作者位次 #3/8MICRO 2026Oral· Low-Bit Quantization for LLM Inference
Software-Hardware Co-Design of Prior-Aware W4A4 Micro-Block Quantization for Robust LLM Inference Across Model Families
Yijian Wei · Tianchang Yang · Sicheng Tao · Miao Hao · Tianyi Liu · Tingting Zhang · Fuxin Zhang · Tmall Group of Alibaba)