Ashish Panwar

26 papers A* 6B 1C 1Misc 1Journal 13Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
LLM-42: Enabling Determinism in LLM Inference with Verified Speculation.
CoRR
Raja Gond, Aditya K. Kamath, Ramachandran Ramjee, Ashish Panwar
2025 C conf
EMD: Fair and Efficient Dynamic Memory De-bloating of Transparent Huge Pages.
ISMM
Parth Gangar, Ashish Panwar, K. Gopinath
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 — conf
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference.
ASPLOS (2)
Aditya K. Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar
2025 J jnl
PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch.
CoRR
Abhishek Ghosh, Ajay Nayak, Ashish Panwar, Arkaprava Basu
2025 — conf
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention.
ASPLOS (1)
Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar
2024 J jnl
Address Scaling: Architectural Support for Fine-Grained Thread-Safe Metadata Management.
IEEE Comput. Archit. Lett.
Deepanjali Mishra, Konstantinos Kanellopoulos, Ashish Panwar, Akshitha Sriraman, Vivek Seshadri, Onur Mutlu, Todd C. Mowry
2024 J jnl
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference.
CoRR
Aditya K. Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar
2024 J jnl
SIGMA: Secure GPT Inference with Function Secret Sharing.
Proc. Priv. Enhancing Technol.
Kanav Gupta, Neha Jawalkar, Ananta Mukherjee, Nishanth Chandran, Divya Gupta, Ashish Panwar, Rahul Sharma
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
2024 J jnl
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention.
CoRR
Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar
2023 J jnl
SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.
CoRR
Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee
2023 J jnl
SIGMA: Secure GPT Inference with Function Secret Sharing.
IACR Cryptol. ePrint Arch.
Kanav Gupta, Neha Jawalkar, Ananta Mukherjee, Nishanth Chandran, Divya Gupta, Ashish Panwar, Rahul Sharma
2021 A* conf
Fast local page-tables for virtualized NUMA servers with vMitosis.
ASPLOS
Ashish Panwar, Reto Achermann, Arkaprava Basu, Abhishek Bhattacharjee, K. Gopinath, Jayneel Gandhi
2021 A* conf
Trident: Harnessing Architectural Resources for All Page Sizes in x86 Processors.
MICRO
Venkat Sri Sai Ram, Ashish Panwar, Arkaprava Basu
2021 B conf
nuKSM: NUMA-aware Memory De-duplication on Multi-socket Servers.
PACT
Akash Panda, Ashish Panwar, Arkaprava Basu
2020 J jnl
Leveraging Architectural Support of Three Page Sizes with Trident.
CoRR
Venkat Sri Sai Ram, Ashish Panwar, Arkaprava Basu
2020 A* conf
Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines.
ASPLOS
Reto Achermann, Ashish Panwar, Abhishek Bhattacharjee, Timothy Roscoe, Jayneel Gandhi
2019 A* conf
HawkEye: Efficient Fine-grained OS Support for Huge Pages.
ASPLOS
Ashish Panwar, Sorav Bansal, K. Gopinath
2019 J jnl
Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines.
CoRR
Reto Achermann, Ashish Panwar, Abhishek Bhattacharjee, Timothy Roscoe, Jayneel Gandhi
2018 A* conf
Making Huge Pages Actually Useful.
ASPLOS
Ashish Panwar, Aravinda Prasad, K. Gopinath
2016 — conf
A Case for Protecting Huge Pages from the Kernel.
APSys
Ashish Panwar, Naman Patel, K. Gopinath
2015 Misc conf
Towards Practical Page Placement for a Green Memory Manager.
HiPC
Ashish Panwar, K. Gopinath