@article{transmlamultiheadlatentattentionisall,
  title = {TransMLA: Multi-Head Latent Attention Is All You Need},
  author = {Fanxu Meng and Zengwei Yao and Muhan Zhang},
  year = {2025},
  eprint = {2502.07864},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.07864v2},
}