DynSpAttn: Efficient Attention via Dual-Side Dynamic Sparsity on Sparse Tensor Cores

Xiangrui Yu, Ruibo Fan, ZeYu Li, Weile Luo, Gu Gong, Xiaowen Chu 0001. DynSpAttn: Efficient Attention via Dual-Side Dynamic Sparsity on Sparse Tensor Cores. In Proceedings of the 40th ACM International Conference on Supercomputing, ICS 2026, Belfast, United Kingdom, July 6-9, 2026. pages 1053-1064, ACM, 2026. [doi]

Authors

Xiangrui Yu

This author has not been identified. Look up 'Xiangrui Yu' in Google

Ruibo Fan

This author has not been identified. Look up 'Ruibo Fan' in Google

ZeYu Li

This author has not been identified. Look up 'ZeYu Li' in Google

Weile Luo

This author has not been identified. Look up 'Weile Luo' in Google

Gu Gong

This author has not been identified. Look up 'Gu Gong' in Google

Xiaowen Chu 0001

This author has not been identified. Look up 'Xiaowen Chu 0001' in Google