作者位次 #2/8ACL 2026Poster· Natural Language Processing
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
Hong Huang · Decheng Wu · Qiangqiang Hu · Guanghua Yu · Jinhai Yang · Jianchen Zhu · Xue Liu · Dapeng Wu
摘要
The deployment of Large Language Models (LLMs) on resource-constrained edge devices is increasingly hindered by prohibitive memory and computational requirements. While ternary quantization offers a compelling solution by reducing weights to -1, 0, +1 , current implementations suffer from a funda...