@article{gatedlinearattentiontransformerswith,
  title = {Gated Linear Attention Transformers with Hardware-Efficient Training},
  author = {Songlin Yang and Bailin Wang and Yikang Shen and Rameswar Panda and Yoon Kim},
  year = {2023},
  eprint = {2312.06635},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.06635v6},
}