Wush Adaptive Quantization Transforms

Derives closed-form optimal linear blockwise transforms combining fixed Hadamard matrices with data-dependent components from second-order statistics, providing provably near-optimal quantization for both weights and activations with GPU efficiency.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 83872b79e7

Frequently asked questions

npx get-skill add adu2021/wush-adaptive-quantization-transforms