Adaptive Row-wise Attention Score Pruning and Compensation for Attention Acceleration

Chia-Chun Wang, Yu-Lin Lin, Ren-Shuo Liu. Adaptive Row-wise Attention Score Pruning and Compensation for Attention Acceleration. In IEEE International Symposium on Circuits and Systems, ISCAS 2026, Shanghai, China, May 24-28, 2026. pages 1924-1928, IEEE, 2026. [doi]

Abstract

Abstract is missing.