HotaQ: Hardware Oriented Token Adaptive Quantization for Large Language Models
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems（2024）
关键词
Large Language Models (LLMs),Hardware and Software Co-design,Quantization,Mobile,FPGAs
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