JOHN R. MATTHEWS. Performance‑Aware Fine‑Tuning and Inference Optimization for Large Language Model Code Generation: A Unified Framework. American Journal of Applied Science and Technology, [S. l.], v. 5, n. 11, p. 277–282, 2025. Disponível em: https://theusajournals.com/index.php/ajast/article/view/8336. Acesso em: 18 feb. 2026.