Haoran Qiu

Ph.D. in Computer Science

University of Illinois, Urbana-Champaign (UIUC)

Biography

I have joined Microsoft Azure Research – Systems (AzRS).

I obtained my PhD in Computer Science at UIUC, advised by Prof. Ravishankar K. Iyer. I am affiliated with the DEPEND research group in the Coordinated Science Laboratory.

I am broadly interested in distributed systems, with a focus on performance, resilience, and sustainability. My recent research focuses on designing and integrating ML/RL-based solutions seamlessly (i.e., efficiency, robustness, and reliability) with algorithm-system co-design into the design and management of production cloud systems:
➪ [ATC24, AIOps24a, SoCC24] Energy-efficient, SLO-aware interactive LLM serving
➪ [ATC23, NeurIPS23, MLSys24] Robust, at-scale ML model deployment in cloud systems
➪ [SoCC22, NeurIPS22] Multi-tenant serverless computing resource management
➪ [OSDI20] Fine-grained resource management for cloud microservices

Before joining UIUC, I got my bachelor’s degree in Computer Science from the University of Hong Kong (HKU). I was advised by Prof. Heming Cui at the HKU Systems Software Group.

In the past, I have worked with IBM Research, Google SRG, and Microsoft Research.

You can find my CV here and my PhD dissertation here.

Interests

ML/DL/LLM Systems
Distributed Systems
Cloud Computing
ML for Systems

Education

Ph.D. in Computer Science, 2024
University of Illinois, Urbana-Champaign
B.Eng in Computer Science, 2019
University of Hong Kong
Visiting Student in College of Engineering, 2018
University of Wisconsin-Madison

Publications

ATC'24
Power-aware Deep Learning Model Serving with µ-Serve.
Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Saurabh Jha, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 2024 USENIX Annual Technical Conference (ATC 2024).

PDF Preprint Code Slides Video

MLSys'24
FLASH: Fast Model Adaptation in ML-Centric Cloud Platforms.
Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 7th Annual Conference on Machine Learning and Systems (MLSys 2024).

PDF Code Slides

DSN'24
When Green Computing Meets Performance and Resilience SLOs.
Haoran Qiu, Weichao Mao, Chen Wang, Saurabh Jha, Hubertus Franke, Chandra Narayanaswami, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN 2024 Distrupt Track).
Selected at the NSF Workshop on Sustainable Computing for Sustainability 2024

PDF DOI

AIOps'24 @ASPLOS'24
Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction.
Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Saurabh Jha, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 5th International Workshop on Cloud Intelligence / AIOps (AIOps 2024).

PDF Code

AIOps'24 @ASPLOS'24
QLM: Queue Management for Large Language Model Serving.
Archit Patke, Dhemath Reddy, Saurabh Jha, Christian Pinto, Haoran Qiu, Shengkun Cui, Chandra Narayanaswami, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer
In Proceedings of the 5th International Workshop on Cloud Intelligence / AIOps (AIOps 2024).

PDF Preprint

ISCA'24
SmartOClock: Workload- and Risk-Aware Overclocking in the Cloud.
Jovan Stojkovic, Pulkit Misra, Íñigo Goiri, Sam Whitlock, Esha Choukse, Mayukh Das, Chetan Bansal, Jason Lee, Zoey Sun, Haoran Qiu, Reed Zimmermann, Savyasachi Samal, Brijesh Warrier, Ashish Raniwala, Ricardo Bianchini
In Proceedings of the 51st International Symposium on Computer Architecture (ISCA 2024).

PDF

MLSys Workshop @NeurIPS'23
On the Promise and Challenges of Foundation Models for Learning-based Cloud Systems Management.
Haoran Qiu, Weichao Mao, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 7th Workshop on ML for Systems at NeurIPS 2023 (MLSys Workshop 2023).
Selected for Spotlight Presentation

PDF Slides

MLSys Workshop @NeurIPS'23
PARM: Adaptive Resource Allocation for Datacenter Power Capping.
Haoran Qiu, Linghao Zhang, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer
In Proceedings of the 7th Workshop on ML for Systems at NeurIPS 2023 (MLSys Workshop 2023).

PDF

ATC'23
AWARE: Automate Workload Autoscaling with Reinforcement Learning in Production Cloud Systems.
Haoran Qiu, Weichao Mao, Chen Wang, Hubertus Franke, Alaa Youssef, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 2023 USENIX Annual Technical Conference (ATC 2023).
Artifact Available, Functional, Reproduced
Selected for Presentation at KubeCon + CloudNativeCon North America 2023

PDF Code Slides Video

NeurIPS'23
Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity.
Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer, Tamer Başar
In Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023).

PDF

SoCC'22
SIMPPO: A Scalable and Incremental Online Learning Framework for Serverless Resource Management.
Haoran Qiu, Weichao Mao, Archit Patke, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 13th ACM Symposium on Cloud Computing (SoCC 2022).

PDF Preprint Slides DOI

NeurIPS'22
A Mean-Field Game Approach to Cloud Resource Management with Function Approximation.
Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer, Tamer Başar
In Proceedings of the 36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022).

PDF Slides Video

CompSys Workshop @IPDPS'22
Evaluating Hardware Memory Disaggregation under Delay and Contention.
Archit Patke, Haoran Qiu, Saurabh Jha, Srikumar Venugopal, Michele Gazzetti, Christian Pinto, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer
In Proceedings of the 1st Workshop on Composable Systems Co-located with IPDPS 2022 (COMPSYS 2022).
Best Presentation Award

PDF Video DOI

EuroMLSys Workshop @EuroSys'22
Reinforcement Learning for Resource Management in Multi-tenant Serverless Platforms.
Haoran Qiu, Weichao Mao, Archit Patke, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Tamer Başar, Ravishankar K. Iyer
In Proceedings of the 2nd European Workshop on Machine Learning and Systems Co-located with EuroSys 2022 (EuroMLSys 2022).

PDF Slides Video DOI

WoSC @Middleware'21
Is Function-as-a-Service a Good Fit for Latency-Critical Services?.
Haoran Qiu, Saurabh Jha, Subho S. Banerjee, Chen Wang, Hubertus Franke, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer
In Proceedings of the 7th International Workshop on Serverless Computing Co-located with ACM/IFIP Middleware 2021 (WoSC7).

PDF Code Slides Video DOI

ICS'21
Delay Sensitivity-driven Congestion Mitigation for HPC Systems.
Archit Patke, Saurabh Jha, Haoran Qiu, Jim Brandt, Ann Gentile, Joe Greenseid, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer
In Proceedings of the 35th ACM International Conference on Supercomputing (ICS 2021).

PDF Video DOI

OSDI'20
FIRM: An Intelligent Fine-Grained Resource Management Frameworkfor SLO-Oriented Microservices.
Haoran Qiu, Subho S. Banerjee, Saurabh Jha, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer
In Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2020).
Artifact Available, Functional, Reproduced
Selected as ACM ICPE 2024 Data Challenge

PDF Code Dataset Slides Video DOI

DSN'18
OWL: Understanding and Detecting Concurrency Attacks.
Shixiong Zhao, Rui Gu, Haoran Qiu, Tsz-On Li, Yuexuan Wang, Heming Cui, Junfeng Yang
In Proceedings of the 48th IEEE International Conference on Dependable Systems and Networks (DSN 2018).

PDF Code Slides DOI

NSDI'18
PLOVER: Fast, Multi-core Scalable Virtual Machine Fault-tolerance.
Cheng Wang, Xusheng Chen, Boxuan Li, Haoran Qiu, Shixiong Zhao, Heming Cui
In Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 2018).

PDF Code Slides Video DOI

Honors & Awards

ML and Systems Rising Stars, MLCommons, 2023
Mavis Future Faculty Fellowship, UIUC, 2023–24
UIUC CS PhD Fellowship, UIUC, 2023–24
Best Presentation Award, Workshop on Composable Systems (IPDPS), 2022
Yunni & Maxine Pao Memorial Fellowship, UIUC, 2021
Conference Presentation Award, UIUC, 2020
Travel Grants: MLSys 2024, USENIX OSDI/ATC 2023, DSN 2022, ACM SIGMETRICS 2021
Best Undergraduate Thesis 2nd Runner-up, HKU, 2019
Dean’s Honour List, HKU, 2016–19
International Student Academic Excellence Award, University of Wisconsin-Madison, 2018
Lee Shau Kee Scholarships for Student Enrichment, HKU, 2017
Honorable Mention in Mathematical Contest In Modeling, COMAP, 2017
HKU Foundation Scholarships For Outstanding Students, 2015–19

Services

Review Services:

Organizing Committee, ML for Systems Workshop, NeurIPS 2024
External Review Committee, USENIX ATC 2024
Program Committee, Workshop on Cloud Intelligence / AIOps, ASPLOS 2024
Program Committee, ML for Systems Workshop, NeurIPS 2023
Program Committee, DSN 2023 Doctoral Forum
Reviewer, IEEE Transactions on Parallel and Distributed Systems (TPDS), 2024
Reviewer, Journal of Systems Research (JSys), 2024
Reviewer, ACM Trasactions on Software Engineering Methodology, 2024
Reviewer, IEEE Transactions on Automation Science and Engineering, 2024
Reviewer, Sustainable Computing: Informatics and Systems, 2024
Reviewer, ACM Transactions on Architecture and Code Optimization (TACO), 2023
Reviewer, IEEE Internet of Things Journal, 2022
External Program Committee: EuroSys 2024, EuroSys 2022
Artifact Evaluation Committee: SOSP 2023, EuroSys 2023, MLSys 2023, OSDI/ATC 2022
Session Chair, Machine Learning Session, UIUC CSL Student Conference 2021

Community Services:

Mentor, Promoting Undergraduate Research in Engineering (PURE), UIUC, 2023
Mentor, Illinois Science and Technology Coalition (ISTC), 2023–24
Member, Institute for Inclusion, Diversity, Equity & Access (IDEA), UIUC, 2023
Mentor, Undergraduate Research Experience (URE) at IIDAI, 2022–23

Haoran Qiu

Ph.D. in Computer Science

University of Illinois, Urbana-Champaign (UIUC)

Biography

Interests

Education

Recent News

Publications

Honors & Awards

Services

Teaching

Experience

PhD Software Engineer Intern, SystemsResearch@Google (SRG)

Google LLC

Visiting Researcher, Hybrid Cloud and AI

IBM Research

PhD Software Engineer Intern, Google Cloud Infrastructure

Google LLC

Research Intern, Systems Research Group

Microsoft Research

PhD Software Engineer Intern, Google Cloud Infrastructure

Google LLC

Software Engineer Intern, Risk IT Department

Credit Suisse Ltd.

R&D Software Engineer Intern

Hututa Technology Ltd.

Contact