Sotabase

Career

· Principal Researcher, Microsoft2018–
· Co-founder, Chekkoo2015–2017
· Senior Software Engineer, Google2011–2015
· PhD in Computer Science, Stanford University2006–2011
· Masters in Computer Science, Georgia Institute of Technology2004–2006
· B.Tech in Computer Science and Engineering, Indian Institute of Technology, Delhi2000–2004

Publications (49)

Texture optimization for example-based synthesis
ACM Transactions on Graphics · 2005
767
cited
Gandiva: Introspective Cluster Scheduling for Deep Learning
USENIX Symposium on Operating Systems Design and Implementation · 2018
536
cited
Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve
USENIX Symposium on Operating Systems Design and Implementation · 2024
386
cited
Two-Way Coupled SPH and Particle Level Set Fluid Simulation
IEEE Transactions on Visualization and Computer Graphics · 2008
275
cited
SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills
arXiv.org · 2023
165
cited
Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning
European Conference on Computer Systems · 2020
164
cited
A method for avoiding the acoustic time step restriction in compressible flow
Journal of Computational Physics · 2009
145
cited
RespireNet: A Deep Neural Network for Accurately Detecting Abnormal Lung Sounds in Limited Data Setting
Annual International Conference of the IEEE Engineering in Medicine and Biology Society · 2020
111
cited
Varuna: scalable, low-cost training of massive deep learning models
European Conference on Computer Systems · 2021
108
cited
Vidur: A Large-Scale Simulation Framework For LLM Inference
Conference on Machine Learning and Systems · 2024
83
cited
Texturing Fluids
IEEE Transactions on Visualization and Computer Graphics · 2006
78
cited
Numerically stable fluid-structure interactions between compressible flow and solid structures
Journal of Computational Physics · 2011
61
cited
A Framework for Activity Recognition and Detection of Unusual Activities
Indian Conference on Computer Vision, Graphics & Image Processing · 2004
53
cited
Just-In-Time Checkpointing: Low Cost Error Recovery from Deep Learning Training Failures
European Conference on Computer Systems · 2024
39
cited
Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule
Journal of machine learning research · 2020
34
cited
Fluid Simulation with Articulated Bodies
IEEE Transactions on Visualization and Computer Graphics · 2010
32
cited
Practical animation of compressible flow for shock waves and related phenomena
Symposium on Computer Animation · 2010
23
cited
Singularity: Planet-Scale, Preemptive and Elastic Scheduling of AI Workloads
arXiv.org · 2022
23
cited
Unsupervised Clustering using Pseudo-semi-supervised Learning
International Conference on Learning Representations · 2020
21
cited
Examining the challenges of blood pressure estimation via photoplethysmogram
Scientific Reports · 2024
16
cited
Sotabase
Nipun Kwatra | Researcher Profile | Sotabase | Sotabase