过新增的两个可选 API 字段即可实现按分区部署模型。官方实测对比了分区方案与整张旧款 GPU 的使用效果，用于提升小型模型的 GPU 利用率。
SageMaker 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.