Zhao, Liangyu

1. NanoFlow: Towards Optimal Large Language Model Serving Throughput
   2024/08/22 by Kan Zhu, Zhu, Kan, Yufei Gao +28 · 33 citations
   Computer Science · #Distributed #FOS: Computer and information sciences #Parallel #Topic Modeling #and Cluster Computing (cs.DC)
2. Efficient Direct-Connect Topologies for Collective Communications
   2022/02/07 by Liangyu Zhao, Siddharth Pal, Zhao, Liangyu +12 · 6 citations
   Computer Science · Engineering · #Advanced Optical Network Technologies #Distributed #FOS: Computer and information sciences #Interconnection Networks and Systems #Machine Learning (cs.LG) #Networking and Internet Architecture (cs.NI) #Opportunistic and Delay-Tolerant Networks #Parallel #and Cluster Computing (cs.DC)
3. AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly
   2021/05/22 by Yuchen Jin, Tianyi Zhou, Jin, Yuchen +11 · 3 citations
   Computer Science · #Machine Learning and Data Classification #Machine Learning and Algorithms #Gaussian Processes and Bayesian Inference
4. Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs
   2025/02/17 by Kan Zhu, Tian Tang, Zhu, Kan +16 · 6 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Data Mining Algorithms and Applications #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG)
5. FAST: An Efficient Scheduler for All-to-All GPU Communication
   2025/05/14 by Lei, Yiran, Lee, Dongjoo, Zhao, Liangyu +9 · 4 citations
   #Distributed #FOS: Computer and information sciences #Networking and Internet Architecture (cs.NI) #Parallel #and Cluster Computing (cs.DC)
6. Efficient All-to-All Collective Communication Schedules for Direct-Connect Topologies
   2023/09/24 by Prithwish Basu, Liangyu Zhao, Basu, Prithwish +9 · 1 citation
   Computer Science · Engineering · #Advanced Memory and Neural Computing #Distributed #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Interconnection Networks and Systems #Networking and Internet Architecture (cs.NI) #Parallel #and Cluster Computing (cs.DC)
7. ForestColl: Throughput-Optimal Collective Communications on Heterogeneous Network Fabrics
   2024/02/09 by Liangyu Zhao, Zhao, Liangyu, Saeed Maleki +9 · 1 citation
   Computer Science · #Distributed #FOS: Computer and information sciences #Interconnection Networks and Systems #Machine Learning (cs.LG) #Networking and Internet Architecture (cs.NI) #Opportunistic and Delay-Tolerant Networks #Parallel #Software-Defined Networks and 5G #and Cluster Computing (cs.DC)