Building Production AI Applications with Ray Serve
Offered By: Anyscale via YouTube
Course Description
Overview
Explore the capabilities of Ray Serve for productionizing modern machine learning workloads in this 30-minute talk. Discover how Ray Serve addresses complex requirements, enabling safe and cost-effective production deployment. Learn about flexible scaling and coordination of multiple models, safe deployment and upgrades, and maximizing hardware utilization with minimal management overhead. Witness a demonstration of Ray Serve's production-ready features, including improvements in scalability, high availability, fault tolerance, and observability. Gain insights into production ML serving patterns and how Ray Serve is tailored to solve them. Hear real-world examples of how the community uses Ray Serve to lower ML inference costs. Watch a live demo of serving an ML application using Ray Serve on the Anyscale platform, highlighting recent improvements in observability, autoscaling, and cost savings. Access the slide deck for additional information and explore Anyscale's AI Application Platform for developing, running, and scaling AI workloads.
Syllabus
Building Production AI Applications with Ray Serve
Taught by
Anyscale
Related Courses
Financial Sustainability: The Numbers side of Social Enterprise+Acumen via NovoEd Cloud Computing Concepts: Part 2
University of Illinois at Urbana-Champaign via Coursera Developing Repeatable ModelsĀ® to Scale Your Impact
+Acumen via Independent Managing Microsoft Windows Server Active Directory Domain Services
Microsoft via edX Introduction aux conteneurs
Microsoft Virtual Academy via OpenClassrooms