ULSeq-TA: Ultra-Long Sequence Attention Fusion Transformer Accelerator Supporting Grouped Sparse Softmax and Dual-Path Sparse LayerNorm

Jingyu Wang, Lu Zhang, Xueqing Li, Huazhong Yang, Yongpan Liu. ULSeq-TA: Ultra-Long Sequence Attention Fusion Transformer Accelerator Supporting Grouped Sparse Softmax and Dual-Path Sparse LayerNorm. IEEE Trans. on CAD of Integrated Circuits and Systems, 43(3):892-905, March 2024. [doi]

@article{WangZLYL24,
  title = {ULSeq-TA: Ultra-Long Sequence Attention Fusion Transformer Accelerator Supporting Grouped Sparse Softmax and Dual-Path Sparse LayerNorm},
  author = {Jingyu Wang and Lu Zhang and Xueqing Li and Huazhong Yang and Yongpan Liu},
  year = {2024},
  month = {March},
  doi = {10.1109/TCAD.2023.3329039},
  url = {https://doi.org/10.1109/TCAD.2023.3329039},
  researchr = {https://researchr.org/publication/WangZLYL24},
  cites = {0},
  citedby = {0},
  journal = {IEEE Trans. on CAD of Integrated Circuits and Systems},
  volume = {43},
  number = {3},
  pages = {892-905},
}