主仓库
01-论文
1bit LLMS
模型量化
无损压缩
异常感知（论文原文）
Atom
AWQ
GPTQ
GPTQ（原文）
KIVI
KVquant
LLM.int8()
nnzip
OBC（高效压缩）
OLAccel
QLoRA
Qserve
Qserve（原文）
SmoothQuant
Tender
Zeroquant
index

原文 OLAccel

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-01.png
Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-02.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-03.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-04.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-05.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-06.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-07.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-08.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-09.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-10.png

Park 等 - 2018 - Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation-zh-11.png

Table Of Contents
原文 OLAccel