@article{flightllmefficientlargelanguagemodel, title = {FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs}, author = {Shulin Zeng and Jun Liu and Guohao Dai and Xinhao Yang and Tianyu Fu and Hongyi Wang and Wenheng Ma and Hanbo Sun and Shiyao Li and Zixiao Huang and Yadong Dai and Jintao Li and Zehao Wang and Ruoyu Zhang and Kairui Wen and Xuefei Ning and Yu Wang}, year = {2024}, eprint = {2401.03868}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.03868v2}, }