QIAN LI 
About Me
I am a co-founder at DBOS, Inc. Previously, I completed my Ph.D. in Computer Science at Stanford University. I have broad interests in computer systems, databases, and architecture. My Ph.D. research focused on efficient management of emerging new workloads in cloud platforms. In graduate school, I was advised by Christos Kozyrakis and worked closely with Matei Zaharia and Mike Stonebraker on the DBMS-oriented Operating System (DBOS) academic project, which is the foundation of our startup.
I earned my M.S. in Computer Science at Stanford University in 2019. Prior to joining Stanford, I received my B.Sc. in Computer Science and Technology from Peking University in 2017.
News
- November 20, 2024 - Databases and Serverless are Made for Each Other (Talk at SF Systems Meetup)
- November 5, 2024 - Why Durable Execution Should Be Lightweight (w/ Peter Kraft)
- October 1, 2024 - Time Travel Queries with Postgres (Talk at PGConf NYC)
- May 15, 2024 - How We Manage Customer Billing in <500 Lines of Typescript
- August 28, 2023 - The Time Traveler's Guide to Distributed Applications
- December 9, 2022 - Your Infrastructure Should Know More About Your Database (w/ Peter Kraft)
- September 3, 2022 - DBOS: A Database-Oriented Operating System (w/ Peter Kraft)
Selected Publications
* denotes equal contribution | Full list of publications
Transactions and Serverless are Made for Each Other
Qian Li, Peter Kraft
Communications of the ACM, Posted Nov 20 2024.
Transactions and Serverless are Made for Each Other
Qian Li, Peter Kraft
ACM Queue, Volume 22, Issue 3.
R3: Record-Replay-Retroaction for Database-Backed Applications
Qian Li, Peter Kraft, Michael Cafarella, Çağatay Demiralp ,Goetz Graefe, Christos Kozyrakis, Michael Stonebraker, Lalith Suresh, Xiangyao Yu, Matei Zaharia.
VLDB 2023.
Epoxy: ACID Transactions Across Diverse Data Stores
Peter Kraft, Qian Li, Xinjing Zhou, Peter Bailis, Michael Stonebraker, Xiangyao Yu, Matei Zaharia.
VLDB 2023.
Apiary: A DBMS-Integrated Transactional Function-as-a-Service Framework
Peter Kraft*, Qian Li*, Kostis Kaffes, Athinagoras Skiadopoulos, Deeptaanshu Kumar, Danny Cho, Jason Li, Robert Redmond, Nathan Weckwerth, Brian Xia, Peter Bailis, Michael Cafarella, Goetz Graefe, Jeremy Kepner, Christos Kozyrakis, Michael Stonebraker, Lalith Suresh, Xiangyao Yu, Matei Zaharia.
arXiv Preprint.
Transactions Make Debugging Easy
Qian Li, Peter Kraft, Michael Cafarella, Çağatay Demiralp, Goetz Graefe, Christos Kozyrakis, Michael Stonebraker, Lalith Suresh, Matei Zaharia.
CIDR 2023.
A Progress Report on DBOS: A DBMS-Oriented Operating System
Qian Li*, Peter Kraft*, Kostis Kaffes*, Athinagoras Skiadopoulos, Deeptaanshu Kumar, Jason Li, Michael Cafarella, Goetz Graefe, Jeremy Kepner, Christos Kozyrakis, Michael Stonebraker, Lalith Suresh, Matei Zaharia.
CIDR 2022.
DBOS: A DBMS-oriented Operating System
Athinagoras Skiadopoulos*, Qian Li*, Peter Kraft*, Kostis Kaffes*, Daniel Hong, Shana Mathew, David Bestor, Michael Cafarella, Vijay Gadepally, Goetz Graefe, Jeremy Kepner, Christos Kozyrakis, Tim Kraska, Michael Stonebraker, Lalith Suresh, Matei Zaharia.
VLDB 2022. (vision paper)
INFaaS: Automated Model-less Inference Serving
Francisco Romero*, Qian Li*, Neeraja J. Yadwadkar, Christos Kozyrakis.
In Proceedings of the 2021 USENIX Annual Technical Conference (ATC'21), Virtual, July 2021.
(Awarded Best Paper!)
RAMBO: Resource Allocation for Microservices Using Bayesian Optimization
Qian Li, Bin Li, Pietro Mercati, Ramesh Illikkal, Charlie Tai, Michael Kishinevsky, Christos Kozyrakis.
IEEE Computer Architecture Letters (CAL), Volume: 20, Issue: 1, Jan. - June 1 2021.
From Laptop to Lambda: Outsourcing Everyday Jobs to Thousands of Transient Functional Containers
Sadjad Fouladi, Francisco Romero, Dan Iter, Qian Li, Shuvo Chatterjee, Christos Kozyrakis, Matei Zaharia, and Keith Winstein.
In Proceedings of the 2019 USENIX Annual Technical Conference (ATC ’19), Renton, WA, USA, July 2019.
A Case for Managed and Model-less Inference Serving
Neeraja J. Yadwadkar, Francisco Romero, Qian Li, Christos Kozyrakis.
In Proceedings of the 17th Workshop on Hot Topics in Operating Systems (HotOS '19), Bertinoro, Italy, May 2019.
[the morning paper blog]
Arachne: Core-Aware Thread Management
Henry Qin, Qian Li, Jacqueline Speiser, Peter Kraft, John Ousterhout.
In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’18), Carlsbad, CA, USA, October 2018.
Exploiting Sparsity to Accelerate Fully Connected Laye
rs of CNN-based Applications on Mobile SoCs
Xinfeng Xie, Dayou Du, Qian Li, Yun Liang, Wai Teng Tang, Zhong Liang Ong, Mian Lu, Huynh Phung Huynh, Siow Mong Rick.
ACM Transactions on Embedded Computing Systems (TECS), Volume 17 Issue 2, Article No. 37, Dec
ember 2017.
Enabling High Performance Deep Learning Networks on
Embedded Systems
Qian Li, Qingcheng Xiao, Yun Liang.
The 43rd Annual Conference of the IEEE Industrial Electronics Society (IEC
ON ’17), Beijing, China, November 2017. (invited paper)
Learning from the Ubiquitous Language: An Empirical Analysis of Emoji Usage of Smartphone Users
Xuan Lu, Wei Ai, Xuanzhe Liu, Qian Li, Ning Wang, Gang Huang, Qiaozhu Mei.
In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '16), Heidelberg, Germany, September 2016.
Research
A major part of my research was DBOS, where we propose a radically new cluster-OS design based on data-centric architecture: all operating system state should be represented uniformly as database tables, and operations on this state should be made via queries from otherwise stateless tasks. This design makes it easy to scale and evolve the OS without whole-system refactoring. Particularly, I have built Apiary (arXiv), a database-backed FaaS platform and R3 (VLDB'23, CIDR'23), a time-travel debugger.
[project website]
I have built INFaaS: an INFerence-as-a-Service platform that makes ML inference accessible and easy-to-use by abstracting resource management and model selection. By leveraging heterogeneous compute resources and efficient sharing, INFaaS achieves high throughput and low SLO violations while minimizing cost.
[project website]
Arachne is a new user-level implementation of threads that provides both low latency and high throughput for applications with extremely short-lived threads. I used Arachne to restructure Memcached that reduces performance interference and provides finer-grain load-balancing; achieved lower tail latency and higher SLO-compliant throughput.
[Memcached-A code] [benchmark code]
Teaching
Electrical Engineering · Stanford
Computer Science · Stanford
School of EECS · PKU
School of EECS · PKU
Awards
- USENIX ATC Best Paper Award (INFaaS), 2021
- Cadence Women in Technology Scholarship, 2019
- Stanford School of Engineering Fellowship, 2017
- Outstanding Graduate Award of Beijing, China, 2017
- National Scholarship, China, 2016
- National Undergraduate Research and Innovation Fund, China, 2015
- Tung OOCL Scholarship, 2015
- Okamatsu Scholarship, 2014