EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Unified Compression and Adaptive Layer Voting
EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Unified Compression and Adaptive Layer Voting
复制标题
EDGE-LLM:通过统一压缩和自适应层投票在边缘设备上实现高效的大型语言模型自适应
DOI:
--
复制
发表时间:
2024
期刊:
影响因子:
--
通讯作者:
Lin, Yingyan Celine
中科院分区:
文献类型:
--
作者:
Yu, Zhongzhi;Wang, Zheng;Li, Yuhan;Gao, Ruijie;Zhou, Xiaoya;Bommu, Sreenidhi Reddy;Zhao, Yang Katie;Lin, Yingyan Celine