作者位次 #2/8MICRO 2026Oral· ML System Interconect
Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling
Jiaqi Yang · Jiayi Li · Yihan Fu · Hongxiao Zhao · Zhan Chen · Qiuping Wu · Yuchao Yang · Bonan Yan
效率与系统OpenReview