Token-Burst-Aware Capacity Planning for LLM Inference Services: Request Arrival, Token Demand, and Failure Risk Modeling from BurstGPT Traces. Journal of Technology Informatics and Engineering, [S. l.], v. 5, n. 2, p. 142–164, 2026. DOI: 10.51903/jtie.v5i2.565. Disponível em: https://jtie.stekom.ac.id/index.php/jtie/article/view/565. Acesso em: 8 sep. 2026.