AI RESEARCH
Understanding and Improving Communication Performance in Multi-node LLM Inference
arXiv CS.LG
•
ArXi:2511.09557v4 Announce Type: replace-cross As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only across multiple GPUs but also across multiple nodes. In this work, we present a detailed performance study of multi-node distributed inference using LLMs on GPU-based supercomputers. We conduct experiments with several state-of-the-art inference engines alongside YALIS, a research-oriented prototype engine designed for controlled experimentation.