未登录
分享
收藏
分享
收藏FlashAttention-T: Towards Fully Tensorized Attention by Exploiting Tensor-Vector ParallelismFlashAttention-T:通过利用张量-向量并行实现完全张量化注意力
Xu, Jianxing; Wen, Yuanbo; Bi, Jun; Xu, Ruibai; Xu, Guanglin; Zhang, Rui; Li, Wei; Li, Ling; Chen, Tianshi; Guo, Qi; Chen, Yunji
分享
收藏Swift: High Parallelism Program Generation of Tensor Operators for Accelerating Deep Learning InferenceSwift: 加速深度学习推理的张量算子高并行度程序生成
Yu, Xiyue; Bi, Jun; Wen, Yuanbo; Xu, Jianxing; Huang, Di; Guo, Jiaming; Li, Wei; Du, Zidong; Li, Jing; Chen, Tianshi; Guo, Qi
分享
收藏
分享
收藏A matrix for estimating the unfrozen water content of freezing soils用于估算冻结土壤中未冻水含量的矩阵
Bi, Jun; Wang, Guoxu; Mu, Wenxuan; Wen, Haiyan; Pei, Wansheng; Zhang, Qiyong; Yang, Sheng; Mao, Mengyao; Lin, Gaochao; Wang, Chong
分享
收藏Efficient and Fast High-Performance Library Generation for Deep Learning Accelerators
Bi, Jun; Wen, Yuanbo; Li, Xiaqing; Zhao, Yongwei; Guo, Yuxuan; Zhou, Enshuai; Hu, Xing; Du, Zidong; Li, Ling; Chen, Huaping; Chen, Tianshi; Guo, Qi
分享
收藏
分享
收藏
分享
收藏