no code implementations • 4 Mar 2024 • Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Alexey Tumanov, Ramachandran Ramjee
However, batching multiple requests leads to an interleaving of prefill and decode iterations which makes it challenging to achieve both high throughput and low latency.
no code implementations • 31 Aug 2023 • Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee
SARATHI employs chunked-prefills, which splits a prefill request into equal sized chunks, and decode-maximal batching, which constructs a batch using a single prefill chunk and populates the remaining slots with decodes.
no code implementations • 23 Apr 2023 • Suril Mehta, Nipun Kwatra, Mohit Jain, Daniel McDuff
The use of observed wearable sensor data (e. g., photoplethysmograms [PPG]) to infer health measures (e. g., glucose level or blood pressure) is a very active area of research.
no code implementations • 10 Aug 2022 • Aditya Aggarwal, Siddhartha Gairola, Uddeshya Upadhyay, Akshay P Vasishta, Diwakar Rao, Aditya Goyal, Kaushik Murali, Nipun Kwatra, Mohit Jain
We develop a video processing pipeline that takes retinoscopic videos as input and estimates the net refractive error based on our proposed extension of the retinoscopy mathematical model.
1 code implementation • 14 Jul 2022 • Aditya Chetan, Nipun Kwatra
The manifold hypothesis (real world data concentrates near low-dimensional manifolds) is suggested as the principle behind the effectiveness of machine learning algorithms in very high dimensional problems that are common in domains such as vision and speech.
no code implementations • 7 May 2022 • Siddhartha Gairola, Pallavi Joshi, Anand Balasubramaniam, Kaushik Murali, Nipun Kwatra, Mohit Jain
Similar to medical-grade topographers, SmartKC outputs curvature heatmaps and quantitative metrics that need to be evaluated by doctors for keratoconus diagnosis.
no code implementations • 16 Feb 2022 • Dharma Shukla, Muthian Sivathanu, Srinidhi Viswanatha, Bhargav Gulavani, Rimma Nehme, Amey Agrawal, Chen Chen, Nipun Kwatra, Ramachandran Ramjee, Pankaj Sharma, Atul Katiyar, Vipul Modi, Vaibhav Sharma, Abhishek Singh, Shreshth Singhal, Kaustubh Welankar, Lu Xun, Ravi Anupindi, Karthik Elangovan, Hasibur Rahman, Zhou Lin, Rahul Seetharaman, Cheng Xu, Eddie Ailijiang, Suresh Krishnappa, Mark Russinovich
At the heart of Singularity is a novel, workload-aware scheduler that can transparently preempt and elastically scale deep learning workloads to drive high utilization without impacting their correctness or performance, across a global fleet of AI accelerators (e. g., GPUs, FPGAs).
1 code implementation • ICML Workshop AutoML 2021 • Nikhil Iyer, V Thejas, Nipun Kwatra, Ramachandran Ramjee, Muthian Sivathanu
For example on ImageNet with Resnet-50, LRTuner shows up to 0. 2% absolute gains in test accuracy compared to the hand-tuned baseline schedule.
1 code implementation • 31 Oct 2020 • Siddhartha Gairola, Francis Tom, Nipun Kwatra, Mohit Jain
Auscultation of respiratory sounds is the primary tool for screening and diagnosing lung diseases.
Ranked #10 on Audio Classification on ICBHI Respiratory Sound Database (using extra training data)
no code implementations • 23 Oct 2020 • Arunava Chakraborty, Rahul Ragesh, Mahir Shah, Nipun Kwatra
We propose a framework for semi-supervised training of cGANs which utilizes sparse labels to learn the conditional mapping, and at the same time leverages a large amount of unsupervised data to learn the unconditional distribution.
no code implementations • ICLR 2020 • Divam Gupta, Ramachandran Ramjee, Nipun Kwatra, Muthian Sivathanu
In this paper, we propose a framework that leverages semi-supervised models to improve unsupervised clustering performance.
2 code implementations • 9 Mar 2020 • Nikhil Iyer, V Thejas, Nipun Kwatra, Ramachandran Ramjee, Muthian Sivathanu
Several papers argue that wide minima generalize better than narrow minima.
Ranked #6 on Machine Translation on WMT2014 German-English
no code implementations • 25 Sep 2019 • Nipun Kwatra, V Thejas, Nikhil Iyer, Ramachandran Ramjee, Muthian Sivathanu
We compare favorably against state of the art learning rate schedules for the given dataset and models, including for ImageNet on Resnet-50, Cifar-10 on Resnet-18, and SQuAD fine-tuning on BERT.