FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search

arXiv:2308.03290v2 Announce Type: replace-cross
Abstract: Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent hardware, including multiple variants of integer and floating point, mixed-precision quantization has become necessary to achieve high-quality results with low model cost. Prior mixed-precision methods have performed either a post-training quantization search, which compromises on accuracy, or a differentiable quantization search, which leads to high memory usage …

abstract arxiv become compression computational consumption cs.cv cs.lg energy floating point hardware integer mixed mixed-precision modern multiple networks neural networks numerical precision quality quantization requirements results search support type variants