14 min listen
#390: High performance and the lowest cost machine learning inference in the cloud with AWS Inferentia
FromAWS Podcast
#390: High performance and the lowest cost machine learning inference in the cloud with AWS Inferentia
FromAWS Podcast
ratings:
Length:
20 minutes
Released:
Sep 6, 2020
Format:
Podcast episode
Description
AWS Inferentia is custom built by AWS to provide high performance and lowest cost machine learning inference in the cloud. Amazon EC2 Inf1 instances, powered by AWS Inferentia, provide up to 3x higher throughput and up to 40% lower cost per inference over comparable GPU-based instances. In this podcast, learn more about AWS Inferentia, Inf1 instances, and how to get started with Inf1 instances. https://aws.amazon.com/machine-learning/inferentia/
Released:
Sep 6, 2020
Format:
Podcast episode
Titles in the series (100)
AWS Podcast Episode 153: In this episode Simon speaks with Willem Sundblad… by AWS Podcast