LLMICLR2023AlgoGPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers基于 Hessian 的逐层误差补偿，把大模型权重量化到低比特。
LLMAAAI2024AlgoOWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models感知激活离群值来保护敏感权重列的混合精度量化。
LLMNeurIPS2022AlgoZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers面向大规模 Transformer 的高效低成本训练后量化方案。
LLMICML2020AlgoAdaRound: Up or Down? Adaptive Rounding for Post-Training Quantization从二阶视角推导权重的自适应舍入，取代四舍五入。
LLMICML2021AlgoAdaQuant: Accurate Post Training Quantization With Small Calibration Sets用小校准集做逐层重构的训练后量化方法。