2024

2024-116

论文阅读习惯

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

OneBit: Towards Extremely Low-bit Large Language Models

矩阵奇异值分解SVD

梯度估计STE

Welcome to bg51717's Wiki and Blog

2024-104

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

拉格朗日乘数法解条件极值

大模型量化~GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

llm.int8