Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree

Gao et al. "Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I22.34566

[Gao et al. "Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/gao2025aaai-falcon/) doi:10.1609/AAAI.V39I22.34566

@inproceedings{gao2025aaai-falcon,
  title     = {{Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree}},
  author    = {Gao, Xiangxiang and Xie, Weisheng and Xiang, Yiwei and Ji, Feng},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {23933-23941},
  doi       = {10.1609/AAAI.V39I22.34566},
  url       = {https://mlanthology.org/aaai/2025/gao2025aaai-falcon/}
}