4 papers
Unsupervised Cycle Detection in Agentic Applications
Felix George, Harshit Kumar, Divya Pathak +3
Agentic applications powered by Large Language Models exhibit non-deterministic behaviors that can form hidden execution cycles, silently consuming resources without triggering exp…
Metric Criticality Identification for Cloud Microservices
Akanksha Singal, Divya Pathak, Kaustabha Ray +3
Modern cloud-native applications built on microservice architectures present unprecedented challenges for system monitoring and alerting. Site Reliability Engineers (SREs) face the…
Statistical Modeling and Uncertainty Estimation of LLM Inference Systems
Kaustabha Ray, Nelson Mimura Gonzalez, Bruno Wassermann +2
Large Language Model (LLM) inference systems present significant challenges in statistical performance characterization due to dynamic workload variations, diverse hardware archite…
On the Partitioning of GPU Power among Multi-Instances
Tirth Vamja, Kaustabha Ray, Felix George +1
Efficient power management in cloud data centers is essential for reducing costs, enhancing performance, and minimizing environmental impact. GPUs, critical for tasks like machine…