Model deployment scenarios on Amazon SageMaker

In this whiteboard video, I walk you through three model deployment scenarios on Amazon SageMaker: - One model per endpoint, - Several model variants per endpoint, - Multi-model endpoints. ⭐️⭐️⭐️ Don't forget to subscribe to be notified of future videos ⭐️⭐️⭐️ Blog posts: * Mastering the mystical art of model deployment, part 1 https://medium.com/@julsimon/mastering-the-mystical-art-of-model-deployment-c0cafe011175 * Mastering the mystical art of model deployment, part 2 https://medium.com/@julsimon/mastering-the-mystical-art-of-model-deployment-part-2-deploying-amazon-sagemaker-endpoints-with-cf9539dc2579 * Multi-model endpoints https://aws.amazon.com/blogs/machine-learning/save-on-inference-costs-by-using-amazon-sagemaker-multi-model-endpoints/ Notebooks: * Multi-model endpoints examples (scikit-learn, XGBoost, custom container): https://github.com/awslabs/amazon-sagemaker-examples/tree/master/advanced_functionality For more content, follow me on : * Medium: https://medium.com/@julsimon * Twitter: https://twitter.com/juliensimon