From the 1 of 8 linked papers with an AI index.
6 papers · 1 filter
OpRAG: A Resource-Deterministic Runtime for GPU-Backed Multi-Stage RAG Workflows
Arup Kumar Sarker, Mills Staylor, Aymen Alsaadi +3
Agentic retrieval-augmented generation (RAG) systems combine preprocessing, embedding, retrieval, memory access, context construction, generation, and vector-index updates. Althoug…
[AAFLOW+] Stateful Operator Abstraction with Zero-Copy Distributed KV Cache Orchestration for Multi-Agent Workflows
Arup Kumar Sarker, Alexander James Halpern, Mills Staylor +5
The paper presents AAFLOW+, a framework that treats key‑value (KV) caches as distributed objects, enabling zero‑copy sharing of model state across multi‑agent LLM workflows to cut…
AAFLOW: Scalable Patterns for Agentic AI Workflows
Arup Kumar Sarker, Mills Staylor, Aymen Alsaadi +3
Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to…
Combining Serverless and High-Performance Computing Paradigms to support ML Data-Intensive Applications
Mills Staylor, Arup Kumar Sarker, Gregor von Laszewski +3
Data is found everywhere, from health and human infrastructure to the surge of sensors and the proliferation of internet-connected devices. To meet this challenge, the data enginee…
Towards Experiment Execution in Support of Community Benchmark Workflows for HPC
Gregor von Laszewski, Wesley Brewer, Sean R. Wilkinson +5
A key hurdle is demonstrating compute resource capability with limited benchmarks. We propose workflow templates as a solution, offering adaptable designs for specific scientific a…
Deep RC: A Scalable Data Engineering and Deep Learning Pipeline
Arup Kumar Sarker, Aymen Alsaadi, Alexander James Halpern +7
Significant obstacles exist in scientific domains including genetics, climate modeling, and astronomy due to the management, preprocess, and training on complicated data for deep l…