Amazon SageMaker is a fully managed service that provides every developer and data scientist with the ability to build, train, and deploy machine learning (ML) models quickly. To deploy ML models for real-time predictions, Amazon SageMaker provides you with a large selection of
AWS compute instances, so you can find the right cost to performance ratio depending on your requirements. One such instance type is
Amazon Inf1, powered by
AWS Inferentia, a custom chip built from the ground up by AWS to accelerate ML inference workloads. Amazon ml.Inf1 instances were available in Amazon SageMaker in the US East (N. Virginia) and US West (Oregon) regions. Starting today, Amazon ml.Inf1 instances are available on Amazon SageMaker in 14 additional AWS regions worldwide.
Source:: Amazon AWS