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).
  Artifact Available, Functional, Reproduced

PDF Preprint Cite Code Slides Video

SoCC'24
QLM: Queue Management for Large Language Model Serving.
Archit Patke, Dhemath Reddy, Saurabh Jha, Haoran Qiu, Christian Pinto, Chandra Narayanaswami, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer
In Proceedings of the 15th ACM Symposium on Cloud Computing (SoCC 2024).
  Integrated with vLLM v0.6.2 [link]

PDF Preprint Cite Code DOI

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 Cite 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 Cite 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 Cite 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 Cite

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 Cite Slides

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 Cite 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 Cite

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 Cite 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 Cite

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 Cite 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 Cite 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 Cite 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 Cite Slides Video DOI

IEEE TSC'22
A Geography-Based P2P Overlay Network for Fast and Robust Blockchain Systems.
Haoran Qiu, Tao Ji, Shixiong Zhao, Xusheng Chen, Ji Qi, Heming Cui, Sen Wang
In IEEE Transactions on Services Computing 2022 (IEEE TSC 2022).

PDF Cite Code Slides 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 Cite 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 Cite 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 Cite 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).
  CVE-2017-12193, CVE-2017-7533

PDF Cite 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 Cite Code Slides Video DOI