New Setup Tool To Get Started Quickly with Amazon Elastic Inference

We are excited to announce a new python script that makes it easy to get started with Amazon Elastic Inference.

Amazon Elastic Inference (EI) 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%. Amazon EI supports TensorFlow, Apache MXNet, and ONNX models, with more frameworks coming soon. Currently, Amazon EI is offered in four regions US East, US West, EU, and Asia Pacific.

If you are using Amazon EI for the first time, setting up your environment to launch instances to Amazon EI can take time. You'll need to setup a number of dependencies including AWS PrivateLink VPC Endpoints, AWS IAM policies, and security group rules before you can use Amazon EI accelerators. The Amazon EI python script makes it easy to get started by creating the necessary resources that will help you launch Amazon EI accelerators in minutes. You can download the amazonei_setup.py script from GitHub to your local machine and run it from your terminal using following command:

$ python amazonei_setup.py

The script will ensure that all settings are correctly configured and instance is launched with requisite permissions to use Amazon EI.

For more information on how to use the Amazon EI python script, please see Launch EI accelerators in minutes with the Amazon Elastic Inference setup tool for EC2.