@article{acasestudyincudakernelfusion,
  title = {A Case Study in CUDA Kernel Fusion: Implementing FlashAttention-2 on NVIDIA Hopper Architecture using the CUTLASS Library},
  author = {Ganesh Bikshandi and Jay Shah},
  year = {2023},
  eprint = {2312.11918},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.11918v1},
}