谷歌浏览器插件
订阅小程序
在清言上使用

SASDenSebLE: A Compact Vision Transformer Inference Architecture with Saturation-Approximate Softmax Dataflow Enabling Sequence-Parallelism Boosted Layer-Fusion Execution

Liu He,Yujin Wang, Zongle Huang, Shupei Fan,Chen Tang, Shuyuan Zhang, Luchang Lei,Huazhong Yang,Yongpan Liu,Hongyang Jia

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems(2025)

引用 0|浏览1
关键词
Transformer,SW-HW Co-design,Approximate Softmax,Scalability
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要