Skip to content
Hot storiesContinuously updated

SageMaker推理支持NVIDIA MIG硬件级GPU分区

1 reports1 reporting sourcesUpdated 8 hours ago

Start here

AI overview

2026年11月7日，AWS 机器学习宣布 Amazon SageMaker Inference 正式支持基于 NVIDIA MIG 的 GPU 硬件级分区。根据官方发布的内容，该功能允许用户在托管端点上操作，将单张物理 GPU 划分为最多 7 个相互独立的硬件级分区，并能够在各个分区中分别部署不同的模型。

AI-generated from reports · Updated 8 hours ago

Latest developmentsNov 7 02:01
Amazon SageMaker Inference 宣布支持基于 NVIDIA MIG 的硬件级 GPU 分区。

Report timeline

Follow the reports to see different sides of the story.

Nov 7
  1. AWS 机器学习Selected
    Amazon SageMaker Inference Supports NVIDIA MIG Hardware-Level GPU Partitioning

    Amazon SageMaker Inference announced support for hardware-level GPU partitioning powered by NVIDIA MIG, enabling users to divide a single physical GPU into up to seven isolated instances on managed endpoints to deploy different models.

Story heat trend

Current heat 8·Comparable peak 10（Nov 7 03:00）·Comparable change, last 24 hours–

02.557.510Nov7Nov7Nov7Nov7

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.