EdgeSpec: Distributed Speculative Decoding for Large Language Models at Edge.
Yulin Chen, Meng Tian, Chao Qiu, Xiaofei Wang, Haipeng Yao, Yuan He, Yunhao Liu
Browse the full INFOCOM paper archive.
Yulin Chen, Meng Tian, Chao Qiu, Xiaofei Wang, Haipeng Yao, Yuan He, Yunhao Liu
Browse the full INFOCOM paper archive.