4 papers
When Scaling Fails: Network and Fabric Effects on Distributed GPU Training Performance
Dinesh Gopalan, Ratul Ali
Scaling distributed GPU training is commonly assumed to yield predictable performance gains as additional nodes are added. In practice, many large-scale deployments encounter dimin…
HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference
Dinesh Gopalan, Ratul Ali
The escalating demand for high-fidelity, real-time inference in distributed edge-cloud environments necessitates aggressive model optimization to counteract severe latency and ener…
Scalable and Secure AI Inference in Healthcare: A Comparative Benchmarking of FastAPI and Triton Inference Server on Kubernetes
Ratul Ali
Efficient and scalable deployment of machine learning (ML) models is a prerequisite for modern production environments, particularly within regulated domains such as healthcare and…
ML-ASPA: A Contemplation of Machine Learning-based Acoustic Signal Processing Analysis for Sounds, & Strains Emerging Technology
Ratul Ali, Aktarul Islam, Md. Shohel Rana +3
Acoustic data serves as a fundamental cornerstone in advancing scientific and engineering understanding across diverse disciplines, spanning biology, communications, and ocean and…