您是否尝试加载模型，然后在每次有请求时进行推断？
您应该只加载一次，并在推理进程的整个生命周期中保留会话。您还可以查看ONNXruntime附带的执行提供程序，以尝试加快推理时间，如CUDA, tensorRT ...

import onnxruntime as ort

def load_model(onnx_model_path):
    inference_session = ort.InferenceSession(
            onnx_model_path,
        )
    
     # get input and output names of model layers for inference placeholder
     inputs = inference_session.get_inputs()[0].name
     outputs = [
            output.name for output in inference_session.get_outputs()
        ]

     return inference_session, {"inputs": inputs, "outputs": outputs}

def main():
    inf_session, input_output_dict = load_model("your/model.onnx")

    while True:
        inf_session.run(input_output_dict["outputs"], {
                str(input_output_dict[inputs]): your_array_input})