mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-05-28 14:06:25 -05:00
4b11adaaaf
- Renamed all module.yaml files to [module_name].yml for consistency - Updated module configuration format and structure - Added new module configurations for all 20 modules - Removed obsolete benchmarking module (20_benchmarking) - Added new capstone module (20_capstone) - Enhanced autograd module with visual examples and improved implementation - Updated optimizers module with latest improvements - Standardized YAML structure across all modules
29 lines
862 B
YAML
29 lines
862 B
YAML
name: Quantization
|
|
number: 17
|
|
type: optimization
|
|
difficulty: advanced
|
|
estimated_hours: 6-8
|
|
|
|
description: |
|
|
Precision optimization through INT8 quantization. Students learn to reduce model size
|
|
and accelerate inference by using lower precision arithmetic while maintaining accuracy.
|
|
Especially powerful for CNN convolutions and edge deployment.
|
|
|
|
learning_objectives:
|
|
- Understand precision vs performance trade-offs
|
|
- Implement INT8 quantization for neural networks
|
|
- Build calibration-based quantization systems
|
|
- Optimize CNN inference for mobile deployment
|
|
|
|
prerequisites:
|
|
- Module 09: Spatial (CNNs)
|
|
- Module 16: Acceleration
|
|
|
|
skills_developed:
|
|
- Quantization techniques and mathematics
|
|
- Post-training optimization strategies
|
|
- Hardware-aware optimization
|
|
- Mobile and edge deployment patterns
|
|
|
|
exports:
|
|
- tinytorch.quantization |