State of Ray Serve in 2.0 - Features and Updates for Multi-model Inference

State of Ray Serve in 2.0 - Features and Updates for Multi-model Inference

Anyscale via YouTube Direct link

Production Hardening

12 of 13

12 of 13

Production Hardening

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

State of Ray Serve in 2.0 - Features and Updates for Multi-model Inference

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Working Example: Content Understanding
  3. 3 Content Understanding Architecture
  4. 4 Requirements for Online Inference
  5. 5 Basic Solution: Multi-model Monolith
  6. 6 Ray Serve is built for Multi-model Inference
  7. 7 Model Composition Requirements
  8. 8 Solution: Model Composition API
  9. 9 Model Composition Pattern
  10. 10 Ray Serve Model Composition API
  11. 11 Autoscaling for ML Models
  12. 12 Production Hardening
  13. 13 Chaos Testing: 99.99% uptime

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.