@article{costoptimalgroupedqueryattentionforlong,
  title = {Cost-Optimal Grouped-Query Attention for Long-Context Modeling},
  author = {Yingfa Chen and Yutong Wu and Chenyang Song and Zhen Leng Thai and Xingyu Shen and Xu Han and Zhiyuan Liu and Maosong Sun},
  year = {2025},
  eprint = {2503.09579},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.09579v2},
}