ZHENG, Yixin; TANG, Ruming. Quantifying the Throughput–Tail-Latency Trade-off of Continuous Batching and Chunked-Prefill Scheduling under Production LLM Traces: An Empirical Comparison. Spectrum of Research, [S. l.], v. 6, n. 2, 2026. Disponível em: https://spectrumofresearch.com/index.php/sr/article/view/58. Acesso em: 29 oct. 2026.