Towards Efficient LLM Inference via Collective and Adaptive Speculative Decoding.

Siqi Wang, Hailong Yang, Xuezhu Wang, Tongxuan Liu, Pengbo Wang, Yufan Xu, Xuning Liang, Kejie Ma, Tianyu Feng, Xin You, Ruihao Gong, Rui Wang, Zhongzhi Luan, Yi Liu, Depei Qian

Browse the full SC paper archive.