I am a PhD candidate in Computer Science at Stanford University, where I work with Prof. Christos Kozyrakis on scaling software systems for Large Language Models (LLMs).
My broad research interests include distributed systems and cloud computing – in particular, I am interested in the system-side problems associated with learning, deploying, and operationalizing machine learning models at scale.
Previously, I was a Research Fellow at Microsoft Research India and prior to that obtained my Masters (by Research) in Computer and Data Systems from the Indian Institute of Science (IISc).
· [August 2024] Our work on Resilient DNN training is accepted to SOSP 2024! 🎉
· [June 2024] Awarded Stanford CS Department's Student Service Award 2023-24 🥳
1. ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation November 2024
Swapnil Gandhi, Mark Zhao, Athinagoras Skiadopoulos, and Christos Kozyrakis
30th ACM SIGOPS Symposium on Operating Systems Principles (SOSP) 2024
2. Improving DNN Inference Throughput Using Practical, Per-Input Compute Adaptation November 2024
Anand Iyer, Mingyu Guan, Yinwei Dai, Rui Pan, Swapnil Gandhi, and Ravi Netravali
30th ACM SIGOPS Symposium on Operating Systems Principles (SOSP) 2024
3. P3: Distributed Deep Graph Learning at Scale July 2021
Swapnil Gandhi and Anand Iyer
15th USENIX Symposium on Operating Systems Design and Implementation (OSDI) 2021
PDF
Video
Slides
4. An Interval-centric Model for Distributed Computing over Temporal Graphs April 2020
Swapnil Gandhi and Yogesh Simmhan
IEEE 36th International Conference on Data Engineering (ICDE) in Dalas, Texas 2020
PDF
Video
Slides
IEEE Xplore
Code
Distributed Programming Abstraction for Scalable Processing of Temporal Graphs January 2020
Swapnil Gandhi
M.Tech (Research) Thesis · Indian Institute of Science (IISc)
PDF
1. Wave : A Substrate for Distributed Incremental Graph Processing on Commodity Clusters October 2019
Swapnil Gandhi
ACM Student Research Competition (SRC) at 27th Symposium on Operating Systems Principles (SOSP), Ontario, Canada
Bronze Medal
2. Distributed Querying over Compressed Property Graphs December 2018
Swapnil Gandhi, Sayandip Sarkar, Abhilash Sharma, Yogesh Simmhan
Student Research Symposium (SRS) at 24th IEEE International Conference on High Performance Computing, Data and Analytics (HiPC), Jaipur, India
Best Poster Award