FQP: A Fibonacci Quantization Processor with Multiplication-Free Computing and Topological-Order Routing
Xiaolong Yang, Yang Wang, Yubin Qin, Jiachen Wang, Shaojun Wei, Yang Hu, Shouyi Yin
2024Year
1Citations
Abstract
With the continuous advancement of artificial intelligence, neural networks exhibit an escalating parameter size, demanding increased computational power and excessive memory access. Low bit-width quantization emerges as a viable solution to address this challenge. However, conventional low bit-width uniform quantization suffers from a mismatch with the weight and activation data distribution in neural networks, resulting in accuracy degradation.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Improving Low-Precision Network Quantization via Bin RegularizationTiantian Han, Dong Li, Ji Liu, Lu Tian et al.ICCV 2021 · 45 citations
- Adaptive Loss-Aware Quantization for Multi-Bit NetworksZhongnan Qu, Zimu Zhou, Yun Cheng, Lothar ThieleCVPR 2020
- Energy-Efficient and Dequantization-Free Quantization of LLMs: A Spiking Neural Network Approach to Salient Value MitigationChenyu Wang, Zhanglu Yan, Zhi Zhou, Xu Chen et al.WWW 2026
- Towards Accurate Low Bit-Width Quantization with Multiple Phase AdaptationsZhaoyi Yan, Yemin Shi, Yaowei Wang, Mingkui Tan et al.AAAI 2020 · 2 citations
- Learnable Companding Quantization for Accurate Low-Bit Neural NetworksKohei YamamotoCVPR 2021
