Koneru, Pavankumar, Sai Kumar Pola, and Prabhu Ravi. 2026. “When Does Disaggregated, Cache-Aware LLM Serving Pay Off? An Analytical Crossover Model Validated on Real Compute, Network, and Coordination Measurements”. International Journal of Artificial Intelligence and Machine Learning 6 (8s):1275-86. https://doi.org/10.51483/IJAIML.2970.