Back to news

AI · Article

AWS Adds NVIDIA GPU Partitioning to SageMaker Inference Endpoints to Cut Costs

Unite.AI ·

At a glance

AWS now lets a single GPU be split into several pieces on SageMaker real-time endpoints, so multiple models can share it. This uses resources more efficiently than giving an entire GPU to one model. However, it does not benefit every workload.

Key points

Why it matters

When serving AI models, GPU costs could drop significantly, which may help companies run AI more cheaply.

Original source

AWS, SageMaker 추론 엔드포인트에 NVIDIA GPU 분할 기능 추가

Unite.AI · Nov 7, 03:23 KST

Read on Unite.AI ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to Unite.AI.

Amazon Web Services · Ranking and more news