Enter your
email for instant access to
Mod Week AI/ML
on-demand

Opt-in to Future Emails

Yes, I'd like Amazon Web Services (AWS) to share the latest news about AWS services and related offerings with me by email, post or telephone.

You may unsubscribe from receiving AWS news and offers at any time by following the instructions in the communications received. AWS handles your information as described in the AWS Privacy Notice.

Thank you!

Error - something went wrong!

Achieve high performance and cost-effective model deployment

To maximize your ML investments, high performance and cost-effective techniques, including real-time, asynchronous, and batch, are needed to scale model deployments.

In this session, discuss the different inference options available in Amazon SageMaker such as multi-container endpoints, inference pipelines, multi-model endpoints, frameworks such as TensorFlow and PyTorch, Python-based backend servers, and C++/Go-based backend servers. Pick the best inference option for your ML use case so you can scale to thousands of models across your business.

Click here and download the presentation deck to learn more!

Previous Video

Implementing MLOps practices with Amazon SageMaker

Explore the features in Amazon SageMaker Pipelines that help you increase automation, track data lineage, c...

Next Video

Easily deploy models for the best performance and cost using Amazon SageMaker

Learn how Amazon SageMaker Inference Recommender auto-selects the compute instance type, instance count, co...

Questions about AI/ML?

Get in touch »

Return to Home

Achieve high performance and cost-effective model deployment

Previous Video

Next Video

Other content in this Stream

Understanding what your customers are saying is critical to your business. In this session, learn how AWS CCI solutions help you uncover valuable insights from your live and recorded calls.

Learn how to use Amazon Personalize to deliver a wide array of personalization experiences like product and media recommendations, personalized product pre-ranking, and customized direct marketing.

Learn how digital platforms of all shapes and sizes can accelerate and improve their ability to identify bad actors with AWS managed services.

Join this session to learn how you can make the shift towards more automation, more proactive mechanisms and enable your IT team to innovate faster with AWS AIOPs solutions.

Learn how AI can automate document processing extracting data and insights from insurance claims, mortgage applications, healthcare claims or legal contracts among others.

Create a fully functional search application in just a few clicks with Kendra Experience Builder. Quickly build and deploy your custom search application, without any coding or ML experience.

Learn how to prepare data for ML using Amazon SageMaker. See a complete data-preparation workflow including how to extract data from multiple data sources, transform it, and create model features.

In this session, learn how to use fully managed Jupyter notebooks complemented by an in-depth demonstration on how to build ML models at scale.

In this session, you’ll learn about compiler technologies such as operator fusion and how SageMaker Training Compiler can be used to accelerate your training jobs.

Explore the features in Amazon SageMaker Pipelines that help you increase automation, track data lineage, catalog ML models for production, improve the quality of your end-to-end workflows, and more.

Learn how Amazon SageMaker Inference Recommender auto-selects the compute instance type, instance count, container parameters, and model optimizations to maximize performance and minimize cost.