mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-03-12 02:43:35 -05:00
753ae52ae0
This commit implements the pedagogically optimal "inevitable discovery" module progression based on expert validation and educational design principles. ## Module Reordering Summary **Previous Order (Problems)**: - 05_losses → 06_autograd → 07_dataloader → 08_optimizers → 09_spatial → 10_training - Issues: Autograd before optimizers, DataLoader before training, scattered dependencies **New Order (Beautiful Progression)**: - 05_losses → 06_optimizers → 07_autograd → 08_training → 09_spatial → 10_dataloader - Benefits: Each module creates inevitable need for the next ## Pedagogical Flow Achieved **05_losses** → "Need systematic weight updates" → **06_optimizers** **06_optimizers** → "Need automatic gradients" → **07_autograd** **07_autograd** → "Need systematic training" → **08_training** **08_training** → "MLPs hit limits on images" → **09_spatial** **09_spatial** → "Training is too slow" → **10_dataloader** ## Technical Changes ### Module Directory Renaming - `06_autograd` → `07_autograd` - `07_dataloader` → `10_dataloader` - `08_optimizers` → `06_optimizers` - `10_training` → `08_training` - `09_spatial` → `09_spatial` (no change) ### System Integration Updates - **MODULE_TO_CHECKPOINT mapping**: Updated in tito/commands/export.py - **Test directories**: Renamed module_XX directories to match new numbers - **Documentation**: Updated all references in MD files and agent configurations - **CLI integration**: Updated next-steps suggestions for proper flow ### Agent Configuration Updates - **Quality Assurance**: Updated module audit status with new numbers - **Module Developer**: Updated work tracking with new sequence - **Documentation**: Updated MASTER_PLAN_OF_RECORD.md with beautiful progression ## Educational Benefits 1. **Inevitable Discovery**: Each module naturally leads to the next 2. **Cognitive Load**: Concepts introduced exactly when needed 3. **Motivation**: Students understand WHY each tool is necessary 4. **Synthesis**: Everything flows toward complete ML systems understanding 5. **Professional Alignment**: Matches real ML engineering workflows ## Quality Assurance - ✅ All CLI commands still function - ✅ Checkpoint system mappings updated - ✅ Documentation consistency maintained - ✅ Test directory structure aligned - ✅ Agent configurations synchronized **Impact**: This reordering transforms TinyTorch from a collection of modules into a coherent educational journey where each step naturally motivates the next, creating optimal conditions for deep learning systems understanding.
Module 17: Precision - Numerical Optimization through Quantization
Overview
Reduce model size by 75% and accelerate inference by 2-4x through INT8 quantization. Learn how production systems deploy billion-parameter models on edge devices.
What You'll Build
- INT8 Quantizer: Convert FP32 models to INT8
- Calibration System: Find optimal scaling factors
- Quantized Operations: Fast integer arithmetic
- Accuracy Validator: Measure precision/performance tradeoffs
Learning Objectives
- Numerical Representation: FP32 vs FP16 vs INT8 tradeoffs
- Post-Training Quantization: Convert trained models efficiently
- Calibration Techniques: Minimize accuracy loss
- Hardware Acceleration: Why INT8 is 4x faster on modern hardware
Prerequisites
- Module 15: Acceleration (backend dispatch)
- Module 10: Training (trained models to quantize)
Key Concepts
The Problem: Model Size and Speed
# FP32 Model - High precision, slow, large
model = TinyGPT() # 400MB, 100ms/token
# After quantization - Lower precision, fast, small
quantized = quantize_int8(model) # 100MB, 25ms/token
Quantization Process
# 1. Calibration - Find scale factors
scales = calibrate(model, calibration_data)
# 2. Quantization - Convert weights
quantized_weights = (weights / scales).round().clip(-128, 127)
# 3. Inference - Use integer ops
output = quantized_forward(input, quantized_weights, scales)
Performance Impact
- Model Size: 4x reduction (FP32 → INT8)
- Inference Speed: 2-4x faster on CPU/GPU
- Accuracy: Typically <1% loss with good calibration
- Memory Bandwidth: 4x reduction
Real-World Applications
- Mobile Deployment: Run LLMs on phones
- Edge AI: Raspberry Pi inference
- Datacenter Efficiency: 4x more models per GPU
- TensorFlow Lite: Production quantization
Module Structure
- Numerical Basics: Understanding precision and range
- Quantization Math: Scale factors and rounding
- Calibration: Finding optimal quantization parameters
- Implementation: Building quantized operations
- Evaluation: Accuracy vs performance analysis
Hands-On Examples
# Quantize your trained CNN
cnn = load_trained_model("cifar10_cnn.pt")
quantized = quantize_model(cnn, calibration_loader)
# Compare accuracy
original_acc = evaluate(cnn, test_loader) # 75.2%
quantized_acc = evaluate(quantized, test_loader) # 74.8%
# Measure speedup
original_time = benchmark(cnn) # 45ms/batch
quantized_time = benchmark(quantized) # 12ms/batch (3.75x faster!)
Success Criteria
- ✅ Quantize models to INT8 with <1% accuracy loss
- ✅ Achieve 2-4x inference speedup
- ✅ Reduce model size by 75%
- ✅ Understand hardware acceleration principles