They feature up to 16 AWS Inferentia chips, high-performance machine learning inference chips designed and built by AWS. Inf1 instances are built from the ground up to support machine learning inference applications. They deliver up to 2.3x higher throughput and up to 70% lower cost per inference than comparable Amazon EC2 instances. Customers are looking for cost-effective infrastructure solutions for deploying their ML applications in production.Īmazon EC2 Inf1 instances deliver high-performance and low cost ML inference. Up to 90% of the infrastructure spend for developing and running ML applications is often on inference. Machine learning models that power AI applications are becoming increasingly complex resulting in rising underlying compute infrastructure costs. Businesses across a diverse set of industries are looking at AI-powered transformation to drive business innovation, improve customer experience and process improvements.
