EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the Edge.
Xuan ShenZhenglun KongChangdi YangZhaoyang HanLei LuPeiyan DongCheng LyuChih-hsiang LiXuehang GuoZhihao ShuWei NiuMiriam LeeserPu ZhaoYanzhi WangPublished in: CoRR (2024)