23.8 an 88.36TOPS/W Bit-Level-Weight-Compressed Large-Language-Model Accelerator with Cluster-Aligned INT-FP-GEMM and Bi-Dimensional Workflow Reformulation

Yubin Qin,Yang Wang,Jiachen Wang, Zhiwei Lin, Yushu Zhao,Shaojun Wei,Yang Hu,Shouyi Yin

IEEE International Solid-State Circuits Conference（2025）

引用 0|浏览26

关键词

Large Language Models,Nonlinear Function,Energy Conservation,Softmax,Taylor Series,Taylor Expansion,Power Factor,Low Precision,Load Data,Manhattan Distance,Trigonometric Functions,Edge Devices,Efficient Deployment,Powers Of 3,Network-on-chip,Traditional Transformation

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要