FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection
Ziyu Huang · Yangjie Zhou · Zihan Liu · Xinhao Luo · Yijia Diao · Minyi Guo · Jidong Zhai · Yu Feng · Chen Zhang · Anbang Wu · Jingwen Leng
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Ziyu Huang · Yangjie Zhou · Zihan Liu · Xinhao Luo · Yijia Diao · Minyi Guo · Jidong Zhai · Yu Feng · Chen Zhang · Anbang Wu · Jingwen Leng
Yitong Ding · Jiawei Huang · Renyang Guan · Zihan Liu · Yangjie Zhou · Yu Feng · Shixuan Sun · Jingwen Leng · Mingyi Guo · Jian Weng
Xing Ma · Yangjie Zhou · Wu Sun · Zihan Liu · Jingwen Leng · Yun Lin · Shixuan Sun · Minyi Guo · Jin Song Dong
Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and compilers trade performance for flexibility, while expert-written kernels achieve high efficienc...