@article{beyond24exploringvnmsparsityfor,
  title = {Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs},
  author = {Kang Zhao and Tao Yuan and Han Bao and Zhenfeng Su and Chang Gao and Zhaofeng Sun and Zichen Liang and Liping Jing and Jianfei Chen},
  year = {2024},
  eprint = {2410.16135},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.16135v1},
}