Deployment - FSDL 2022

Deployment - FSDL 2022

The Full Stack via YouTube Direct link

Overview

1 of 23

1 of 23

Overview

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Deployment - FSDL 2022

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

  1. 1 Overview
  2. 2 First, deploy a prototype with gradio or streamlit
  3. 3 Model-in-server architecture
  4. 4 Model-in-database architecture
  5. 5 Model-as-a-service architecture
  6. 6 REST APIs for model services
  7. 7 Dependency management for model services
  8. 8 Containerization for model services with Docker
  9. 9 Performance optimization: to GPU or not to GPU?
  10. 10 Optimization for CPUs: distillation, quantization, and caching
  11. 11 Optimization for GPUs: Batching and GPU sharing
  12. 12 Libraries for model serving on GPUs
  13. 13 Horizontal scaling
  14. 14 Horizontal scaling with container orchestration k8s
  15. 15 Horizontal scaling with serverless services
  16. 16 Rollouts: shadows and canaries
  17. 17 Managed options for model serving AWS Sagemaker
  18. 18 Takeaways on model services
  19. 19 Moving to edge
  20. 20 Frameworks for edge deployment
  21. 21 Making efficient models for the edge
  22. 22 Mindsets and takeaways for edge deployment
  23. 23 Takeways for deploying ML models

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.