About Me

Hi, I am Lily (Xiaoxuan) Liu. I am a CS PhD student from UC Berkeley. I am affiliated with Sky Lab (formerly known as RISE/AMP Lab). I am fortunately advised by Professor Alvin Cheung and Professor Ion Stoica. I got my master’s from CMU, working with amazing Andy and Huanchen. I did my undergraduate in PKU.

Research Interest

I am broadly interested in database and machine learning system research. Concretely, I am interested in building fast, cost-efficient LLM systems. I am fortunate to learn from my colleagues and become part of the vllm team.

Selected Publication and Manuscripts

• Optimizing Speculative Decoding for Serving Large Language Models Using Goodput, arxiv, 2024.
  Xiaoxuan Liu, Cade Daniel, Langxiang Hu, Woosuk Kwon, Zhuohan Li, Xiangxi Mo, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang
• Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity, arxiv, 2024. [code]
  Tyler Griggs^*, Xiaoxuan Liu^*, Jiaxiang Yu, Doyoung Kim, Wei-Lin Chiang, Alvin Cheung, Ion Stoica
• Online Speculative Decoding, ICML 2024. [code][blog]
  Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang
• Leveraging Application Data Constraints to Optimize Database-Backed Web Applications, VLDB 2023. [code]
  Xiaoxuan Liu, Shuxian Wang, Mengzhu Sun, Sicheng Pan, Ge Li, Siddharth Jha, Cong Yan, Junwen Yang, Shan Lu, Alvin Cheung.
• GACT: Activation Compressed Training for Generic Network Architectures, ICML 2022. [code][slides][talk]
  Xiaoxuan Liu, Lianmin Zheng, Dequan Wang, Yukuo Cen, Weize Chen, Xu Han, Jianfei Chen, Zhiyuan Liu, Jie Tang, Joey Gonzalez, Michael Mahoney, Alvin Cheung.
• Order-Preserving Key Compression for In-Memory Search Trees, SIGMOD 2020. [code][slides][talk]
  Huanchen Zhang, Xiaoxuan Liu, David Anderson, Michael Kaminsky, Kimberly Keeton, Andrew Pavlo.

Papers that die silently I do randomly

• An Evaluation of Memory Optimization Methods for Training Neural Networks, arxiv, 2023
  Xiaoxuan Liu, Siddharth Jha, Alvin Cheung