What is Quantization

Introduction The aim of quantization is to reduce the memory usage of the model parameters by using lower precision types than your typical float32 or (b)float16. Using lower bit widths like 8-bit and 4-bit uses less memory compared to float32 (32-bit) and (b)float16 (16-bit). The quantization procedure does not simply trim the number of bits... Read more »

The post What is Quantization appeared first on Lightning AI.

16-bit aim articles blog introduction memory precision quantization reduce tutorials types usage