作者位次 #5/15MICRO 2026Oral· Low-Bit Quantization for LLM Inference
SkewQ: Skewness-Aware Cross-Layer Quantization for Efficient LLM Inference via Software-Hardware Co-Design
Wenju Zhao · Jianhui Yue · Pengcheng Yao · Jiaqi Zhai · Yundong Zhang · Yu Huang · Shunsen Lv · Bing Zhu · Zhongtian Long · Long Zheng · Chencheng Ye · Lihong Gu · Jingling Xue · Hai Jin · Xiaofei Liao