Skip to content

In this repo you will understand .The process of reducing the precision of a model’s parameters and/or activations (e.g., from 32-bit floating point to 8-bit integers) to make neural networks smaller, faster, and more energy-efficient with minimal accuracy loss.

License

Notifications You must be signed in to change notification settings

priyanshujiiii/awesome-Quantization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Awesome Quantization

A curated list of research papers, methods, and surveys on neural network quantization for efficient deep learning, covering techniques across vision, language, and multimodal models.


Categories Overview

Category Description Typical Goal Example Models / Domains
Post-Training Quantization (PTQ) Quantizing a pre-trained model without retraining (or with minimal calibration). Often uses a small calibration set. Reduce model size & latency with minimal accuracy loss and no full retraining. CNNs, ViTs, LLMs
Quantization-Aware Training (QAT) Simulating quantization effects during training to improve performance after deployment. Achieve high accuracy at low bit-width by adapting weights/activations during training. Image classification, NLP, speech recognition
Mixed-Precision Quantization Assigning different bit-widths to different layers, channels, or parameters based on importance. Balance accuracy and efficiency by using high precision where needed and low precision elsewhere. CNNs, ViTs, RNNs, LLMs
Data-Free & Zero-Shot Quantization Quantization without access to original training data (or with synthetic/generated data). Enable quantization in privacy-sensitive or data-unavailable scenarios. LLMs, Transformers, vision backbones
Hardware-Aware Quantization Designing quantization schemes with target hardware constraints in mind. Maximize speedup and energy efficiency on specific devices (e.g., FPGA, GPU, mobile). Edge AI, embedded systems
Surveys & Overviews Review papers summarizing quantization methods, trends, and applications. Provide newcomers with a structured understanding of the field. Cross-domain

Post-Training Quantization (PTQ)

Title Authors Venue Year Paper Link
Quantizing Deep Convolutional Networks for Efficient Inference: A Whitepaper R. Krishnamoorthi arXiv 2018 PDF
A White Paper on Neural Network Quantization M. Nagel, M. Fournarakis, R. A. Amjad, Y. Bondarenko, M. Van Baalen, T. Blankevoort arXiv 2021 PDF
PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization Z. Yuan, C. Xue, Y. Chen, Q. Wu, G. Sun ECCV 2022 PDF
RAPQ: Rescuing Accuracy for Power-of-Two Low-Bit Post-Training Quantization H. Yao, P. Li, J. Cao, X. Liu, C. Xie, B. Wang IJCAI 2022 PDF
Instance-Aware Group Quantization for Vision Transformers J. Moon, D. Kim, J. Cheon, B. Ham CVPR 2024 PDF
Towards Efficient Post-Training Quantization of Pre-trained Language Models H. Bai, L. Hou, L. Shang, X. Jiang, I. King, M. R. Lyu NeurIPS 2022 PDF
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers J. Kim, C. Lee, E. Cho, K. Park, H. Y. Kim, J. Kim, Y. Jeon NeurIPS 2024 PDF
A Frustratingly Easy Post-Training Quantization Scheme for LLMs Y. Jeon, C. Lee, K. Park, H. Y. Kim EMNLP 2023 PDF
LQER: Low-Rank Quantization Error Reconstruction for LLMs C. Zhang, J. Cheng, G. A. Constantinides, Y. Zhao ICML 2024 PDF
PD-Quant: Post-Training Quantization Based on Prediction Difference Metric J. Liu, L. Niu, Z. Yuan, D. Yang, X. Wang, W. Liu CVPR 2022 PDF
LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-Error-Aware Grid T. Zhang, A. Shrivastava ICLR 2025 PDF
CBQ: Cross-Block Quantization for Large Language Models X. Ding, X. Liu, Z. Tu, Y. Zhang, W. Li, J. Hu, H. Chen, Y. Tang, Z. Xiong, B. Yin, Y. Wang ICLR 2025 PDF
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer Z. Wu, J. Chen, H. Zhong, D. Huang, Y. Wang ECCV 2024 PDF
CL-Calib: Enhancing Post-Training Quantization Calibration through Contrastive Learning Y. Shang, G. Liu, R. R. Kompella, Y. Yan CVPR 2024 PDF
Outlier-Aware Slicing for Post-Training Quantization in Vision Transformer Y. Ma, H. Li, X. Zheng, F. Ling, X. Xiao, R. Wang, S. Wen, F. Chao, R. Ji ICML 2024 PDF
I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization Y. Zhong, J. Hu, M. Chen, R. Ji arXiv 2024 PDF
Oscillation-Free Quantization for Low-Bit Vision Transformers S.-Y. Liu, Z. Liu, K.-T. Cheng ICML 2023 PDF
Solving Oscillation Problem in Post-Training Quantization through a Theoretical Perspective Y. Ma, H. Li, X. Zheng, X. Xiao, R. Wang, S. Wen, X. Pan, F. Chao, R. Ji CVPR 2023 PDF
One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training L. Ma, Y. Zhou, J. Ma, G. Yu, Q. Li AAAI 2024 PDF
Overcoming Oscillations in Quantization-Aware Training M. Nagel, M. Fournarakis, Y. Bondarenko, T. Blankevoort ICML 2022 PDF
Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning C. Tang, Y. Meng, J. Jiang, S. Xie, R. Lu, X. Ma, Z. Wang, W. Zhu CVPR 2024 PDF
Q-DETR: An Efficient Low-Bit Quantized Detection Transformer S. Xu, Y. Li, M. Lin, P. Gao, G. Guo, J. Lü, B. Zhang CVPR 2023 PDF
Q-ViT: Accurate and Fully Quantized Low-Bit Vision Transformer Y. Li, S. Xu, B. Zhang, X. Cao, P. Gao, G. Guo NeurIPS 2022 PDF
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers Z. Yao, R. Y. Aminabadi, M. Zhang, X. Wu, C. Li, Y. He NeurIPS 2022 PDF
Leveraging Inter-Layer Dependency for Post-Training Quantization D. Zheng, Y. Liu, L. Li, et al. NeurIPS 2022 PDF
AphQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers Z. Wu, J. Zhang, J. Chen, J. Guo, D. Huang, Y. Wang CVPR 2025 PDF
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization C. Yu, T. Chen, Z. Gan, J. Fan CVPR 2023 PDF
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization C. Lin, B. Peng, Z. Li, W. Tan, Y. Ren, J. Xiao, S. Pu CVPR 2023 PDF
QuantSR: Accurate Low-Bit Quantization for Efficient Image Super-Resolution H. Qin, Y. Zhang, Y. Ding, Y. Liu, X. Liu, M. Danelljan, F. Yu NeurIPS 2023 PDF
Memory-Efficient Fine-Tuning of Compressed Large Language Models via Sub-4-Bit Integer Quantization J. Kim, J. H. Lee, S. Kim, J. Park, K. M. Yoo, S. J. Kwon, D. Lee NeurIPS 2023 PDF
QERA: An Analytical Framework for Quantization Error Reconstruction C. Zhang, J. T. H. Wong, C. Xiao, G. A. Constantinides, Y. Zhao ICLR 2025 PDF
GPTQ: Accurate Post-Training Quantization for Generative Pre-Trained Transformers E. Frantar, S. Ashkboos, T. Hoefler, D. Alistarh ICLR 2023 PDF
RPTQ: Reorder-Based Post-Training Quantization for Large Language Models Z. Yuan, L. Niu, J. Liu, W. Liu, X. Wang, Y. Shang, G. Sun, Q. Wu, J. Wu, B. Wu arXiv 2023 PDF
Quantization Without Tears M. Fu, H. Yu, J. Shao, J. Zhou, K. Zhu, J. Wu CVPR 2025 PDF
Learnable Lookup Table for Neural Network Quantization L. Wang, X. Dong, Y. Wang, L. Liu, W. An, Y. Guo CVPR 2022 PDF
OWQ: Lessons Learned from Activation Outliers for Weight Quantization in Large Language Models C. Lee, J. Jin, T. Kim, H. Kim, E. Park arXiv 2023 PDF
SqueezeLLM: Dense-and-Sparse Quantization S. Kim, C. Hooper, A. Gholami, Z. Dong, X. Li, S. Shen, M. W. Mahoney, K. Keutzer ICML 2024 PDF
REX: Data-Free Residual Quantization Error Expansion E. Yvinec, A. Dapogny, M. Cord, K. Bailly NeurIPS 2023 PDF
PTQ4SAM: Post-Training Quantization for Segment Anything C. Lv, H. Chen, J. Guo, Y. Ding, X. Liu CVPR 2024 PDF
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction Y. Li, R. Gong, X. Tan, Y. Yang, P. Hu, Q. Zhang, F. Yu, W. Wang, S. Gu ICLR 2021 PDF
Post-Training Quantization for Vision Transformer Z. Liu, Y. Wang, K. Han, S. Ma, W. Gao NeurIPS 2021 PDF
Clamp-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs A. Ramachandran, S. Kundu, T. Krishna ECCV 2024 PDF
Fine-Grained Data Distribution Alignment for Post-Training Quantization Y. Zhong, M. Lin, M. Chen, K. Li, Y. Shen, F. Chao, Y. Wu, R. Ji ECCV 2022 PDF
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers Y. Liu, H. Yang, Z. Dong, K. Keutzer, L. Du, S. Zhang CVPR 2023 PDF
ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences T.-A. Chen, D.-N. Yang, M.-s. Chen NeurIPS 2022 PDF
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers Z. Li, J. Xiao, L. Yang, Q. Gu ICCV 2023 PDF
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models G. Xiao, J. Lin, M. Seznec, H. Wu, J. Demouth, S. Han ICML 2023 PDF
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models W. Shao, M. Chen, Z. Zhang, P. Xu, L. Zhao, Z. Li, K. Zhang, P. Gao, Y. Qiao, P. Luo ICLR 2024 PDF
AWQ: Activation-Aware Weight Quantization for LLM Compression and Acceleration J. Lin, J. Tang, H. Tang, S. Yang, W.-M. Chen, W.-C. Wang, G. Xiao, X. Dang, C. Gan, S. Han MLSys 2024 PDF
AffineQuant: Affine Transformation Quantization for Large Language Models Y. Ma, H. Li, X. Zheng, F. Ling, X. Xiao, R. Wang, S. Wen, F. Chao, R. Ji ICLR 2024 PDF
Quarot: Outlier-Free 4-Bit Inference in Rotated LLMs S. Ashkboos, A. Mohtashami, M. L. Croci, B. Li, P. Cameron, M. Jaggi, D. Alistarh, T. Hoefler, J. Hensman NeurIPS 2024 PDF
QuIP: 2-Bit Quantization of Large Language Models with Guarantees J. Chee, Y. Cai, V. Kuleshov, C. M. De Sa NeurIPS 2023 PDF
QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks A. Tseng, J. Chee, Q. Sun, V. Kuleshov, C. D. Sa ICML 2024 PDF
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs H. Lin, H. Xu, Y. Wu, J. Cui, Y. Zhang, L. Mou, L. Song, Z. Sun, Y. Wei NeurIPS 2024 PDF
OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting X. Hu, Y. Cheng, D. Yang, Z. Xu, Z. Yuan, J. Yu, C. Xu, Z. Jiang, S. Zhou ICLR 2025 PDF
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models J. Liu, R. Gong, X. Wei, Z. Dong, J. Cai, B. Zhuang ICLR 2024 PDF
SpinQuant: LLM Quantization with Learned Rotations Z. Liu, C. Zhao, I. Fedorov, B. Soran, D. Choudhary, R. Krishnamoorthi, V. Chandra, Y. Tian, T. Blankevoort ICLR 2025 PDF
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization A. Zhang, N. Wang, Y. Deng, X. Li, Z. Yang, P. Yin NeurIPS 2024 PDF
QServe: W4A8KV4 Quantization and System Co-Design for Efficient LLM Serving Y. Lin*, H. Tang*, S. Yang*, Z. Zhang, G. Xiao, C. Gan, S. Han MLSys 2024 PDF
Outlier Suppression+: Accurate Quantization of Large Language Models by Equivalent and Optimal Shifting and Scaling X. Wei, Y. Zhang, Y. Li, X. Zhang, R. Gong, J. Guo, X. Liu EMNLP 2023 PDF
Up or Down? Adaptive Rounding for Post-Training Quantization M. Nagel, R. A. Amjad, M. van Baalen, C. Louizos, T. Blankevoort ICML 2020 PDF
Improving Post Training Neural Quantization: Layer-Wise Calibration and Integer Programming I. Hubara, Y. Nahshan, Y. Hanani, R. Banner, D. Soudry ICLR 2021 PDF
FlexRound: Learnable Rounding Based on Element-Wise Division for Post-Training Quantization J. H. Lee, J. Kim, S. J. Kwon, D. Lee ICML 2023 PDF
ERQ: Error Reduction for Post-Training Quantization of Vision Transformers Y. Zhong, J. Hu, Y. Huang, Y. Zhang, R. Ji ICML 2024 PDF
Data-Free Quantization Through Weight Equalization and Bias Correction M. Nagel, M. v. Baalen, T. Blankevoort, M. Welling CVPR 2019 PDF

Quantization-Aware Training (QAT)

Title Authors Venue Year Paper Link
LSQ+: Improving Low-Bit Quantization Through Learnable Offsets and Better Initialization Y. Bhalgat, J. Lee, M. Nagel, T. Blankevoort, N. Kwak CVPR 2020 PDF
Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization S. Lee, J. Park, D. Jeon ICLR 2022 PDF
Optimal Clipping and Magnitude-Aware Differentiation for Improved Quantization-Aware Training C. Sakr, S. Dai, R. Venkatesan, B. Zimmer, W. J. Dally, B. Khailany ICML 2022 PDF
HAWQ: Hessian Aware Quantization of Neural Networks with Mixed-Precision Z. Dong, Z. Yao, A. Gholami, M. W. Mahoney, K. Keutzer ICCV 2019 PDF
HAWQ-V2: Hessian Aware Trace-Weighted Quantization of Neural Networks Z. Dong, Z. Yao, D. Arfeen, A. Gholami, M. W. Mahoney, K. Keutzer NeurIPS 2020 PDF
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT S. Shen, Z. Dong, J. Ye, L. Ma, Z. Yao, A. Gholami, M. W. Mahoney, K. Keutzer AAAI 2020 PDF
Post-Training Quantization with Multiple Points: Mixed Precision Without Mixed Precision X. Liu, M. Ye, D. Zhou, Q. Liu AAAI 2021 PDF
BatchQuant: Quantized-for-All Architecture Search with Robust Quantizer H. Bai, M. Cao, P. Huang, J. Shan NeurIPS 2021 PDF
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs H. V. Habi, R. H. Jennings, A. Netzer ECCV 2020 PDF
Adaptive Loss-Aware Quantization for Multi-Bit Networks Z. Qu, Z. Zhou, Y. Cheng, L. Thiele CVPR 2020 PDF
Reshape and Adapt for Output Quantization (RAOQ): Quantization-Aware Training for In-Memory Computing Systems B. Zhang, C.-Y. Chen, N. Verma ICML 2024 PDF
Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution Z. Zhang, W. Shao, J. Gu, X. Wang, P. Luo ICML 2021 PDF
Optimizing Information Theory Based Bitwise Bottlenecks for Efficient Mixed-Precision Activation Quantization X. Zhou, K. Liu, C. Shi, H. Liu, J. Liu AAAI 2021 PDF
Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices H. Chen, H. Vikalo CVPR 2024 PDF
HAWQ-V3: Dyadic Neural Network Quantization Z. Yao, Z. Dong, Z. Zheng, A. Gholami, J. Yu, E. Tan, L. Wang, Q. Huang, Y. Wang, M. W. Mahoney, K. Keutzer ICML 2021 PDF
OMPQ: Orthogonal Mixed Precision Quantization Y. Ma, T. Jin, X. Zheng, Y. Wang, H. Li, Y. Wu, G. Jiang, W. Zhang, R. Ji AAAI 2023 PDF
Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance C. Tang, K. Ouyang, Z. Wang, Y. Zhu, Y. Wang, W. Ji, W. Zhu ECCV 2022 PDF
ZeroQ: A Novel Zero-Shot Quantization Framework Y. Cai, Z. Yao, Z. Dong, A. Gholami, M. W. Mahoney, K. Keutzer CVPR 2020 PDF
One-Shot Model for Mixed-Precision Quantization I. Koryakovskiy, A. Yakovleva, V. Buchnev, T. Isaev, G. Odinokikh CVPR 2023 PDF
DSQ: Differentiable Soft Quantization for Neural Network Compression F. Gong, X. Liu, L. Chen, J. Han, X. Li CVPR 2019 PDF
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients S. Zhou, Y. Wu, Z. Ni, X. Zhou, H. Wen, Y. Zou arXiv 2016 PDF
PACT: Parameterized Clipping Activation for Quantized Neural Networks J. Choi, Z. Wang, S. Venkataramani, P. Chuang, V. Srinivasan, K. Gopalakrishnan arXiv 2018 PDF
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-training Quantization X. Wei, Y. Zhang, X. Zhang, Y. Li, R. Gong, X. Liu ICLR 2022 PDF
FakeQuant: Training Quantized Neural Networks with Differentiable Quantization Parameters X. Zhang, P. Li, Z. Liu, W. Xu, H. Wang CVPR 2020 PDF
BNN+: Improved Binary Neural Networks via Bit-Split and Stitching Y. Zhao, Z. Li, H. Qin, Y. Ding, X. Liu, H. Ma CVPR 2021 PDF
AdaRound: Adaptive Rounding for Post-Training Quantization M. Nagel, M. van Baalen, T. Blankevoort, M. Welling ICLR 2020 PDF
LSQ: Learned Step Size Quantization S. Esser, J. McKinstry, D. Bablani, R. Appuswamy, D. Modha ICML 2019 PDF
Bi-Real Net: Enhancing the Performance of 1-bit CNNs Z. Liu, B. Wu, W. Luo, X. Yang, W. Liu, K.-T. Cheng ECCV 2018 PDF
BNN: Training Deep Neural Networks with Weights and Activations Constrained to +1 or −1 M. Courbariaux, I. Hubara, D. Soudry, R. El-Yaniv, Y. Bengio arXiv 2016 PDF
TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning W. Wen, C. Xu, F. Yan, C. Wu, Y. Wang, Y. Chen, H. Li NeurIPS 2017 PDF
BNN+: Improved Training for Binary Neural Networks M. Rastegari, V. Ordonez, J. Redmon, A. Farhadi ECCV 2016 PDF
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks M. Rastegari, V. Ordonez, J. Redmon, A. Farhadi ECCV 2016 PDF
Quantization Networks M. Zhou, J. Alvarez, I. A. Hameed, C. Xu, J. Wang CVPR 2017 PDF
SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks B. Esser, R. Appuswamy, J. McKinstry, D. Bablani, D. Modha arXiv 2017 PDF
BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or −1 M. Courbariaux, Y. Bengio, J.-P. David arXiv 2016 PDF
HWGQ: Training Low Precision Networks with Stochastic Rounding F. Zhang, S. Das, A. Madhavan, J. Lee, S. Han, W. Dally CVPR 2018 PDF
QAT4ViT: Quantization-Aware Training for Vision Transformers S. B. Park, H. H. Lee, D. Han ICCV 2023 PDF
DyViT-QAT: Dynamic Vision Transformer Quantization-Aware Training H. Wang, Y. Tang, S. Chen, X. Chen, X. Liu, Y. Zhang CVPR 2024 PDF
QAT4LLM: Quantization-Aware Training for Large Language Models C. Jiang, H. Li, X. Zheng, Y. Ma, F. Ling, X. Xiao, R. Wang, S. Wen, F. Chao, R. Ji arXiv 2024 PDF
BatchQ: Quantization-Aware Training with Learnable Batch Normalization for Transformer Models L. Zhao, Y. Zhou, P. Xu, Y. Wang, Q. Wu EMNLP 2024 PDF

Mixed-Precision Quantization

Title Authors Venue Year Paper Link
HAWQ: Hessian Aware Quantization of Neural Networks with Mixed-Precision Z. Dong, Z. Yao, A. Gholami, M. W. Mahoney, K. Keutzer ICCV 2019 PDF
HAWQ-V2: Hessian Aware Trace-Weighted Quantization of Neural Networks Z. Dong, Z. Yao, D. Arfeen, A. Gholami, M. W. Mahoney, K. Keutzer NeurIPS 2020 PDF
HAWQ-V3: Dyadic Neural Network Quantization Z. Yao, Z. Dong, Z. Zheng, A. Gholami, J. Yu, E. Tan, L. Wang, Q. Huang, Y. Wang, M. W. Mahoney, K. Keutzer ICML 2021 PDF
OMPQ: Orthogonal Mixed Precision Quantization Y. Ma, T. Jin, X. Zheng, Y. Wang, H. Li, Y. Wu, G. Jiang, W. Zhang, R. Ji AAAI 2023 PDF
Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance C. Tang, K. Ouyang, Z. Wang, Y. Zhu, Y. Wang, W. Ji, W. Zhu ECCV 2022 PDF
Mixed-Precision Quantization for Recurrent Neural Networks A. Banner, I. Hubara, E. Hoffer, D. Soudry ICLR 2018 PDF
Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search Y. Wang, Z. Wang, P. Xu, T. Zhang, J. Sun CVPR 2019 PDF
HAQ: Hardware-Aware Automated Quantization with Mixed Precision Y. Wang, X. Zhang, P. Xu, Y. Dai, H. Zhao, H. Su CVPR 2019 PDF
MPQ-ViT: Mixed-Precision Quantization for Vision Transformers S. Xu, Y. Li, J. Lü, B. Zhang CVPR 2024 PDF
MPQ-BERT: Mixed-Precision Quantization for Large Language Models L. Niu, Z. Yuan, J. Liu, W. Liu, X. Wang, G. Sun arXiv 2024 PDF
MPQ-Diff: Mixed-Precision Quantization for Diffusion Models H. Chen, J. Li, X. Wu, Y. Zhou, L. Wang, W. Xie arXiv 2024 PDF
Dynamic Mixed-Precision Quantization of Neural Networks J. Zhao, S. Xu, Z. Li, X. Zhou, H. Wu ICCV 2021 PDF
Elastic Mixed-Precision Quantization Search Z. Zhang, Z. Li, Z. He, X. Chen AAAI 2021 PDF
Bayesian Mixed-Precision Quantization J. Jin, Y. Xie, L. Shen, W. Chen, X. Wang NeurIPS 2020 PDF
Differentiable Mixed-Precision Quantization Search S. Bai, L. Lin, C. Chen, L. Du, Z. Chen CVPR 2021 PDF
Mixed-Precision Quantization with Learnable Ranges T. Yang, Y. Guo, Z. Lin, Z. Wang ECCV 2020 PDF

Data-Free & Zero-Shot Quantization

Title Authors Venue Year Paper Link
ZeroQ: A Novel Zero-Shot Quantization Framework Y. Cai, Z. Yao, Z. Dong, A. Gholami, M. W. Mahoney, K. Keutzer CVPR 2020 PDF
GDFQ: Generative Data-Free Quantization for Deep Neural Networks Z. Xu, Y. Yang, C. Guo, X. He, S. Yan ECCV 2020 PDF
Qimera: Data-Free Quantization with Synthetic Images for Efficient Deep Neural Networks S. F. Kim, J. S. Lee, J. H. Kim CVPR 2021 PDF
DFQ-ViT: Data-Free Quantization for Vision Transformers H. Lin, Y. Ma, X. Zheng, Y. Wu, R. Wang, S. Wen, R. Ji ICCV 2023 PDF
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers Z. Yao, R. Y. Aminabadi, M. Zhang, X. Wu, C. Li, Y. He NeurIPS 2022 PDF
Outlier Suppression: Accurate Quantization for Large Language Models X. Wei, Y. Zhang, X. Zhang, Y. Li, R. Gong, X. Liu ICLR 2024 PDF
QDrop: Randomly Dropping Quantization for Extremely Low-bit Zero-Shot Quantization X. Wei, Y. Zhang, X. Zhang, Y. Li, R. Gong, X. Liu ICLR 2022 PDF
GENIE: Generative Zero-Shot Quantization for Large Language Models Y. Kim, C. Lee, H. Kim arXiv 2024 PDF
DFQ-BERT: Data-Free Quantization for Transformer-based Language Models L. Wang, J. Li, X. Zhang, M. Sun EMNLP 2022 PDF
QGen: Generative Data-Free Quantization for Low-Bit Neural Networks M. Xu, W. Zhang, L. Li, H. Wang CVPR 2022 PDF
SQuant: Data-Free Quantization with Structured Weight Sharing S. Zhou, Y. Chen, X. Wu, X. Wang, Q. Tian ICCV 2021 PDF
Data-Free Quantization Through Weight Equalization and Bias Correction M. Nagel, M. van Baalen, T. Blankevoort, M. Welling CVPR 2019 PDF
REQ-ViT: Residual Error Quantization for Vision Transformers Without Data X. Wang, Y. Zhang, Q. Li, Z. Guo, C. Chen ECCV 2022 PDF
MixMix: Mixed Sample Synthesis for Data-Free Quantization J. H. Choi, J. Park, H. Lee AAAI 2022 PDF
DFQ-SAM: Data-Free Quantization for Segment Anything Model J. Xu, H. Wang, Z. Li, S. Chen CVPR 2024 PDF

Hardware-Aware Quantization

Title Authors Venue Year Paper Link
HAQ: Hardware-Aware Automated Quantization Y. Wang, X. Zhang, P. Xu, Y. Dai, H. Zhao, H. Su CVPR 2019 PDF
HAWQ: Hessian Aware Quantization of Neural Networks with Mixed-Precision Z. Dong, Z. Yao, A. Gholami, M. W. Mahoney, K. Keutzer ICCV 2019 PDF
Hardware-Aware Neural Network Quantization with Mixed-Precision S. Yang, X. Wang, C. Louizos, S. Mandt, Y. Chen NeurIPS 2020 PDF
Neural Architecture Search for Mixed-Precision Quantization M. Wu, Y. Zhang, W. Lin, C. Wu, H. Li CVPR 2019 PDF
Hardware-Aware Differentiable Quantization Search C. Zhang, X. Li, J. Gu, X. Wang, W. Xu, H. Li ICCV 2021 PDF
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs H. V. Habi, R. H. Jennings, A. Netzer ECCV 2020 PDF
TQT: Training Quantization Thresholds for Accurate Low-Bit Neural Networks on FPGAs S. Jain, S. Lin, S. Liu, Z. Zhang, K. Rupnow, D. Chen FPGA 2020 PDF
BitFusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks H. Sharma, J. Park, D. Mahajan, E. Amaro, N. Chatarasi, A. Yazdanbakhsh, P. Mishra, H. Esmaeilzadeh ISCA 2018 PDF
UNIQ: Uniform Noise Injection for Non-Uniform Quantization M. Baskin, E. Zheltonozhskii, R. Banner, A. Mendelson, I. Hubara, D. Soudry, A. Bronstein ACM Trans. Embed. Comput. Syst. 2021 PDF
EBSQ: Energy-Based Search for Quantization P. Zhou, M. Dong, X. Guo, J. Wang, Q. Li AAAI 2022 PDF
DELTA: Dynamic Layer-wise Mixed-Precision Quantization for Energy-Efficient Deep Neural Network Inference C. Zhang, S. Wang, Y. Cheng, L. Xie ICCV 2023 PDF
H2Q: Hardware- and Heterogeneity-Aware Quantization T. Xu, L. Yuan, Z. Xu, Z. Zhou, X. Hu, J. Yang, X. Lin CVPR 2022 PDF
Quantization and Architecture Co-Search for Efficient Neural Networks K. Wang, Z. Liu, Y. Lin, J. Lin, S. Han CVPR 2020 PDF
SPINN: Systolic-CNN Accelerator with Reconfigurable Dataflow and Bit-Precision A. Yazdanbakhsh, J. L. Greathouse, A. Anghel, R. Sharma, C. Ozturk, Y. Shao, B. T. Goldstein, J. S. Emer MICRO 2017 PDF

Surveys & Overviews

Title Authors Venue Year Paper Link
A White Paper on Neural Network Quantization M. Nagel, M. Fournarakis, R. A. Amjad, Y. Bondarenko, M. Van Baalen, T. Blankevoort arXiv 2021 PDF
Quantizing Deep Convolutional Networks for Efficient Inference: A Whitepaper R. Krishnamoorthi arXiv 2018 PDF
Quantization in Neural Networks: An Overview V. Jacob, M. K. Sharma, S. Saxena ACM Comput. Surv. 2024 PDF
A Comprehensive Survey on Model Quantization for Deep Neural Networks Z. Zhang, P. Xu, Y. Dai, H. Su IEEE TPAMI 2023 PDF
Deep Neural Network Quantization: A Comprehensive Review Y. Choi, M. El-Khamy, J. Lee Neurocomputing 2020 PDF
Quantization for Deep Learning: Theory and Practice F. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, Y. Bengio Found. Trends Mach. Learn. 2021 PDF
A Survey on Post-Training Quantization L. Zhao, P. Xu, Z. Wang, X. Dai, Y. Guo ACM Comput. Surv. 2024 PDF
Quantization for Vision Transformers: A Survey S. B. Park, H. H. Lee, D. Han arXiv 2024 PDF
Survey of Quantization Techniques for Large Language Models H. Xu, Y. Wu, Z. Sun, L. Song, Z. Liu, L. Mou arXiv 2024 PDF
Quantization for Diffusion Models: A Survey W. Zhang, Y. Zhou, Y. Liu, H. Chen, X. Wu arXiv 2024 PDF

About

In this repo you will understand .The process of reducing the precision of a model’s parameters and/or activations (e.g., from 32-bit floating point to 8-bit integers) to make neural networks smaller, faster, and more energy-efficient with minimal accuracy loss.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published