English

HAWQV3: Dyadic Neural Network Quantization

Computer Vision and Pattern Recognition 2021-06-24 v3

Abstract

Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values. This hidden cost limits the latency improvement realized by quantizing Neural Networks. To address this, we present HAWQV3, a novel mixed-precision integer-only quantization framework. The contributions of HAWQV3 are the following: (i) An integer-only inference where the entire computational graph is performed only with integer multiplication, addition, and bit shifting, without any floating point operations or even integer division; (ii) A novel hardware-aware mixed-precision quantization method where the bit-precision is calculated by solving an integer linear programming problem that balances the trade-off between model perturbation and other constraints, e.g., memory footprint and latency; (iii) Direct hardware deployment and open source contribution for 4-bit uniform/mixed-precision quantization in TVM, achieving an average speed up of 1.45×1.45\times for uniform 4-bit, as compared to uniform 8-bit for ResNet50 on T4 GPUs; and (iv) extensive evaluation of the proposed methods on ResNet18/50 and InceptionV3, for various model compression levels with/without mixed precision. For ResNet50, our INT8 quantization achieves an accuracy of 77.58%77.58\%, which is 2.68%2.68\% higher than prior integer-only work, and our mixed-precision INT4/8 quantization can reduce INT8 latency by 23%23\% and still achieve 76.73%76.73\% accuracy. Our framework and the TVM implementation have been open sourced.

Keywords

Cite

@article{arxiv.2011.10680,
  title  = {HAWQV3: Dyadic Neural Network Quantization},
  author = {Zhewei Yao and Zhen Dong and Zhangcheng Zheng and Amir Gholami and Jiali Yu and Eric Tan and Leyuan Wang and Qijing Huang and Yida Wang and Michael W. Mahoney and Kurt Keutzer},
  journal= {arXiv preprint arXiv:2011.10680},
  year   = {2021}
}
R2 v1 2026-06-23T20:24:31.483Z