Haowei Tu, et al. “LLM-Augmented Salable GPU Supply Forecasting for Disaggregated Recommendation Serving: Predicting Instance Readiness, Scheduling Delay, and Capacity Risk”. Journal of Advanced Computing Systems , vol. 4, no. 9, Sept. 2024, pp. 85-102, https://ciajournal.com/index.php/JACS/article/view/394.