2 papers
stat.ML2026
Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents
J. G. Dai, Tianze Deng, Yueying Li +1
As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems for efficient LLM inference becomes critical. While significant efforts have targeted sys…
math.PR2025
Tight matrices and heavy traffic steady state convergence in queueing networks
J. G. Dai, Yiquan Ji, Masakiyo Miyazawa
We are interested to prove that the stationary distribution of a multiclass queueing network converges to the stationary distribution of a semimartingale reflecting Brownian motion…