作者位次 #2/5EuroSys 2026Oral· Computer Systems
PiLLM: Resource-Efficient LLM Inference Using Workload Prediction
Yunqian Fan · Shihao Bai · Ruihao Gong · Zaijun Wang · Rui Fan
效率与系统OpenReview
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。
Yunqian Fan · Shihao Bai · Ruihao Gong · Zaijun Wang · Rui Fan
Lingkun Long · Yushi Huang · Shihao Bai · Ruihao Gong · Jun Zhang · Ao Zhou · Jianlei Yang
Diffusion Large Language Models (dLLMs) deliver strong long-context processing capability in a non-autoregressive decoding paradigm. However, the considerable computational cost of bidirectional full attention limits the inference efficiency. Although sparse attention is promising, existing metho...