Save up to 71% on Your Machine Learning Inference Costs Using Amazon EC2 Inf1 - AWS Online Tech Talk

Deploying machine learning models in production can account for 90% of the costs of running ML infrastructure. Amazon EC2 Inf1 instances powered by AWS Inferentia, are purpose built to deliver the lowest cost inference in the cloud. Attend this tech talk to learn how you can save up to 70% of your ML inference costs and get 2.3X better performance when compared to current generation GPU-based instances. We will show how you can easily migrate your existing models onto Inf1 instances and the performance enhancements you will see for popular ML models. We will wrap with customer examples on how they are deploying their models on to Inf1 instances using Amazon SageMaker, at scale and with minimal code changes. Learning Objectives: *Learn how to get started with Inf1 instances *Learn about ease of migration to Inf1 instances *Learn about enhanced performance and increased cost savings for popular ML models ***To learn more about the services featured in this talk, please visit: https://aws.amazon.com/ec2/instance-types/inf1/ Subscribe to AWS Online Tech Talks On AWS: https://www.youtube.com/@AWSOnlineTechTalks?sub_confirmation=1 Follow Amazon Web Services: Official Website: https://aws.amazon.com/what-is-aws Twitch: https://twitch.tv/aws Twitter: https://twitter.com/awsdevelopers Facebook: https://facebook.com/amazonwebservices Instagram: https://instagram.com/amazonwebservices ☁️ AWS Online Tech Talks cover a wide range of topics and expertise levels through technical deep dives, demos, customer examples, and live Q&A with AWS experts. Builders can choose from bite-sized 15-minute sessions, insightful fireside chats, immersive virtual workshops, interactive office hours, or watch on-demand tech talks at your own pace. Join us to fuel your learning journey with AWS. #AWS