Model Serving Foundations (Ray Serve) thumbnail

Model Serving Foundations (Ray Serve)

Foundations

Learn to deploy your machine learning models in this foundations course on Ray Serve.

About this course

6 lessons
1 module
Tags
FoundationsBeginnerModel ServingLegacy Import
Level: Beginner
ML Model Deployment
Scalable Inference Services

Course Modules

0

Serve

Learn when to use Ray Serve and how its application/deployment architecture supports scalable ML serving. Build and deploy a PyTorch MNIST image-classification service by converting a local model into an online Ray Serve deployment and running inference via an endpoint.

  • Ray Serve Overview
  • When To Use Serve?
  • Ray Serve Architecture
+3 more lessons