LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
Raja Gond, Aditya K Kamath, Ramachandran Ramjee, Ashish Panwar
January 2026
Ashish Panwar
Principal Researcher
Publications
-
-
-
-
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
Aditya K Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar
Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025
-
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar
Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025
-
-
-
SIGMA: Secure GPT Inference with Function Secret Sharing
Kanav Gupta, Neha Jawalkar, Ananta Mukherjee, Nishanth Chandran, Divya Gupta, Ashish Panwar, Rahul Sharma
Privacy Enhancing technologies Symposium (PETS) 2024 | June 2024
-
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
MLSys | May 2024
-
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
-
-
-
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
-
-
-
Trident: Harnessing Architectural Resources for All Page Sizes in x86 Processors
Ashish Panwar, Venkat Sri Sai Ram, Arkaprava Basu
2021 International Symposium on Microarchitecture | October 2021
-
nuKSM: NUMA-aware Memory De-duplication on Multi-socket Servers
Akash Panda, Ashish Panwar, Arkaprava Basu
2021 International Conference on Parallel Architectures and Compilation Techniques | August 2021
-
Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis
Ashish Panwar, Reto Achermann, Arkaprava Basu, Abhishek Bhattacharjee, K. Gopinath, Jayneel Gandhi
2021 Architectural Support for Programming Languages and Operating Systems | April 2021
-
-
-
Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines
Reto Achermann, Ashish Panwar, Abhishek Bhattacharjee, Timothy Roscoe, Jayneel Gandhi
2020 Architectural Support for Programming Languages and Operating Systems | March 2020
-
-
-
HawkEye: Efficient Fine-grained OS Support for Huge Pages
Ashish Panwar, Sorav Bansal, K. Gopinath
2019 Architectural Support for Programming Languages and Operating Systems | April 2019
-
-
-
Making Huge Pages Actually Useful
Ashish Panwar, Aravinda Prasad, K. Gopinath
2018 Architectural Support for Programming Languages and Operating Systems | March 2018
-
-
-
A Case for Protecting Huge Pages from the Kernel
Ashish Panwar, Naman Patel, K. Gopinath
2016 Asia-Pacific Workshop on Systems | August 2016
-
-
-
Towards Practical Page Placement for a Green Memory Manager
Ashish Panwar, K. Gopinath
2015 IEEE International Conference on High Performance Computing, Data, and Analytics | December 2015
-
-
-
LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
Raja Gond, Aditya K Kamath, Ramachandran Ramjee, Ashish Panwar
January 2026
-
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
Aditya K Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar
Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025
-
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar
Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025
-
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
MLSys | May 2024
-
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
-
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
-
Trident: Harnessing Architectural Resources for All Page Sizes in x86 Processors
Ashish Panwar, Venkat Sri Sai Ram, Arkaprava Basu
2021 International Symposium on Microarchitecture | October 2021
-
nuKSM: NUMA-aware Memory De-duplication on Multi-socket Servers
Akash Panda, Ashish Panwar, Arkaprava Basu
2021 International Conference on Parallel Architectures and Compilation Techniques | August 2021
-
Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis
Ashish Panwar, Reto Achermann, Arkaprava Basu, Abhishek Bhattacharjee, K. Gopinath, Jayneel Gandhi
2021 Architectural Support for Programming Languages and Operating Systems | April 2021
-
Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines
Reto Achermann, Ashish Panwar, Abhishek Bhattacharjee, Timothy Roscoe, Jayneel Gandhi
2020 Architectural Support for Programming Languages and Operating Systems | March 2020
-
HawkEye: Efficient Fine-grained OS Support for Huge Pages
Ashish Panwar, Sorav Bansal, K. Gopinath
2019 Architectural Support for Programming Languages and Operating Systems | April 2019
-
Making Huge Pages Actually Useful
Ashish Panwar, Aravinda Prasad, K. Gopinath
2018 Architectural Support for Programming Languages and Operating Systems | March 2018
-
A Case for Protecting Huge Pages from the Kernel
Ashish Panwar, Naman Patel, K. Gopinath
2016 Asia-Pacific Workshop on Systems | August 2016
-
Towards Practical Page Placement for a Green Memory Manager
Ashish Panwar, K. Gopinath
2015 IEEE International Conference on High Performance Computing, Data, and Analytics | December 2015
-
-
-
SIGMA: Secure GPT Inference with Function Secret Sharing
Kanav Gupta, Neha Jawalkar, Ananta Mukherjee, Nishanth Chandran, Divya Gupta, Ashish Panwar, Rahul Sharma
Privacy Enhancing technologies Symposium (PETS) 2024 | June 2024
-
-
-
LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
Raja Gond, Aditya K Kamath, Ramachandran Ramjee, Ashish Panwar
January 2026
-
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
-
-
-
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
Aditya K Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar
Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025
-
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar
Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025 | March 2025
-
SIGMA: Secure GPT Inference with Function Secret Sharing
Kanav Gupta, Neha Jawalkar, Ananta Mukherjee, Nishanth Chandran, Divya Gupta, Ashish Panwar, Rahul Sharma
Privacy Enhancing technologies Symposium (PETS) 2024 | June 2024
-
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
MLSys | May 2024
-
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
-
Trident: Harnessing Architectural Resources for All Page Sizes in x86 Processors
Ashish Panwar, Venkat Sri Sai Ram, Arkaprava Basu
2021 International Symposium on Microarchitecture | October 2021
-
nuKSM: NUMA-aware Memory De-duplication on Multi-socket Servers
Akash Panda, Ashish Panwar, Arkaprava Basu
2021 International Conference on Parallel Architectures and Compilation Techniques | August 2021
-
Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis
Ashish Panwar, Reto Achermann, Arkaprava Basu, Abhishek Bhattacharjee, K. Gopinath, Jayneel Gandhi
2021 Architectural Support for Programming Languages and Operating Systems | April 2021
-
Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines
Reto Achermann, Ashish Panwar, Abhishek Bhattacharjee, Timothy Roscoe, Jayneel Gandhi
2020 Architectural Support for Programming Languages and Operating Systems | March 2020
-
HawkEye: Efficient Fine-grained OS Support for Huge Pages
Ashish Panwar, Sorav Bansal, K. Gopinath
2019 Architectural Support for Programming Languages and Operating Systems | April 2019
-
Making Huge Pages Actually Useful
Ashish Panwar, Aravinda Prasad, K. Gopinath
2018 Architectural Support for Programming Languages and Operating Systems | March 2018
-
A Case for Protecting Huge Pages from the Kernel
Ashish Panwar, Naman Patel, K. Gopinath
2016 Asia-Pacific Workshop on Systems | August 2016
-
Towards Practical Page Placement for a Green Memory Manager
Ashish Panwar, K. Gopinath
2015 IEEE International Conference on High Performance Computing, Data, and Analytics | December 2015
-