Completed
Decouple Web Serving and Model Serving
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
AI Inference Workloads - Solving MLOps Challenges in Production
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Agenda
- 3 The Machine Learning Process
- 4 Deployment Types for Inference Workloads
- 5 Machine Learning is Different than Traditional Software Engineering
- 6 Low Latency
- 7 High Throughput
- 8 Maximize GPU Utilization
- 9 Embedding ML. Models into Web Servers
- 10 Decouple Web Serving and Model Serving
- 11 Model Serving System on Kubernetes
- 12 Multi-Instance GPU (MIG)
- 13 Run:Al's Dynamic MIG Allocations
- 14 Run 3 instances of type 2g.10gb
- 15 Valid Profiles & Configurations
- 16 Serving on Fractional GPUs
- 17 A Game Changer for Model Inferencing
