Saurav Muralidharan

28 papers A* 6A 1B 1Journal 17Unranked 2
YearRankTypeTitle / Venue / Authors
2025 J jnl
Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning.
CoRR
Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Marcin Chochowski, Yashaswi Karnati, Raviraj Joshi, Ameya Sunil Mahabaleshwarkar, Zijia Chen, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, Jan Kautz, Bryan Catanzaro, Ashwath Aithal, Nima Tajbakhsh, Pavlo Molchanov
2025 A* conf
LLaMaFlex: Many-in-one LLMs via Generalized Pruning and Weight Sharing.
ICLR
Ruisi Cai, Saurav Muralidharan, Hongxu Yin, Zhangyang Wang, Jan Kautz, Pavlo Molchanov
2025 J jnl
Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs.
CoRR
Ali Taghibakhshi, Sharath Turuvekere Sreenivas, Saurav Muralidharan, Ruisi Cai, Marcin Chochowski, Ameya Sunil Mahabaleshwarkar, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, Jan Kautz, Bryan Catanzaro, Ashwath Aithal, Nima Tajbakhsh, Pavlo Molchanov
2025 J jnl
Small Language Models are the Future of Agentic AI.
CoRR
Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralidharan, Yingyan Celine Lin, Pavlo Molchanov
2024 A* conf
Compact Language Models via Pruning and Knowledge Distillation.
NeurIPS
Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov
2024 J jnl
Compact Language Models via Pruning and Knowledge Distillation.
CoRR
Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov
2024 J jnl
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation.
CoRR
Shih-Yang Liu, Huck Yang, Chein-Yi Wang, Nai Chit Fung, Hongxu Yin, Charbel Sakr, Saurav Muralidharan, Kwang-Ting Cheng, Jan Kautz, Yu-Chiang Frank Wang, Pavlo Molchanov, Min-Hung Chen
2024 A* conf
Flextron: Many-in-One Flexible Large Language Model.
ICML
Ruisi Cai, Saurav Muralidharan, Greg Heinrich, Hongxu Yin, Zhangyang Wang, Jan Kautz, Pavlo Molchanov
2024 J jnl
Flextron: Many-in-One Flexible Large Language Model.
CoRR
Ruisi Cai, Saurav Muralidharan, Greg Heinrich, Hongxu Yin, Zhangyang Wang, Jan Kautz, Pavlo Molchanov
2024 J jnl
LLM Pruning and Distillation in Practice: The Minitron Approach.
CoRR
Sharath Turuvekere Sreenivas, Saurav Muralidharan, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov
2024 A* conf
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models.
NeurIPS
Gongfan Fang, Hongxu Yin, Saurav Muralidharan, Greg Heinrich, Jeff Pool, Jan Kautz, Pavlo Molchanov, Xinchao Wang
2024 J jnl
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models.
CoRR
Gongfan Fang, Hongxu Yin, Saurav Muralidharan, Greg Heinrich, Jeff Pool, Jan Kautz, Pavlo Molchanov, Xinchao Wang
2023 A* conf
HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity.
MICRO
Yannan Nellie Wu, Po-An Tsai, Saurav Muralidharan, Angshuman Parashar, Vivienne Sze, Joel S. Emer
2023 J jnl
HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity.
CoRR
Yannan Nellie Wu, Po-An Tsai, Saurav Muralidharan, Angshuman Parashar, Vivienne Sze, Joel S. Emer
2023 J jnl
The Sparsity Roofline: Understanding the Hardware Limits of Sparse Neural Networks.
CoRR
Cameron Shinn, Collin McCarthy, Saurav Muralidharan, Muhammad Osama, John D. Owens
2023 J jnl
Understanding the Effect of the Long Tail on Neural Network Compression.
CoRR
Harvey Dam, Vinu Joseph, Aditya Bhaskara, Ganesh Gopalakrishnan, Saurav Muralidharan, Michael Garland
2023 — conf
Uniform Sparsity in Deep Neural Networks.
MLSys
Saurav Muralidharan
2022 J jnl
Efficient Sparsely Activated Transformers.
CoRR
Salar Latifi, Saurav Muralidharan, Michael Garland
2020 J jnl
A Programmable Approach to Neural Network Compression.
IEEE Micro
Vinu Joseph, Ganesh Gopalakrishnan, Saurav Muralidharan, Michael Garland, Animesh Garg
2020 J jnl
Reliable Model Compression via Label-Preservation-Aware Loss Functions.
CoRR
Vinu Joseph, Shoaib Ahmed Siddiqui, Aditya Bhaskara, Ganesh Gopalakrishnan, Saurav Muralidharan, Michael Garland, Sheraz Ahmed, Andreas Dengel
2019 J jnl
A Programmable Approach to Model Compression.
CoRR
Vinu Joseph, Saurav Muralidharan, Animesh Garg, Michael Garland, Ganesh Gopalakrishnan
2016 — —
Abstractions and Strategies for Adaptive Programming.
Saurav Muralidharan
2016 A* conf
Architecture-Adaptive Code Variant Tuning.
ASPLOS
Saurav Muralidharan, Amit Roy, Mary W. Hall, Michael Garland, Piyush Rai
2016 J jnl
Designing a Tunable Nested Data-Parallel Programming System.
ACM Trans. Archit. Code Optim.
Saurav Muralidharan, Michael Garland, Albert Sidelnik, Mary W. Hall
2015 B conf
A collection-oriented programming model for performance portability.
PPoPP
Saurav Muralidharan, Michael Garland, Bryan Catanzaro, Albert Sidelnik, Mary W. Hall
2014 A conf
Nitro: A Framework for Adaptive Code Variant Tuning.
IPDPS
Saurav Muralidharan, Manu Shantharam, Mary W. Hall, Michael Garland, Bryan Catanzaro
2013 J jnl
Towards making autotuning mainstream.
Int. J. High Perform. Comput. Appl.
Protonu Basu, Mary W. Hall, Malik Murtaza Khan, Suchit Maindola, Saurav Muralidharan, Shreyas Ramalingam, Axel Rivera, Manu Shantharam, Anand Venkat
2009 — conf
Galaxia: A Semi-decentralized System for Implementing Secure-Group P2P Networks.
NetCoM
Saurav Muralidharan, Sajin Koroth, Nevil Anto, Rafeeque Pandarachalil