FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs.

Xilong Xie Liang Wang 0020 Limin Xiao 0001 Meng Han Lin Sun Shuai Zheng Xiangrong Xu 0002 FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs. 1-7 2025 DATE https://doi.org/10.23919/DATE64628.2025.10993129 conf/date/2025 db/conf/date/date2025.html#XieWXHSZX25