HUANG, Hen-Hsen. Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 46, p. 39707–39714, 2026. DOI: 10.1609/aaai.v40i46.41324. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41324. Acesso em: 25 may. 2026.