Event ·Official first-hand

SageMaker Inference 支持 NVIDIA MIG，可将单张 GPU 分区部署多个模型

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。

Current read

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。

7 sources39° AI heatLast updated 2026/11/6 18:01:00

Evidence

7 sources

Primary sourceAWS Machine Learning Blog

2026/11/6 18:01:00View source

Related source 1vLLM

2026/11/5 14:14:59View source

Related source 2PyTorch

2026/11/4 19:28:47View source

Related source 3IT之家

2026/11/5 01:50:15View source

Related source 4techcrunch

2026/11/5 14:00:00View source

Related source 5NVIDIA AI

2026/11/5 17:00:20View source

Related source 6rohanpaul_ai

2026/11/5 20:48:25View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story