作者位次 #6/14MICRO 2026Oral· 3D-Stacked & PIM Architectures for LLM/MoE Serving
ATLAS: Pathfinding Efficient 3D-DRAM-based LLM Inference Accelerator Design via Silicon-Proven Full-Stack Simulation
Cong Li · Chenhao Xue · Yi Ren · Xiping Dong · Yu Cheng · Yinbo Hu · Fujun Bai · Yixin Guo · Xiping Jiang · Qiang Wu · Tmall Group of Alibaba) · Zhe Cheng · Yuan Xie · Guangyu Sun