Completed
An exploding ecosystem makes ML deployment difficult
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Bringing Choice, Automation and Performance to ML Deployment with Apache TVM and the OctoML Platform
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Machine Learning is hard and costly to deploy
- 3 Trend: ML workload diversity is exploding
- 4 Trend: ML hardware capabilities exploding
- 5 An exploding ecosystem makes ML deployment difficult
- 6 ML-based optimizations
- 7 Why use Apache TVM?
- 8 TVM: Getting Optimal Performance
- 9 OctoML's Broad HW & Model Architecture Coverage Octomizer supports any model architecture with standard operators see lists here and here
- 10 Thank you Apache TVM community! 615+!
