Haowei Tu, Siming Zhao, and Samuel He . “LLM-Augmented Salable GPU Supply Forecasting for Disaggregated Recommendation Serving: Predicting Instance Readiness, Scheduling Delay, and Capacity Risk”. Journal of Advanced Computing & Intelligent Systems 4, no. 9 (September 24, 2024): 85–102. Accessed October 6, 2026. https://learnedvertex.com/index.php/JACIS/article/view/394.