Introduction to Model Deployment with Ray Serve
Offered By: MLOps World: Machine Learning in Production via YouTube
Course Description
Overview
Explore the fundamentals of model deployment using Ray Serve in this comprehensive tutorial from MLOps World: Machine Learning in Production. Dive into a two-part session led by Jules Damji and Archit Kulkarni from Anyscale Inc, covering Ray core APIs and Ray Serve concepts. Begin with hands-on coding exercises to master Ray's distributed computing patterns, then progress to Ray Serve's scalable architecture and deployment strategies. Learn to create, expose, and deploy models using core deployment APIs through practical Jupyter notebook examples. Discover Ray Serve's integration with MLflow for model registry management and its compatibility with FastAPI. Gain essential skills in converting Python functions and classes to distributed settings, utilizing Ray Serve APIs for model deployment, accessing deployment endpoints, configuring compute resources for production scaling, and leveraging key integrations to enhance your MLOps workflow.
Syllabus
Introduction to Model Deployment with Ray Serve
Taught by
MLOps World: Machine Learning in Production
Related Courses
Machine Learning Operations (MLOps): Getting StartedGoogle Cloud via Coursera Проектирование и реализация систем машинного обучения
Higher School of Economics via Coursera Demystifying Machine Learning Operations (MLOps)
Pluralsight Machine Learning Engineer with Microsoft Azure
Microsoft via Udacity Machine Learning Engineering for Production (MLOps)
DeepLearning.AI via Coursera