Modern Data Architecture on AWS by Behram Irani

Author:Behram Irani
Language: eng
Format: epub
Publisher: Packt
Published: 2023-12-15T00:00:00+00:00

The final steps in the ML pipeline are to deploy and manage the models. SageMaker provides a bunch of tools to help with this process too. To prevent this chapter from getting too bloated, I’ll keep it to a summary here:

Real-time inference: Useful for steady traffic patterns

Serverless inference: Useful for intermittent traffic patterns

Multi-model and multi-container endpoints: Helps reduce costs

Inference Recommender: Helps to select the best compute instances and configurations in an automated manner

Model Monitor: Helps to maintain the accuracy of the deployed models

Kubernetes and Kubeflow integration: Helps to simplify Kubernetes-based ML

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.