Posted On: Sep 24, 2020

AWS has expanded the availability of Amazon EC2 Inf1 instances to Europe (Paris), Asia Pacific (Mumbai, Singapore), and South America (São Paulo). Inf1 instances are powered by AWS Inferentia chips, which AWS custom-designed to provide high performance and lowest cost machine learning inference in the cloud.  

These instances deliver up to 30% higher throughput and up to 45% lower cost per inference than the lowest cost GPU based instances and are ideal for applications such as image recognition, natural language processing, personalization and anomaly detection.  

The easiest and quickest way to get started with Inf1 instances is via Amazon SageMaker, a fully managed service for building, training, and deploy machine learning models. Developers who prefer to manage their own machine learning application development platforms, can get started by either launching Inf1 instances with AWS Deep Learning AMIs, which include the Neuron SDK, or use Inf1 instances via Amazon Elastic Kubernetes Service (EKS) or Amazon Elastic Container Service (ECS) for containerized ML applications. 

Amazon EC2 Inf1 instances are available in 4 sizes, providing up to 16 Inferentia chips, 96 vCPUs, 192GB of memory, 100 Gbps of networking bandwidth and 19 Gbps of Elastic Block Store (EBS) bandwith. These instances are purchasable On-Demand, as Reserved Instances, as Spot instances, or as part of Savings Plans. They are available in 11 regions globally, including US East (N. Virginia, Ohio), US West (Oregon), Europe (Frankfurt, Ireland, Paris), Asia Pacific (Mumbai, Singapore, Sydney, Tokyo) and South America (São Paulo). 

To get started, visit the getting started guide. To learn more visit the Amazon EC2 Inf1 instance page.