HAWQ-V3: Dyadic Neural Network Quantization

2021

Citations in the corpus

• LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale (2022, neutral): “For example, using Hessian information (Dong et al., 2019), step-size quantization (Esser et al., 2019), soft quantization (Gong et al., 2019), mixed-precision via linear programming optimization (Yao et al., 2021), and other learned quantization methods (Zhang et al., 2018; Gholami et al., 2021).”
• NIPQ: Noise Injection Pseudo Quantization for Automated DNN Optimization (2022, methodology): “This goal is achieved via various methods, e.g., RL-based [28, 29, 30], Hessian-based [31, 32, 33], and differentiable [34, 16] algorithms.”
• Q-Diffusion: Quantizing Diffusion Models (2023, methodology): “Post-training Quantization In situations with limited training data or computing resources for the time-consuming quantization-aware fine-tuning process [50], post-training quantization (PTQ) becomes a preferred method of quantization.”
• Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning (2022, unknown): “The former, e.g. AMC [15] or HAQ [41], search for a layer-wise compression policy directly via, for example, reinforcement learning or genetic programming [43], whereas the latter, e.g. HAWQv3 [44] or AdaQuant [19], construct a relaxed version of the overall problem that is then solved exactly.”
• QuIP: 2-Bit Quantization of Large Language Models With Guarantees (2023, methodology): “[31] Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W.”