178 citations · 1.1k across the 84 of their papers we have counts for
63 papers · 1 filter
Understanding KV Residency in Production-Scale Agentic LLM Workloads
Mayank Arya, Agrim Bari, Anjaly Parayil +4
Agentic large language model (LLM) applications turn one user request into a sequence of model and tool calls over a growing context. Retaining this context's key-value (KV) state…
TrafficFab: An Autonomic Edge-Cloud Testbed Fabric forAI-Driven Traffic Management
Mayank Arya, Pranjal Naman, Priyanshu Pansari +5
Traffic management in emerging megacities requires real-time analytics over thousands of CCTV video streams under latency, bandwidth, compute and energy constraints. We present Tra…
Adaptive and Cost-Efficient Joint Scheduling of UAV Routes and Analytics with Transit-Borne Fog
Suman Raj, Arindam Khanda, Gagana M D +2
Unmanned Aerial Vehicles (UAVs) performing deadline-bound analytics over large rural areas cannot reliably offload workloads to sparse cellular base stations. We propose an approac…
A Resource-centric Analysis and Optimization of NoSQL Workloads using Distressed Resource Volume Metric
Gunika Verma, Aashutosh A, Pooja Srinivas +9
Large-scale managed cloud databases leverage sophisticated load Packing and Migration (PAM) algorithms, which provide the efficiencies necessary for running these services at scale…
Taurus: Accelerating Out-of-Core Graph Neural Network Inference on Billion-Scale Graphs
Pranjal Naman, Yogesh Simmhan
Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core sett…
ATLAS: Efficient Out-of-Core Inference for Billion-Scale Graph Neural Networks
Pranjal Naman, Yogesh Simmhan
Graph Neural Network (GNN) inference on billion-scale graphs is critical for domains like fintech and recommendation systems. Full-graph inference on these large graphs can be chal…
End-to-End and Phase-Level Performance Optimization for Hyperledger Fabric
Pavan Sollu, Aniruddha Mukherjee, Divya Pulivarthi +6
Hyperledger Fabric (HLF) is a modular, permissioned blockchain widely adopted in enterprise settings. Enhancing its throughput and latency remains challenging, as optimization deci…
Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks
Akash Sharma, Pranjal Naman, Roopkatha Banerjee +11
Real-time city-scale traffic analytics requires processing 100s-1000s of CCTV streams under strict latency, bandwidth, and compute limits. We present a scalable AI-driven Intellige…
AeroDaaS: A Programmable Drones-as-a-Service Platform for Intelligent Aerial Systems
Kautuk Astu, Suman Raj, Priyanshu Pansari +1
The increasing adoption of UAVs equipped with advanced sensors and GPU-accelerated edge computing has enabled real-time AI-driven applications in domains such as precision agricult…
Collaborative Processing for Multi-Tenant Inference on Memory-Constrained Edge TPUs
Nathan Ng, Walid A. Hanafy, Prashanthi Kadambi +5
IoT applications increasingly rely on on-device AI accelerators to ensure high performance, especially in low-connectivity and safety-critical scenarios. However, the limited on-ch…
RIPPLE++: An Incremental Framework for Efficient GNN Inference on Evolving Graphs
Pranjal Naman, Parv Agarwal, Hrishikesh Haritas +1
Real-world graphs are dynamic, with frequent updates to their structure and features due to evolving vertex and edge properties. These continual changes pose significant challenges…
FAME: QoS-aware Async Service Orchestration for Agentic Workflows
Haseeb Abdullah Kollorath, Vaibhav Jha, Varad Kulkarni +5
Agentic workflows built on Large Language Models (LLMs) increasingly rely on external tools, with Model Context Protocol (MCP) services emerging as a common interface for tool disc…
AeroResQ: Edge-Accelerated UAV Framework for Scalable, Resilient and Collaborative Escape Route Planning in Wildfire Scenarios
Suman Raj, Radhika Mittal, Rajiv Mayani +5
Drone fleets equipped with onboard cameras, computer vision, and Deep Neural Network (DNN) models present a powerful paradigm for real-time spatio-temporal decision-making. In wild…
OptimES: Optimizing Federated Learning Using Remote Embeddings for Graph Neural Networks
Pranjal Naman, Yogesh Simmhan
Graph Neural Networks (GNNs) have experienced rapid advancements in recent years due to their ability to learn meaningful representations from graph data structures. However, in mo…
Fulcrum: Optimizing Concurrent DNN Training and Inferencing on Edge Accelerators
Prashanthi S. K., Saisamarth Taluri, Pranav Gupta +6
The proliferation of GPU accelerated edge devices like Nvidia Jetsons and the rise in privacy concerns are placing an emphasis on concurrent DNN training and inferencing on edge de…
Pagoda: An Energy and Time Roofline Study for DNN Workloads on Edge Accelerators
Prashanthi S. K., Kunal Kumar Sahoo, Amartya Ranjan Saikia +4
Edge accelerators such as Nvidia Jetsons are becoming an integral part of the computing continuum, and are often used for DNN inferencing and training. Nvidia Jetson edge devices h…
Characterizing the Performance of Accelerated Jetson Edge Devices for Training Deep Learning Models
Prashanthi S. K., Sai Anuroop Kesanapalli, Yogesh Simmhan
Deep Neural Networks (DNNs) have had a significant impact on domains like autonomous vehicles and smart cities through low-latency inferencing on edge computing devices close to th…
AgentX: Towards Orchestrating Robust Agentic Workflow Patterns with FaaS-hosted MCP Services
Shiva Sai Krishna Anand Tokal, Vaibhav Jha, Anand Eswaran +2
Generative Artificial Intelligence (GenAI) has rapidly transformed various fields including code generation, text summarization, image generation and so on. Agentic AI is a recent…
Optimizing Federated Learning for Scalable Power-demand Forecasting in Microgrids
Roopkatha Banerjee, Sampath Koti, Gyanendra Singh +4
Real-time monitoring of power consumption in cities and micro-grids through the Internet of Things (IoT) can help forecast future demand and optimize grid operations. But moving al…
Characterizing FaaS Workflows on Public Clouds: The Good, the Bad and the Ugly
Varad Kulkarni, Nikhil Reddy, Tuhin Khare +3
Function-as-a-service (FaaS) is a popular serverless computing paradigm for developing event-driven functions that elastically scale on public clouds. FaaS workflows, such as AWS S…
AerialDB: A Federated Peer-to-Peer Spatio-temporal Edge Datastore for Drone Fleets
Shashwat Jaiswal, Suman Raj, Subhajit Sidhanta +1
Recent years have seen an unprecedented growth in research that leverages the newest computing paradigm of Internet of Drones, comprising a fleet of connected Unmanned Aerial Vehic…
Flotilla: A scalable, modular and resilient federated learning framework for heterogeneous resources
Roopkatha Banerjee, Prince Modi, Jinal Vyas +5
With the recent improvements in mobile and edge computing and rising concerns of data privacy, Federated Learning(FL) has rapidly gained popularity as a privacy-preserving, distrib…
Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks
Pranjal Naman, Yogesh Simmhan
Graph Neural Networks (GNNs) have experienced rapid advancements in recent years due to their ability to learn meaningful representations from graph data structures. Federated Lear…
Federated Learning within Global Energy Budget over Heterogeneous Edge Accelerators
Roopkatha Banerjee, Tejus Chandrashekar, Ananth Eswar +1
Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, optimizing both energy efficiency and model accuracy…