
面向Transformer模型边缘端部署的常用激活函数高精度轻量级量化推理方法
杨赟辉, 程虎, 魏敬和, 刘国柱, 桑贤侦
电子学报 ›› 2024, Vol. 52 ›› Issue (10) : 3301-3311.
面向Transformer模型边缘端部署的常用激活函数高精度轻量级量化推理方法
High-Precision Lightweight Quantization Inference Method for Prevalent Activation Functions in Transformer Models in Edge Device Deployment
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |