Quantization
Reduce precision to save memory. INT8, INT4, symmetric vs asymmetric, and QAT.
Learning path
Work through each subtopic in order. Click any file below to open its lesson. Track your progress with the checkbox at the bottom.
Subtopics
Each subtopic includes a concise explanation, code examples, and references.
Quantization
Floating-point → integer visualizer.
Dequantization
Integer → approximate floating-point reconstruction.
Quantization Scale
Scale-factor visualizer.
Zero Point
Number-line quantizer.
Quantization Error
Original vs quantized graph.
Symmetric Quantization
Centered quantization levels.
Asymmetric Quantization
Offset quantization levels.
INT8
8-bit representation explorer.
INT4
4-bit quantization visualizer.
Weight Quantization
Model-weight matrix before/after.
Activation Quantization
Activation histogram.
Post-Training Quantization
Finished-model quantization pipeline.
Quantization-Aware Training
Training loop with simulated quantization.
Quantized Inference
Inference memory/latency comparison.