Optimizing LLM Deployments through Inference Backends. Journal of Artificial Intelligence & Cloud Computing, [S. l.], v. 3, n. 4, p. 1–4, 2024. DOI: 10.47363/JAICC/2024(3)E128. Disponível em: https://srcpublishers.com/index.php/ai-cloud-computing/article/view/2545. Acesso em: 16 jan. 2026.