Amazon Elastic Inference

Description

Amazon Elastic Inference allows you to attach low-cost GPU-powered acceleration to Amazon EC2 and Amazon SageMaker instances to reduce the cost of running deep learning inference by up to 75%.

SLA

https://aws.amazon.com/compute/sla/

Data

User data is stored on Amazon servers under the associated AWS account and is protected under the AWS shared responsibility model as detailed here https://aws.amazon.com/compliance/shared-responsibility-model/