Koneru, P., Pola, S. K., & Ravi, P. (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), 1275–1286. https://doi.org/10.51483/IJAIML.2970