作者位次 #2/6RTSS 2026Oral· Real-Time & Embedded Systems
RT-MoE: Real-Time Expert Management for Memory-Constrained MoE Decoding
Ziwei Song · Ruoxiang Li · Fei Guan · Jen-Ming Wu · Jason Xue · Nan Guan
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Ziwei Song · Ruoxiang Li · Fei Guan · Jen-Ming Wu · Jason Xue · Nan Guan
Ziyang Wang · Jiangfeng Xiao · Chuan Xiao · Ruoxiang Li · Rui Mao · Jianbin Qin
Large language models (LLMs) are expensive to serve because dense FFN blocks, multi-head attention, and KV caches dominate memory, making structured pruning a natural way to reduce serving costs under tight parameter and memory budgets. We present GRASPrune, a global budgeted structured pruning f...