Achieve high-performance and cost-effective model deployment

High-performance and cost-effective techniques, including real-time, asynchronous, and batch, are needed to scale model deployments to maximize your ML investments. In this session, learn the different inference options available in Amazon SageMaker, such as multi-container endpoints, inference pipelines, and multi-model endpoints as well as frameworks such as TensorFlow and PyTorch, Python-based backend servers, and C++/Go-based backend servers. Learn how to pick the best inference option for your ML use case so you can scale to thousands of models across your business.

Achieve high-performance and cost-effective model deployment

Opening Keynote: Accelerate innovation with ML

Rethink possible: AI/ML innovation stories

Remove unnecessary onboarding friction with real-time fraud detection

Elevate customer experiences with AWS Contact Center Intelligence

Build unique user experiences through personalization

Extract data and insights from your documents

Adding identity verification to your application

Create real-time personalized user experiences faster at scale

Find accurate information faster with intelligent search

Generate ML predictions without writing any code

Prepare data for ML with ease, speed, and accuracy

Amazon SageMaker: Train models with tens or hundreds of billions of parameters

Use Amazon SageMaker to build high-quality ML models faster

Implementing MLOps practices with Amazon SageMaker

Streamline content moderation workflows with AI/ML

Three ways ML can transform your developer operations

Choosing the right ML instances for your training and inference deployments

Build custom deep learning environments with AWS Deep Learning Containers

ML at the edge with Amazon SageMaker

DJL: An open-source library to build and deploy deep learning in Java