Search Results for author: Nipun Kwatra

Found 13 papers, 4 papers with code

Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

no code implementations4 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.

Scheduling

SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

no code implementations31 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.

Language Modelling Large Language Model

"Can't Take the Pressure?": Examining the Challenges of Blood Pressure Estimation via Pulse Wave Analysis

no code implementations23 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.

Blood pressure estimation

Towards Automating Retinoscopy for Refractive Error Diagnosis

no code implementations10 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.

Specificity

Distance Learner: Incorporating Manifold Prior to Model Training

1 code implementation14 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.

Adversarial Robustness

Keratoconus Classifier for Smartphone-based Corneal Topographer

no code implementations7 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.

Specificity Transfer Learning

Singularity: Planet-Scale, Preemptive and Elastic Scheduling of AI Workloads

no code implementations16 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).

Scheduling

LRTuner: A Learning Rate Tuner for Deep Neural Networks

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.

S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels

no code implementations23 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.

Unsupervised Clustering using Pseudo-semi-supervised Learning

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.

Clustering

AutoLR: A Method for Automatic Tuning of Learning Rate

no code implementations25 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.