# AWS adds hardware GPU partitioning to SageMaker inference endpoints

_Published Friday, November 6, 2026 at 1:10 PM EST · AI · Latest · Tier 2 — Notable_

![AWS adds hardware GPU partitioning to SageMaker inference endpoints — Primary](https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/05/ML-22216-featured-image.png)

AWS says Amazon SageMaker Inference now lets customers divide supported GPUs into hardware-isolated partitions, allowing different models to share an accelerator with dedicated compute and GPU memory. The feature supports P4d, P5, G7 and G7e instances in seven AWS Regions.

Customers select a partition layout when creating an endpoint and assign models through inference components, which specify each model's resources. Support is limited to real-time inference component endpoints; serverless endpoints and heterogeneous instance pools are excluded.

Customers still pay for the full instance. Changing the GPU layout requires a new endpoint and traffic migration, and models sharing an instance still share host resources, including CPU and networking.

## Sources

- [Artificial Intelligence](https://aws.amazon.com/blogs/machine-learning/sagemaker-inference-now-supports-multi-instance-gpu-to-maximize-gpu-utilization-for-model-endpoints/)

---
Canonical: https://techandbusiness.org/newswire/vzD0JwI6wDR319-LH21weK
Published: 2026-11-06T18:10:35.312Z
Story chronology: 2026-11-06T18:01:00.000Z
Retrieved: 2026-11-06T23:12:16.588Z
Publisher: Tech & Business (techandbusiness.org)