Inference Optimization Techniques for Real-Time Generative AI Applications. Journal of Generative Intelligence E: 3117-6429 P: 3117-6437, [S. l.], v. 2, n. 4, p. 9–16, 2025. Disponível em: https://galaxiauniverse.com/index.php/JGI/article/view/314. Acesso em: 30 aug. 2026.