Memory-Aware GPU Resource Scheduling Prediction for DLRM Inference Services with BiGRU-Transformer Models. Journal of Global Engineering Review, [S. l.], v. 4, n. 2, p. 32–47, 2026. DOI: 10.66372/JGER.V4I2.3. Disponível em: https://globalengreview.org/index.php/jger/article/view/49. Acesso em: 23 jul. 2026.