Luo Mai

Assistant Professor

University of Edinburgh

About Me

I am an Assistant Professor in the School of Informatics at the University of Edinburgh, leading the Large-Scale Machine Learning Systems Group and co-directing the UK EPSRC Centre for Doctoral Training in Machine Learning Systems.

My research focuses on creating scalable, efficient, and reliable computer systems for machine learning and data management. This work has been recognized at major conferences such as OSDI, USENIX ATC, NSDI, CoNEXT, JMLR, ICML, NeurIPS, ECCV, and VLDB, earning awards from Google, Microsoft, Alibaba, and Tencent. I authored the open-source textbook Machine Learning Systems: Design and Implementation and co-founded several popular open-source projects including TensorLayer, HyperPose, TorchOpt and ServerlessLLM.

Prior to Edinburgh, I served as a research associate at Imperial College London, working under Peter Pietzuch and was a visiting researcher at Microsoft Research. My PhD, supervised by Paolo Costa and Alexander L. Wolf, was supported by a Google Fellowship in Cloud Computing.

If you are interested in pursuing a PhD or postdoctoral research with me, please send an email with your CV and a brief description of your proposed research.

Interests

Computer Systems
Machine Learning
Data Management

Education

PhD in Computer Science, 2018

Imperial College London, UK
MRes in Advanced Computing, 2012

Imperial College London, UK

News

ServerlessLLM in OSDI 2024.

TorchOpt becomes a PyTorch Ecosystem Project, and its paper gets in JMLR 2023.

Trilled to be nominated for the Chancellor's Rising Star in Research.

Gear library in ICML 2023.

Ekko system in OSDI 2022

MegBA library in ECCV 2022

Meta RL paper in NeruIPS 2022.

Invited lecture at the Oxford ML summer school

KungFu system in OSDI 2020

Cameo system in NSDI 2021

See all posts

Publications

Leyang Xue, Yao Fu, Zhan Lu, Luo Mai, Mahesh Marina (2024). MoE-Infinity: Activation-Aware Expert Offloading for Efficient MoE Serving. In Arxiv.

PDF Code

Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, Luo Mai (2024). ServerlessLLM: Locality-Enhanced Serverless Inference for Large Language Models. In OSDI.

PDF Code

Jie Ren*, Xidong Feng*, Bo Liu*, Xuehai Pan*, Yao Fu, Luo Mai, Yaodong Yang (2023). TorchOpt: An Efficient Library for Differentiable Optimization. In JMLR.

PDF Code

Hanjing Wang*, Man-Kit Sit*, Congjie He, Ying Wen, Weinan Zhang, Jun Wang, Yaodong Yang, Luo Mai (2023). GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models. In ICML.

PDF Code

Zeyuan Tan*, Xiulong Yuan*, Congjie He*, Man-Kit Sit, Guo Li, Xiaoze Liu, Baole Ai, Kai Zeng, Peter Pietzuch, Luo Mai (2023). Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness. In Arxiv.

PDF Code

Chijun Sima*, Yao Fu*, Man-Kit Sit, Liyi Guo, Xuri Gong, Feng Lin, Junyu Wu, Yongsheng Li, Haidong Rong, Pierre-Louis Aublin, Luo Mai (2022). Ekko: A Large-Scale Deep Learning Recommender System with Low-Latency Model Update. In USENIX OSDI.

PDF

Bo Liu, Xidong Feng, Jie Ren, Luo Mai, Rui Zhu, Haifeng Zhang, Jun Wang, Yaodong Yang (2022). A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning. In NeurIPS.

PDF

Jie Ren*, Wenteng Liang*, Ran Yan, Luo Mai, Shiwen Liu, Xiao Liu (2022). MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment. In ECCV.

PDF Code

Le Xu, Shivaram Venkataraman, Indranil Gupta, Luo Mai, Rahul Potharaju (2021). Move Fast and Meet Deadlines: Fine-grained Real-time Stream Processing with Cameo. In USENIX NSDI.

PDF

Zihan Ding, Tianyang Yu, Yanhua Huang, Hongming Zhang, Guo Li, Quancheng Guo, Luo Mai, Hao Dong (2021). Efficient Reinforcement Learning Development with RLzoo. In ACM Multimedia (Open-source Software Competition).

PDF Code

See all publications