Luo C, Wang X. Latency–Throughput Tradeoffs of ONNX Runtime, TensorRT-LLM, vLLM, and Triton: An Empirical Comparison on 1B–3B Parameter LLM Inference. SR [Internet]. 2026 Apr. 13 [cited 2026 Oct. 29];6(1). Available from: https://spectrumofresearch.com/index.php/sr/article/view/49