[ML] Week 3: Model Optimization

[daffa09]

Days 15-17: Performance Optimization

• Optimize model architecture
• Analyze layer contributions
• Prune unnecessary layers
• Implement knowledge distillation
• Implement quantization
  Days 18-21: Inference Optimization
• Build inference pipeline
• Implement batching strategy
• Optimize preprocessing
• Add caching mechanism
• Setup TorchScript/ONNX export