SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints

新聞摘要
Amazon SageMaker Inference now supports GPU partitioning with NVIDIA Multi-Instance GPU (MIG), which divides one GPU into hardware-isolated partitions so
此則由公開來源收錄,摘要不代表已獨立查證。請核對原文日期、數字與事件進展。
在研究介面查看相關線索 →