@article{towardseconomicalinferenceenabling,
  title = {Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs},
  author = {Tao Ji and Bin Guo and Yuanbin Wu and Qipeng Guo and Lixing Shen and Zhan Chen and Xipeng Qiu and Qi Zhang and Tao Gui},
  year = {2025},
  eprint = {2502.14837},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.14837v1},
}