Yüzügüler, Ahmet Caner
- PRESERVE: Prefetching Model Weights and KV-Cache in Distributed LLM Serving
2025/01/14 by Ahmet Caner Yüzügüler, Yüzügüler, Ahmet Caner, Jiawei Zhuang +3 · 5 citations
Computer Science · #Algorithms and Data Compression #Artificial Intelligence (cs.AI) #Distributed #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Network Packet Processing and Optimization #Parallel #Service-Oriented Architecture and Web Services #and Cluster Computing (cs.DC)