Alexey Tumanov

81 papers A* 10A 11C 1Misc 1Journal 38Unranked 18

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data. EuroMLSys@EuroSys Debopam Sanyal, Hongjie Chen, Alexey Tumanov, Joshua Kimball
2026	A	`conf`	Maya: Optimizing Deep Learning Training Workloads using GPU Runtime Emulation. EuroSys Srihas Yarlagadda, Amey Agrawal, Elton Pinto, Hakesh Darapaneni, Mitali Meratwal, Shivam Mittal, Pranavi Bajjuri, Srinivas Sridharan, Alexey Tumanov
2026	J	`jnl`	Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving. CoRR Amey Agrawal, Mayank Yadav, Sukrit Kumar, Anirudha Agrawal, Garv Ghai, Souradeep Bera, Elton Pinto, Sirish Gambhira, Mohammad Adain, Kasra Sohrab, Chus Antonanzas, Alexey Tumanov
2025	—	`conf`	Client Availability in Federated Learning: It Matters! EuroMLSys Dhruv Garg, Debopam Sanyal, Myungjin Lee, Alexey Tumanov, Ada Gavrilovska
2025	J	`jnl`	EMPIRIC: Exploring Missing Pieces in KV Cache Compression for Reducing Computation, Storage, and Latency in Long-Context LLM Inference. ACM SIGOPS Oper. Syst. Rev. Payman Behnam, Yaosheng Fu, Ritchie Zhao, Po-An Tsai, Zhiding Yu, Alexey Tumanov
2025	J	`jnl`	Efficient LLM Inference via Chunked Prefills. ACM SIGOPS Oper. Syst. Rev. Arney Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Alexey Tumanov, Ramachandran Ramjee
2025	J	`jnl`	Maya: Optimizing Deep Learning Training Workloads using Emulated Virtual Accelerators. CoRR Srihas Yarlagadda, Amey Agrawal, Elton Pinto, Hakesh Darapaneni, Mitali Meratwal, Shivam Mittal, Pranavi Bajjuri, Srinivas Sridharan, Alexey Tumanov
2025	J	`jnl`	On Evaluating Performance of LLM Inference Serving Systems. CoRR Amey Agrawal, Nitin Kedia, Anmol Agarwal, Jayashree Mohan, Nipun Kwatra, Souvik Kundu, Ramachandran Ramjee, Alexey Tumanov
2025	A*	`conf`	RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression. ICML Payman Behnam, Yaosheng Fu, Ritchie Zhao, Po-An Tsai, Zhiding Yu, Alexey Tumanov
2025	J	`jnl`	RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression. CoRR Payman Behnam, Yaosheng Fu, Ritchie Zhao, Po-An Tsai, Zhiding Yu, Alexey Tumanov
2025	Misc	`conf`	SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads. NSDI Alind Khare, Dhruv Garg, Sukrit Kalra, Snigdha Grandhi, Ion Stoica, Alexey Tumanov
2025	J	`jnl`	Toward Weight Sharing Paradigm for Efficient AI: Training and Inference Serving. ACM SIGOPS Oper. Syst. Rev. Payman Behnam, Alind Khare, Dhruv Garg, Alexey Tumanov
2025	A*	`conf`	VillainNet: Targeted Poisoning Attacks Against SuperNets Along the Accuracy-Latency Pareto Frontier. CCS David Oygenblik, Abhinav Vemulapalli, Animesh Agrawal, Debopam Sanyal, Alexey Tumanov, Brendan Saltaformaggio
2025	J	`jnl`	∇QDARTS: Quantization as an Elastic Dimension to Differentiable NAS. Trans. Mach. Learn. Res. Payman Behnam, Uday Kamal, Sanjana Vijay Ganesh, Zhaoyi Li, Michael Jurado, Alind Khare, Igor Fedorov, Gaowen Liu, Alexey Tumanov
2024	J	`jnl`	DεS: Delayed ε-Shrinking for Faster Once-For-All Training. CoRR Aditya Annavajjala, Alind Khare, Animesh Agrawal, Igor Fedorov, Hugo Latapie, Myungjin Lee, Alexey Tumanov
2024	—	`conf`	DεpS: Delayed ε-Shrinking for Faster Once-for-All Training. ECCV (89) Aditya Annavajjala, Alind Khare, Animesh Agrawal, Igor Fedorov, Hugo Latapie, Myungjin Lee, Alexey Tumanov
2024	A	`conf`	Harmonica: Hybrid Accelerator to Overcome Imperfections of Mixed-signal DNN Accelerators. IPDPS Payman Behnam, Uday Kamal, Ali Shafiee, Alexey Tumanov, Saibal Mukhopadhyay
2024	J	`jnl`	Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning. CoRR Kaustubh Ponkshe, Raghav Singhal, Eduard Gorbunov, Alexey Tumanov, Samuel Horváth, Praneeth Vepakomma
2024	—	`conf`	Inshrinkerator: Compressing Deep Learning Training Checkpoints via Dynamic Quantization. SoCC Amey Agrawal, Sameer Reddy, Satwik Bhattamishra, Venkata Prabhakara Sarath Nookala, Vidushi Vashishth, Kexin Rong, Alexey Tumanov
2024	J	`jnl`	Metron: Holistic Performance Evaluation Framework for LLM Inference Systems. CoRR Amey Agrawal, Anmol Agarwal, Nitin Kedia, Jayashree Mohan, Souvik Kundu, Nipun Kwatra, Ramachandran Ramjee, Alexey Tumanov
2024	J	`jnl`	Mnemosyne: Parallelization Strategies for Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations. CoRR Amey Agrawal, Junda Chen, Íñigo Goiri, Ramachandran Ramjee, Chaojie Zhang, Alexey Tumanov, Esha Choukse
2024	J	`jnl`	PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off. Trans. Mach. Learn. Res. Sachit Kuhar, Yash Jain, Alexey Tumanov
2024	—	`conf`	SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-device Inference. ECCV (79) Alind Khare, Animesh Agrawal, Aditya Annavajjala, Payman Behnam, Myungjin Lee, Hugo Latapie, Alexey Tumanov
2024	A*	`conf`	Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. OSDI Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Alexey Tumanov, Ramachandran Ramjee
2024	J	`jnl`	Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. CoRR Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Alexey Tumanov, Ramachandran Ramjee
2024	—	`conf`	VIDUR: A Large-Scale Simulation Framework for LLM Inference. MLSys Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, Alexey Tumanov
2024	J	`jnl`	Vidur: A Large-Scale Simulation Framework For LLM Inference. CoRR Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, Alexey Tumanov
2023	J	`jnl`	ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation. CoRR Anshul Ahluwalia, Rohit Das, Payman Behnam, Alind Khare, Pan Li, Alexey Tumanov
2023	J	`jnl`	DynaQuant: Compressing Deep Learning Training Checkpoints via Dynamic Quantization. CoRR Amey Agrawal, Sameer Reddy, Satwik Bhattamishra, Venkata Prabhakara Sarath Nookala, Vidushi Vashishth, Kexin Rong, Alexey Tumanov
2023	J	`jnl`	Hardware-Software Co-Design for Real-Time Latency-Accuracy Navigation in Tiny Machine Learning Applications. IEEE Micro Payman Behnam, Jianming Tong, Alind Khare, Yangyu Chen, Yue Pan, Pranav Gadikar, Abhimanyu Bambhaniya, Tushar Krishna, Alexey Tumanov
2023	J	`jnl`	Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems. CoRR Debopam Sanyal, Jui-Tse Hung, Manav Agrawal, Prahlad Jasti, Shahab Nikkhoo, Somesh Jha, Tianhao Wang, Sibin Mohan, Alexey Tumanov
2023	—	`ed.`	Proceedings of the 4th International Workshop on Distributed Machine Learning, DistributedML 2023, Paris, France, 8 December 2023 DistributedML@CoNEXT Stefanos Laskaridis, Alexey Tumanov, Nathalie Baracaldo, Dimitrios Vytiniotis
2023	J	`jnl`	Signed Binarization: Unlocking Efficiency Through Repetition-Sparsity Trade-Off. CoRR Sachit Kuhar, Yash Jain, Alexey Tumanov
2023	—	`conf`	Subgraph Stationary Hardware-Software Inference Co-Design. MLSys Payman Behnam, Alexey Tumanov, Tushar Krishna, Pranav Gadikar, Yangyu Chen, Jianming Tong, Yue Pan, Abhimanyu Rajeshkumar Bambhaniya, Alind Khare
2023	J	`jnl`	Subgraph Stationary Hardware-Software Inference Co-Design. CoRR Payman Behnam, Jianming Tong, Alind Khare, Yangyu Chen, Yue Pan, Pranav Gadikar, Abhimanyu Rajeshkumar Bambhaniya, Tushar Krishna, Alexey Tumanov
2023	J	`jnl`	SuperFed: Weight Shared Federated Learning. CoRR Alind Khare, Animesh Agrawal, Myungjin Lee, Alexey Tumanov
2023	J	`jnl`	SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads. CoRR Alind Khare, Dhruv Garg, Sukrit Kalra, Snigdha Grandhi, Ion Stoica, Alexey Tumanov
2023	—	`conf`	TransEHR: Self-Supervised Transformer for Clinical Time Series Data. ML4H@NeurIPS Yanbo Xu, Shangqing Xu, Manav Ramprassad, Alexey Tumanov, Chao Zhang
2022	—	`conf`	Automatic Parallelization of Python Programs for Distributed Heterogeneous Computing. Euro-Par Jun Shirako, Akihiro Hayashi, Sri Raj Paul, Alexey Tumanov, Vivek Sarkar
2022	J	`jnl`	Automatic Parallelization of Python Programs for Distributed Heterogeneous Computing. CoRR Jun Shirako, Akihiro Hayashi, Sri Raj Paul, Alexey Tumanov, Vivek Sarkar
2022	C	`conf`	CoDG-ReRAM: An Algorithm-Hardware Co-design to Accelerate Semi-Structured GNNs on ReRAM. ICCD YiXuan Luo, Payman Behnam, Kiran Thorat, Zhuo Liu, Hongwu Peng, Shaoyi Huang, Shu Zhou, Omer Khan, Alexey Tumanov, Caiwen Ding, Tong Geng
2022	—	`conf`	ESCHER: expressive scheduling with ephemeral resources. SoCC Romil Bhardwaj, Alexey Tumanov, Stephanie Wang, Richard Liaw, Philipp Moritz, Robert Nishihara, Ion Stoica
2022	A*	`conf`	UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification. NeurIPS Yanbo Xu, Alind Khare, Glenn Matlin, Monish Ramadoss, Rishikesan Kamaleswaran, Chao Zhang, Alexey Tumanov
2022	J	`jnl`	UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification. CoRR Yanbo Xu, Alind Khare, Glenn Matlin, Monish Ramadoss, Rishikesan Kamaleswaran, Chao Zhang, Alexey Tumanov
2021	A*	`conf`	CompOFA - Compound Once-For-All Networks for Faster Multi-Platform Deployment. ICLR Manas Sahni, Shreya Varshini, Alind Khare, Alexey Tumanov
2021	J	`jnl`	CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment. CoRR Manas Sahni, Shreya Varshini, Alind Khare, Alexey Tumanov
2021	A	`conf`	RubberBand: cloud-based hyperparameter tuning. EuroSys Ujval Misra, Richard Liaw, Lisa Dunlap, Romil Bhardwaj, Kirthevasan Kandasamy, Joseph E. Gonzalez, Ion Stoica, Alexey Tumanov
2020	J	`jnl`	Cloudburst: Stateful Functions-as-a-Service. CoRR Vikram Sreekanti, Chenggang Wu, Xiayue Charles Lin, Johann Schleier-Smith, Jose M. Faleiro, Joseph E. Gonzalez, Joseph M. Hellerstein, Alexey Tumanov
2020	J	`jnl`	Cloudburst: Stateful Functions-as-a-Service. Proc. VLDB Endow. Vikram Sreekanti, Chenggang Wu, Xiayue Charles Lin, Johann Schleier-Smith, Joseph Gonzalez, Joseph M. Hellerstein, Alexey Tumanov
2020	A*	`conf`	HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units. KDD Shenda Hong, Yanbo Xu, Alind Khare, Satria Priambada, Kevin O. Maher, Alaa Aljiffry, Jimeng Sun, Alexey Tumanov
2020	J	`jnl`	HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units. CoRR Shenda Hong, Yanbo Xu, Alind Khare, Satria Priambada, Kevin O. Maher, Alaa Aljiffry, Jimeng Sun, Alexey Tumanov
2020	J	`jnl`	HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline. CoRR Richard Liaw, Romil Bhardwaj, Lisa Dunlap, Yitian Zou, Joseph Gonzalez, Ion Stoica, Alexey Tumanov
2020	—	`conf`	InferLine: latency-aware provisioning and scaling for prediction serving pipelines. SoCC Daniel Crankshaw, Gur-Eyal Sela, Xiangxi Mo, Corey Zumar, Ion Stoica, Joseph Gonzalez, Alexey Tumanov
2019	—	`conf`	Cirrus: a Serverless Framework for End-to-end ML Workflows. SoCC João Carreira, Pedro Fonseca, Alexey Tumanov, Andrew Zhang, Randy H. Katz
2019	J	`jnl`	Dynamic Space-Time Scheduling for GPU Inference. CoRR Paras Jain, Xiangxi Mo, Ajay Jain, Harikaran Subbaraj, Rehan Sohail Durrani, Alexey Tumanov, Joseph Gonzalez, Ion Stoica
2019	—	`conf`	HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline. SoCC Richard Liaw, Romil Bhardwaj, Lisa Dunlap, Yitian Zou, Joseph E. Gonzalez, Ion Stoica, Alexey Tumanov
2019	A*	`conf`	Lineage stash: fault tolerance off the critical path. SOSP Stephanie Wang, John Liagouris, Robert Nishihara, Philipp Moritz, Ujval Misra, Alexey Tumanov, Ion Stoica
2019	A	`conf`	Serverless Computing: One Step Forward, Two Steps Back. CIDR Joseph M. Hellerstein, Jose M. Faleiro, Joseph Gonzalez, Johann Schleier-Smith, Vikram Sreekanti, Alexey Tumanov, Chenggang Wu
2019	J	`jnl`	The OoO VLIW JIT Compiler for GPU Inference. CoRR Paras Jain, Xiangxi Mo, Ajay Jain, Alexey Tumanov, Joseph E. Gonzalez, Ion Stoica
2018	A	`conf`	3Sigma: distribution-based cluster scheduling for runtime uncertainty. EuroSys Jun Woo Park, Alexey Tumanov, Angela H. Jiang, Michael A. Kozuch, Gregory R. Ganger
2018	A	`conf`	IDK Cascades: Fast Deep Learning by Learning not to Overthink. UAI Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, Fisher Yu, Joseph E. Gonzalez
2018	J	`jnl`	InferLine: ML Inference Pipeline Composition Framework. CoRR Daniel Crankshaw, Gur-Eyal Sela, Corey Zumar, Xiangxi Mo, Joseph E. Gonzalez, Ion Stoica, Alexey Tumanov
2018	A*	`conf`	Ray: A Distributed Framework for Emerging AI Applications. OSDI Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I. Jordan, Ion Stoica
2018	J	`jnl`	Serverless Computing: One Step Forward, Two Steps Back. CoRR Joseph M. Hellerstein, Jose M. Faleiro, Joseph E. Gonzalez, Johann Schleier-Smith, Vikram Sreekanti, Alexey Tumanov, Chenggang Wu
2018	—	`conf`	Tributary: spot-dancing for elastic services with latency SLOs. USENIX ATC Aaron Harlap, Andrew Chung, Alexey Tumanov, Gregory R. Ganger, Phillip B. Gibbons
2017	J	`jnl`	IDK Cascades: Fast Deep Learning by Learning not to Overthink. CoRR Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, Joseph E. Gonzalez
2017	A	`conf`	Proteus: agile ML elasticity through tiered reliability in dynamic resource markets. EuroSys Aaron Harlap, Alexey Tumanov, Andrew Chung, Gregory R. Ganger, Phillip B. Gibbons
2017	J	`jnl`	Ray: A Distributed Framework for Emerging AI Applications. CoRR Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, William Paul, Michael I. Jordan, Ion Stoica
2017	A	`conf`	Real-Time Machine Learning: The Missing Pieces. HotOS Robert Nishihara, Philipp Moritz, Stephanie Wang, Alexey Tumanov, William Paul, Johann Schleier-Smith, Richard Liaw, Mehrdad Niknami, Michael I. Jordan, Ion Stoica
2017	J	`jnl`	Real-Time Machine Learning: The Missing Pieces. CoRR Robert Nishihara, Philipp Moritz, Stephanie Wang, Alexey Tumanov, William Paul, Johann Schleier-Smith, Richard Liaw, Mehrdad Niknami, Michael I. Jordan, Ion Stoica
2016	A*	`conf`	Morpheus: Towards Automated SLOs for Enterprise Clusters. OSDI Sangeetha Abdu Jyothi, Carlo Curino, Ishai Menache, Shravan Matthur Narayanamurthy, Alexey Tumanov, Jonathan Yaniv, Ruslan Mavlyutov, Iñigo Goiri, Subru Krishnan, Janardhan Kulkarni, Sriram Rao
2016	—	`—`	Scheduling with Space-Time Soft Constraints In Heterogeneous Cloud Datacenters. Alexey Tumanov
2016	A	`conf`	TetriSched: global rescheduling with adaptive plan-ahead in dynamic heterogeneous clusters. EuroSys Alexey Tumanov, Timothy Zhu, Jun Woo Park, Michael A. Kozuch, Mor Harchol-Balter, Gregory R. Ganger
2014	J	`jnl`	Agility and Performance in Elastic Distributed Storage. ACM Trans. Storage Lianghong Xu, James Cipar, Elie Krevat, Alexey Tumanov, Nitin Gupta, Michael A. Kozuch, Gregory R. Ganger
2014	—	`conf`	Exploiting iterative-ness for parallel ML computations. SoCC Henggang Cui, Alexey Tumanov, Jinliang Wei, Lianghong Xu, Wei Dai, Jesse Haber-Kucharsky, Qirong Ho, Gregory R. Ganger, Phillip B. Gibbons, Garth A. Gibson, Eric P. Xing
2014	—	`conf`	PriorityMeister: Tail Latency QoS for Shared Networked Storage. SoCC Timothy Zhu, Alexey Tumanov, Michael A. Kozuch, Mor Harchol-Balter, Gregory R. Ganger
2014	A	`conf`	SpringFS: bridging agility and performance in elastic distributed storage. FAST Lianghong Xu, James Cipar, Elie Krevat, Alexey Tumanov, Nitin Gupta, Michael A. Kozuch, Gregory R. Ganger
2012	—	`conf`	Heterogeneity and dynamicity of clouds at scale: Google trace analysis. SoCC Charles Reiss, Alexey Tumanov, Gregory R. Ganger, Randy H. Katz, Michael A. Kozuch
2012	—	`conf`	alsched: algebraic scheduling of mixed workloads in heterogeneous clouds. SoCC Alexey Tumanov, James Cipar, Gregory R. Ganger, Michael A. Kozuch
2011	A	`conf`	Kaleidoscope: cloud micro-elasticity via VM state coloring. EuroSys Roy Bryant, Alexey Tumanov, Olga Irzak, Adin Scannell, Kaustubh R. Joshi, Matti A. Hiltunen, H. Andrés Lagar-Cavilla, Eyal de Lara
2007	A*	`conf`	Variability-Aware Latency Amelioration in Distributed Environments. VR Alexey Tumanov, Robert S. Allison, Wolfgang Stürzlinger