@article{bitnetcppefficientedgeinferencefor,
  title = {Bitnet.cpp: Efficient Edge Inference for Ternary LLMs},
  author = {Jinheng Wang and Hansong Zhou and Ting Song and Shijie Cao and Yan Xia and Ting Cao and Jianyu Wei and Shuming Ma and Hongyu Wang and Furu Wei},
  year = {2025},
  eprint = {2502.11880},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.11880v1},
}