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

Intro

1 of 13

1 of 13

Intro

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.