DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
Jakub Tarnawski
Senior Researcher
Publications
Publications by Year
-
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
-
Fairness in Streaming Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Federico Fusco, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
ICML 2023 | June 2023
-
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Online Edge Coloring via Tree Recurrences and Correlation Decay
Janardhan (Jana) Kulkarni, Yang Liu, Yang Liu, Yang Liu, Ashwin Sah, Mehtaab Sawhney, Jakub Tarnawski
STOC 2022 | June 2022
On the Hardness of Scheduling With Non-Uniform Communication Delays
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sai Sandeep, Jakub Tarnawski, Yihao Zhang
SODA 2022 | January 2022
-
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Scheduling with Communication Delays via LP Hierarchies and Clustering II: Weighted Completion Times on Related Machines
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
SODA 2021 | January 2021
-
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
Scheduling with Communication Delays via LP Hierarchies and Clustering
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
FOCS 2020 | April 2020
Hierarchy-Based Algorithms for Minimizing Makespan under Precedence and Communication Constraints
Janardhan (Jana) Kulkarni, Shi Li, Jakub Tarnawski, Minwei Ye
SODA 2020 | January 2020
Publications by Research Area
-
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
Fairness in Streaming Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Federico Fusco, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
ICML 2023 | June 2023
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
-
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
-
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Online Edge Coloring via Tree Recurrences and Correlation Decay
Janardhan (Jana) Kulkarni, Yang Liu, Yang Liu, Yang Liu, Ashwin Sah, Mehtaab Sawhney, Jakub Tarnawski
STOC 2022 | June 2022
On the Hardness of Scheduling With Non-Uniform Communication Delays
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sai Sandeep, Jakub Tarnawski, Yihao Zhang
SODA 2022 | January 2022
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Scheduling with Communication Delays via LP Hierarchies and Clustering II: Weighted Completion Times on Related Machines
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
SODA 2021 | January 2021
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
Scheduling with Communication Delays via LP Hierarchies and Clustering
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
FOCS 2020 | April 2020
Hierarchy-Based Algorithms for Minimizing Makespan under Precedence and Communication Constraints
Janardhan (Jana) Kulkarni, Shi Li, Jakub Tarnawski, Minwei Ye
SODA 2020 | January 2020
-
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
-
Fairness in Streaming Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Federico Fusco, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
ICML 2023 | June 2023
-
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
Publications by Type
-
Integrated Hardware Architecture and Device Placement Search
Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan
2024 International Conference on Machine Learning | July 2024
DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving
Foteini Strati, Sara Mcallister, Amar Phanishayee, Jakub Tarnawski, Ana Klimovic
ICML 2024 | July 2024
Efficiently Computing Similarities to Private Datasets
Arturs Backurs, Zinan Lin, Sepideh Mahabadi, Sandeep Silwal, Jakub Tarnawski
ICLR 2024 | May 2024
Fairness in Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
AISTATS 2024 | May 2024
Fairness in Streaming Submodular Maximization over a Matroid Constraint
Marwa El Halabi, Federico Fusco, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
ICML 2023 | June 2023
Near-Optimal Correlation Clustering with Privacy
Vincent Cohen-Addad, Chenglin Fan, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
NeurIPS 2022 | November 2022
Harmony: Overcoming the hurdles of GPU memory capacity to train massive DNN models on commodity servers
Youjie Li, Amar Phanishayee, Derek Murray, Jakub Tarnawski, Nam Sung Kim
VLDB 2022 | September 2022
Online Edge Coloring via Tree Recurrences and Correlation Decay
Janardhan (Jana) Kulkarni, Yang Liu, Yang Liu, Yang Liu, Ashwin Sah, Mehtaab Sawhney, Jakub Tarnawski
STOC 2022 | June 2022
On the Hardness of Scheduling With Non-Uniform Communication Delays
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Sai Sandeep, Jakub Tarnawski, Yihao Zhang
SODA 2022 | January 2022
Piper: Multidimensional Planner for DNN Parallelization
Jakub Tarnawski, Deepak Narayanan, Amar Phanishayee
NeurIPS 2021 | December 2021
Correlation Clustering in Constant Many Parallel Rounds
Vincent Cohen-Addad, Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Nikos Parotsidis, Jakub Tarnawski
2021 International Conference on Machine Learning | July 2021
Scheduling with Communication Delays via LP Hierarchies and Clustering II: Weighted Completion Times on Related Machines
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
SODA 2021 | January 2021
Fairness in Streaming Submodular Maximization: Algorithms and Hardness
Marwa El Halabi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakab Tardos, Jakub Tarnawski
NeurIPS 2020 | December 2020
Efficient Algorithms for Device Placement of DNN Graph Operators
Jakub Tarnawski, Amar Phanishayee, Nikhil R. Devanur, Divya Mahajan, Fanny Nina Paravecino
NeurIPS 2020 | December 2020
Fully Dynamic Algorithm for Constrained Submodular Optimization
Silvio Lattanzi, Slobodan Mitrović, Ashkan Norouzi-Fard, Jakub Tarnawski, Morteza Zadimoghaddam
NeurIPS 2020 | October 2020
Scheduling with Communication Delays via LP Hierarchies and Clustering
Sami Davies, Janardhan (Jana) Kulkarni, Thomas Rothvoss, Jakub Tarnawski, Yihao Zhang
FOCS 2020 | April 2020
Hierarchy-Based Algorithms for Minimizing Makespan under Precedence and Communication Constraints
Janardhan (Jana) Kulkarni, Shi Li, Jakub Tarnawski, Minwei Ye
SODA 2020 | January 2020