5 papers
Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off
Javad Mirzaei, Jeebak Mitra
Large Language Model (LLM) serving systems must balance latency and throughput while efficiently utilizing distributed GPU resources. This challenge arises because inference consis…
Characterizing Parallelism Strategies in LLM Inference: Fundamental Compute-Communication Trade-offs
Javad Mirzaei, Jeebak Mitra
Large Language Model (LLM) inference has become the dominant workload in modern AI systems, requiring serving infrastructures to maximize throughput while meeting strict latency Se…
Optimizing AI Inference Across the Deployment Stack
Tejinder Singh, John Pflueger, Jeebak Mitra +3
AI deployment performance is shaped not by model architecture alone, but by interactions among compression, compiler transformations, and serving policies. Published benchmarks oft…
TENORAN: Automating Fine-grained Energy Efficiency Profiling in Open RAN Systems
Ravis Shirkhani, Stefano Maxenti, Leonardo Bonati +7
The transition to disaggregated and interoperable Open Radio Access Network (RAN) architectures and the introduction of RAN Intelligent Controllers (RICs) in O-RAN creates new reso…
Graph Attention Network for Optimal User Association in Wireless Networks
Javad Mirzaei, Jeebak Mitra, Gwenael Poitau
With increased 5G deployments, network densification is higher than ever to support the exponentially high throughput requirements. However, this has meant a significant increase i…