@article{fastquerycommunicationefficientembedding,
  title = {FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference},
  author = {Chenqi Lin and Tianshi Xu and Zebin Yang and Runsheng Wang and Ru Huang and Meng Li},
  year = {2024},
  eprint = {2405.16241},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.16241v1},
}