Amazon EC2 Inf1 instances, powered by AWS Inferentia chips, are built from the ground up to provide high performance and the lowest-cost machine learning in the cloud. This session dives into the AWS Inferentia chip, Inf1 instances, and support for Inf1 in Amazon SageMaker, Amazon EKS, and Amazon ECS. This session also provides architecture-level details of hyperscale services such as Amazon Alexa that have adopted Inf1 instances to lower their inference costs. It includes a demo on getting started with Inf1 instances and scaling out deployments.
Learn more about re:Invent 2020 at bit.ly/3c4NSdY
Subscribe:
More AWS videos bit.ly/2O3zS75
More AWS events videos bit.ly/316g9t4
#AWS #AWSEvents
- AWS re:Invent 2020: Machine learning inference with Amazon EC2 Inf1 instances ( Download)
- Save up to 71% on Your Machine Learning Inference Costs Using Amazon EC2 Inf1 - AWS Online Tech Talk ( Download)
- AWS re:Invent 2020: How to choose the right instance type for ML inference ( Download)
- Amazon EC2 Inf1 Instances | Amazon Web Services ( Download)
- Amazon EC2 Inf1 instances based on AWS Inferentia ( Download)
- AWS re:Invent 2020: Selecting the right Amazon EC2 instance for your workloads ( Download)
- AWS re:Invent 2019 Launchpad | Amazon EC2 Inf1 Instances ( Download)
- AWS re:Invent 2022 - How four customers reduced ML inference costs and drove innovation (CMP226) ( Download)
- EC2 15th Anniversary: Accelerate AI/ML adoption with AWS Inferentia | AWS Events ( Download)
- Amazon Alexa adopts Amazon EC2 Inf1 instances powered by AWS Inferentia ( Download)
- AWS re:Invent 2020: Deep dive on AWS Graviton2 processor-powered EC2 instances ( Download)
- AWS re:Invent 2020: AWS infrastructure for large-scale distributed ML training ( Download)
- AWS re:Invent 2020: Proven compute for unprecedented times ( Download)
- Deploying TensorFlow Models on AWS Inferentia Based Inf1 Instances with Amazon SageMaker ( Download)
- AWS re:Invent 2019: [REPEAT 1] Deliver high performance ML inference with AWS Inferentia (CMP324-R1) ( Download)