Deploying TensorFlow Models on AWS Inferentia Based Inf1 Instances with Amazon SageMaker
Published on Jul 23, 2020
Amazon EC2 Inf1 instances deliver high performance and lowest cost machine learning inference in the cloud. Amazon SageMaker supports Inf1 instances to provide one-click deployment of machine learning models onto auto-scaling Inf1 instances across multiple availability zones for high redundancy. Learn more about Amazon EC2 at - https://amzn.to/2BkxHZM Subscribe: More AWS videos http://bit.ly/2O3zS75 More AWS events videos http://bit.ly/316g9t4 #AWS #AWSDemo