検索結果 - Yang, Weiling

Demystifying ARM SME to Optimize General Matrix Multiplications 著者: Deng, Chencheng, Yang, Weiling, Fang, Jianbin, Dong, Dezun

全文の入手
全文の入手

HiNa-MoE: High-Performance, Non-Intrusive MoE Inference on CPUs with Matrix Engines 著者: Yang, Weiling, Zhang, Junwen, Dong, Dezun, Fang, Jianbin, Yu, Enda, Bai, Zhe, Deng, Xiaopeng

全文の入手
全文の入手

LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers 著者: Yu, Enda, Dong, Dezun, Zhang, Zhaoning, Bai, Zhe, Yang, Weiling, Wang, Haojie, Li, Dongsheng, Wu, Yongwei, Liao, Xiangke

全文の入手
全文の入手

PDScope: Breaking the Prefill-Decode Seesaw for Memory-Bound MoE Inference 著者: Yu, Enda, Dong, Dezun, Zhang, Zhaoning, Yang, Xiaojian, Yang, Weiling, Ma, Shaonan, Li, Dongsheng, Wu, Yongwei, Liao, Xiangke

全文の入手
全文の入手