Myunghyun Rhee
- HPU: High-Bandwidth Processing Unit for Scalable, Cost-effective LLM Inference via GPU Co-processing
2025/04/18 by Myunghyun Rhee, Rhee, Myunghyun, Joonseop Sim +14 · 2 citations
Computer Science · Engineering · Physics and Astronomy · #Advanced Algorithms and Applications #Advanced Data Storage Technologies #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Distributed #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Magnetic confinement fusion research #Parallel #and Cluster Computing (cs.DC)
- NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement
2026/07/29 by Sookyung Choi, Seungyong Lee, Kangkyu Park +11
Computer Science · #cs.AR