Kwon, Woosuk

1. Efficient Memory Management for Large Language Model Serving with PagedAttention
   2023/09/12 by Woosuk Kwon, Kwon, Woosuk, Zhuohan Li +15 · 4 voices · 1374 citations
   Computer Science · #Caching and Content Delivery #Software System Performance and Reliability #Topic Modeling #cs.DC #cs.LG
2. Gemma 3 Technical Report
   2025/03/25 by Gemma Team, Aishwarya Kamath, Johan Ferret +418 · 3 voices · 467 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.AI #cs.CL
3. Gemma 2: Improving Open Language Models at a Practical Size
   2024/07/31 by Gemma Team, Morgane Rivière, Riviere, Morgane +292 · 308 citations
   Computer Science · #Natural Language Processing Techniques
4. A Fast Post-Training Pruning Framework for Transformers
   2022/03/29 by Woosuk Kwon, Sehoon Kim, Kwon, Woosuk +9 · 20 citations
   Computer Science · #Advanced Neural Network Applications #Generative Adversarial Networks and Image Synthesis #Domain Adaptation and Few-Shot Learning
5. Learned Token Pruning for Transformers
   2021/07/02 by Kim, Sehoon, Shen, Sheng, Thorsley, David +4 · 15 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences
6. TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
   2024/06/20 by Xiaoxuan Liu, Liu, Xiaoxuan, Park, Jongseok +19 · 4 citations
   Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Performance (cs.PF) #Topic Modeling
7. Jenga: Effective Memory Management for Serving LLM with Heterogeneity
   2025/03/24 by Zhang, Chen, Du, Kuntai, Liu, Shu +10 · 4 citations
   #Distributed #FOS: Computer and information sciences #Parallel #and Cluster Computing (cs.DC)
8. APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving
   2024/11/26 by Lin, Yi-Chien, Kwon, Woosuk, Pineda, Ronald +1 · 2 citations
   #Distributed #FOS: Computer and information sciences #Parallel #and Cluster Computing (cs.DC)