Jayashree Mohan

Metron: Holistic Performance Evaluation Framework for LLM Inference Systems

Amey Agrawal, Anmol Agarwal, Nitin Kedia, Jayashree Mohan, Souvik Kundu, Nipun Kwatra, Ramachandran Ramjee, Alexey Tumanov

July 2024

Preprint Project

vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention

Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar

May 2024

PDF Preprint Github Project

VIDUR: A Large-Scale Simulation Framework for LLM Inference

Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, Alexey Tumanov

The Seventh Annual Conference on Machine Learning and Systems | May 2024

PDF Github Project

Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, Ramachandran Ramjee

OSDI '24 | March 2024

DOI Publication Publication Github Project

Project Silica: Towards Sustainable Cloud Archival Storage in Glass

Patrick Anderson, Erika B. Aranas, Youssef Assaf, Raphael Behrendt, Richard Black, Marco Caballero, Pashmina Cameron, Burcu Canakci, Thales de Carvalho, Andromachi Chatzieleftheriou, James Clegg, Rebekah Storan Clarke, Daniel Cletheroe, Bridgette Cooper, Tim Deegan, Austin Donnelly, Rokas Drevinskas, Alexander Gaunt, Christos Gkantsidis, Ariel Gomez Diaz, Istvan Haller, Freddie Hong, Teodora Ilieva, Shashidhar Joshi, Russell Joyce, Mint Kunkel, David Lara, Sergey Legtchenko, Fanglin Linda Liu, Bruno Magalhaes, Alana Marzoev, Marvin McNett, Jayashree Mohan, Michael Myrah, Truong Nguyen, Sebastian Nowozin, Aaron Ogus, Hiske Overweg, Ant Rowstron, Maneesh Sah, Masaaki Sakakura, Peter Scholtz, Nina Schreiner, Omer Sella, Adam Smith, Ioan Stefanovici, David Sweeney, Benn Thomsen, Govert Verkes, Phil Wainman, Jonathan Westcott, Luke Weston, Charles Whittaker, Pablo Wilke Berenguer, Hugh Williams, Thomas Winkler, Stefan Winzeck

The 29th ACM Symposium on Operating Systems Principles | October 2023

Publication Project

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee

September 2023

Preprint Project

Looking Beyond GPUs for DNN Scheduling on Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022) | July 2022

Publication Project

Accelerating Deep Learning Training : A Storage Perspective

Jayashree Mohan

December 2021

PhD Thesis: University of Texas at Austin | December 2021

Publication

Synergy: Resource Sensitive DNN Scheduling in Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

October 2021

Publication PDF Project

Memory Optimization for Deep Networks

Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krahenbuhl

International Conference on Learning Representations (ICLR 2021) | May 2021

Publication

CheckFreq: Frequent, Fine-Grained DNN Checkpointing

Jayashree Mohan, Amar Phanishayee, Vijay Chidambaram

USENIX FAST 2021 | February 2021

Publication Project

Analyzing and Mitigating Data Stalls in DNN Training

Jayashree Mohan, Amar Phanishayee, Ashish Raniwala, Vijay Chidambaram

VLDB 2021 | January 2021

PDF Publication Project

Recipe: Converting concurrent DRAM indexes to persistent-memory indexes

Se Kwon Lee, Jayashree Mohan, Sanidhya Kashyap, Taesoo Kim, Vijay Chidambaram

Symposium on Operating Systems Principles (SOSP 2019) | October 2019

Publication

Analyzing GDPR compliance through the lens of privacy policy

Jayashree Mohan, Melissa Wasserman, Vijay Chidambaram

Poly workshop at VLDB 2019 | August 2019

Publication

Crashmonkey and ACE: Systematically testing file-system crash consistency

Jayashree Mohan, Ashlie Martinez, Soujanya Ponnapalli, Pandian Raju, Vijay Chidambaram

ACM Transactions on Storage (TOS) | April 2019

Publication

Finding crash-consistency bugs with bounded black-box crash testing

Jayashree Mohan, Ashlie Martinez, Soujanya Ponnapalli, Pandian Raju, Vijay Chidambaram

Symposium on Operating Systems Design and Implementation (OSDI 2018) | October 2018

Publication

The Dangers and Complexities of SQLite Benchmarking

Dhathri Purohith, Jayashree Mohan, Vijay Chidambaram

APSys Workshop | September 2017

Publication

Analyzing IO amplification in Linux file systems

Jayashree Mohan, Rohan Kadekodi, Vijay Chidambaram

July 2017

Publication

Storage on Your Smartphone Uses More Energy Than You Think

Jayashree Mohan, Dhathri Purohith, Mathew Halpern, Vijay Chidambaram, Vijay Janapa Reddi

USENIX HotStorage Workshop | July 2017

Publication

Metron: Holistic Performance Evaluation Framework for LLM Inference Systems

Amey Agrawal, Anmol Agarwal, Nitin Kedia, Jayashree Mohan, Souvik Kundu, Nipun Kwatra, Ramachandran Ramjee, Alexey Tumanov

July 2024

Preprint Project

vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention

Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar

May 2024

PDF Preprint Github Project

VIDUR: A Large-Scale Simulation Framework for LLM Inference

Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, Alexey Tumanov

The Seventh Annual Conference on Machine Learning and Systems | May 2024

PDF Github Project

Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, Ramachandran Ramjee

OSDI '24 | March 2024

DOI Publication Publication Github Project

Project Silica: Towards Sustainable Cloud Archival Storage in Glass

Patrick Anderson, Erika B. Aranas, Youssef Assaf, Raphael Behrendt, Richard Black, Marco Caballero, Pashmina Cameron, Burcu Canakci, Thales de Carvalho, Andromachi Chatzieleftheriou, James Clegg, Rebekah Storan Clarke, Daniel Cletheroe, Bridgette Cooper, Tim Deegan, Austin Donnelly, Rokas Drevinskas, Alexander Gaunt, Christos Gkantsidis, Ariel Gomez Diaz, Istvan Haller, Freddie Hong, Teodora Ilieva, Shashidhar Joshi, Russell Joyce, Mint Kunkel, David Lara, Sergey Legtchenko, Fanglin Linda Liu, Bruno Magalhaes, Alana Marzoev, Marvin McNett, Jayashree Mohan, Michael Myrah, Truong Nguyen, Sebastian Nowozin, Aaron Ogus, Hiske Overweg, Ant Rowstron, Maneesh Sah, Masaaki Sakakura, Peter Scholtz, Nina Schreiner, Omer Sella, Adam Smith, Ioan Stefanovici, David Sweeney, Benn Thomsen, Govert Verkes, Phil Wainman, Jonathan Westcott, Luke Weston, Charles Whittaker, Pablo Wilke Berenguer, Hugh Williams, Thomas Winkler, Stefan Winzeck

The 29th ACM Symposium on Operating Systems Principles | October 2023

Publication Project

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee

September 2023

Preprint Project

Looking Beyond GPUs for DNN Scheduling on Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022) | July 2022

Publication Project

Accelerating Deep Learning Training : A Storage Perspective

Jayashree Mohan

December 2021

PhD Thesis: University of Texas at Austin | December 2021

Publication

Synergy: Resource Sensitive DNN Scheduling in Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

October 2021

Publication PDF Project

Memory Optimization for Deep Networks

Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krahenbuhl

International Conference on Learning Representations (ICLR 2021) | May 2021

Publication

CheckFreq: Frequent, Fine-Grained DNN Checkpointing

Jayashree Mohan, Amar Phanishayee, Vijay Chidambaram

USENIX FAST 2021 | February 2021

Publication Project

Analyzing and Mitigating Data Stalls in DNN Training

Jayashree Mohan, Amar Phanishayee, Ashish Raniwala, Vijay Chidambaram

VLDB 2021 | January 2021

PDF Publication Project

Recipe: Converting concurrent DRAM indexes to persistent-memory indexes

Se Kwon Lee, Jayashree Mohan, Sanidhya Kashyap, Taesoo Kim, Vijay Chidambaram

Symposium on Operating Systems Principles (SOSP 2019) | October 2019

Publication

Crashmonkey and ACE: Systematically testing file-system crash consistency

Jayashree Mohan, Ashlie Martinez, Soujanya Ponnapalli, Pandian Raju, Vijay Chidambaram

ACM Transactions on Storage (TOS) | April 2019

Publication

Finding crash-consistency bugs with bounded black-box crash testing

Jayashree Mohan, Ashlie Martinez, Soujanya Ponnapalli, Pandian Raju, Vijay Chidambaram

Symposium on Operating Systems Design and Implementation (OSDI 2018) | October 2018

Publication

The Dangers and Complexities of SQLite Benchmarking

Dhathri Purohith, Jayashree Mohan, Vijay Chidambaram

APSys Workshop | September 2017

Publication

Analyzing IO amplification in Linux file systems

Jayashree Mohan, Rohan Kadekodi, Vijay Chidambaram

July 2017

Publication

Storage on Your Smartphone Uses More Energy Than You Think

Jayashree Mohan, Dhathri Purohith, Mathew Halpern, Vijay Chidambaram, Vijay Janapa Reddi

USENIX HotStorage Workshop | July 2017

Publication

Looking Beyond GPUs for DNN Scheduling on Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022) | July 2022

Publication Project

Accelerating Deep Learning Training : A Storage Perspective

Jayashree Mohan

December 2021

PhD Thesis: University of Texas at Austin | December 2021

Publication

Synergy: Resource Sensitive DNN Scheduling in Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

October 2021

Publication PDF Project

Memory Optimization for Deep Networks

Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krahenbuhl

International Conference on Learning Representations (ICLR 2021) | May 2021

Publication

CheckFreq: Frequent, Fine-Grained DNN Checkpointing

Jayashree Mohan, Amar Phanishayee, Vijay Chidambaram

USENIX FAST 2021 | February 2021

Publication Project

Analyzing and Mitigating Data Stalls in DNN Training

Jayashree Mohan, Amar Phanishayee, Ashish Raniwala, Vijay Chidambaram

VLDB 2021 | January 2021

PDF Publication Project

Analyzing GDPR compliance through the lens of privacy policy

Jayashree Mohan, Melissa Wasserman, Vijay Chidambaram

Poly workshop at VLDB 2019 | August 2019

Publication

Memory Optimization for Deep Networks

Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krahenbuhl

International Conference on Learning Representations (ICLR 2021) | May 2021

Publication

Metron: Holistic Performance Evaluation Framework for LLM Inference Systems

Amey Agrawal, Anmol Agarwal, Nitin Kedia, Jayashree Mohan, Souvik Kundu, Nipun Kwatra, Ramachandran Ramjee, Alexey Tumanov

July 2024

Preprint Project

VIDUR: A Large-Scale Simulation Framework for LLM Inference

Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, Alexey Tumanov

The Seventh Annual Conference on Machine Learning and Systems | May 2024

PDF Github Project

Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, Ramachandran Ramjee

OSDI '24 | March 2024

DOI Publication Publication Github Project

Project Silica: Towards Sustainable Cloud Archival Storage in Glass

Patrick Anderson, Erika B. Aranas, Youssef Assaf, Raphael Behrendt, Richard Black, Marco Caballero, Pashmina Cameron, Burcu Canakci, Thales de Carvalho, Andromachi Chatzieleftheriou, James Clegg, Rebekah Storan Clarke, Daniel Cletheroe, Bridgette Cooper, Tim Deegan, Austin Donnelly, Rokas Drevinskas, Alexander Gaunt, Christos Gkantsidis, Ariel Gomez Diaz, Istvan Haller, Freddie Hong, Teodora Ilieva, Shashidhar Joshi, Russell Joyce, Mint Kunkel, David Lara, Sergey Legtchenko, Fanglin Linda Liu, Bruno Magalhaes, Alana Marzoev, Marvin McNett, Jayashree Mohan, Michael Myrah, Truong Nguyen, Sebastian Nowozin, Aaron Ogus, Hiske Overweg, Ant Rowstron, Maneesh Sah, Masaaki Sakakura, Peter Scholtz, Nina Schreiner, Omer Sella, Adam Smith, Ioan Stefanovici, David Sweeney, Benn Thomsen, Govert Verkes, Phil Wainman, Jonathan Westcott, Luke Weston, Charles Whittaker, Pablo Wilke Berenguer, Hugh Williams, Thomas Winkler, Stefan Winzeck

The 29th ACM Symposium on Operating Systems Principles | October 2023

Publication Project

Looking Beyond GPUs for DNN Scheduling on Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022) | July 2022

Publication Project

Memory Optimization for Deep Networks

Aashaka Shah, Chao-Yuan Wu, Jayashree Mohan, Vijay Chidambaram, Philipp Krahenbuhl

International Conference on Learning Representations (ICLR 2021) | May 2021

Publication

CheckFreq: Frequent, Fine-Grained DNN Checkpointing

Jayashree Mohan, Amar Phanishayee, Vijay Chidambaram

USENIX FAST 2021 | February 2021

Publication Project

Analyzing and Mitigating Data Stalls in DNN Training

Jayashree Mohan, Amar Phanishayee, Ashish Raniwala, Vijay Chidambaram

VLDB 2021 | January 2021

PDF Publication Project

Recipe: Converting concurrent DRAM indexes to persistent-memory indexes

Se Kwon Lee, Jayashree Mohan, Sanidhya Kashyap, Taesoo Kim, Vijay Chidambaram

Symposium on Operating Systems Principles (SOSP 2019) | October 2019

Publication

Analyzing GDPR compliance through the lens of privacy policy

Jayashree Mohan, Melissa Wasserman, Vijay Chidambaram

Poly workshop at VLDB 2019 | August 2019

Publication

Finding crash-consistency bugs with bounded black-box crash testing

Jayashree Mohan, Ashlie Martinez, Soujanya Ponnapalli, Pandian Raju, Vijay Chidambaram

Symposium on Operating Systems Design and Implementation (OSDI 2018) | October 2018

Publication

The Dangers and Complexities of SQLite Benchmarking

Dhathri Purohith, Jayashree Mohan, Vijay Chidambaram

APSys Workshop | September 2017

Publication

Storage on Your Smartphone Uses More Energy Than You Think

Jayashree Mohan, Dhathri Purohith, Mathew Halpern, Vijay Chidambaram, Vijay Janapa Reddi

USENIX HotStorage Workshop | July 2017

Publication

vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention

Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar

May 2024

PDF Preprint Github Project

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee

September 2023

Preprint Project

Accelerating Deep Learning Training : A Storage Perspective

Jayashree Mohan

December 2021

PhD Thesis: University of Texas at Austin | December 2021

Publication

Crashmonkey and ACE: Systematically testing file-system crash consistency

Jayashree Mohan, Ashlie Martinez, Soujanya Ponnapalli, Pandian Raju, Vijay Chidambaram

ACM Transactions on Storage (TOS) | April 2019

Publication

Synergy: Resource Sensitive DNN Scheduling in Multi-Tenant Clusters

Jayashree Mohan, Amar Phanishayee, Janardhan (Jana) Kulkarni, Vijay Chidambaram

October 2021

Publication PDF Project

Analyzing IO amplification in Linux file systems

Jayashree Mohan, Rohan Kadekodi, Vijay Chidambaram

July 2017

Publication