The demo will show how to:
- Deploy a trained Python model and scale it to a cluster using Ray Serve
- Improve the HTTP API using Ray Serve’s native FastAPI integration
- Compose multiple independently-scalable models into a single model, and run them in parallel to minimize latency.
Anyscale Connect
Building a scalable ML model serving API with Ray Serve
Thursday, September 9, 4:00PM UTCRay Serve is a framework-agnostic and Python-first model serving library built on Ray. In this introductory webinar on Ray Serve, we will highlight how Ray Serve makes it easy to deploy, operate and scale a machine learning API.
The core of the webinar will be a live demo that shows how to build a scalable API using Natural Language Processing models.
Speakers
Tricia Fu
Product Manager, Anyscale
Tricia is currently a Product Manager at Anyscale. Before that, she spent some time at Google as a Product Manager and LinkedIn as a Software Engineer. She holds a BS degree from UC Berkeley in Electrical Engineering and Computer Science. In her free time, she loves taking her dog on alpine lake hikes!