ONNX运行时GPU推断

我正在尝试使用onnxruntime-gpu创建一个推理会话，我已经严重困惑了。

在onnx的官方教程中，https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb，他们在块[10]中创建了一个推理会话，看起来如下：

import psutil
import onnxruntime
import numpy

assert 'CUDAExecutionProvider' in onnxruntime.get_available_providers()
device_name = 'gpu'

sess_options = onnxruntime.SessionOptions()

# Optional: store the optimized graph and view it using Netron to verify that model is fully optimized.
# Note that this will increase session creation time so enable it for debugging only.
sess_options.optimized_model_filepath = os.path.join(output_dir, "optimized_model_{}.onnx".format(device_name))

# Please change the value according to best setting in Performance Test Tool result.
sess_options.intra_op_num_threads=psutil.cpu_count(logical=True)

session = onnxruntime.InferenceSession(export_model_path, sess_options)

latency = []
for i in range(total_samples):
    data = dataset[i]
    ort_inputs = {
        'input_ids':  data[0].cpu().reshape(1, max_seq_length).numpy(),
        'input_mask': data[1].cpu().reshape(1, max_seq_length).numpy(),
        'segment_ids': data[2].cpu().reshape(1, max_seq_length).numpy()
    }
    start = time.time()
    ort_outputs = session.run(None, ort_inputs)
    latency.append(time.time() - start)
    
print("OnnxRuntime {} Inference time = {} ms".format(device_name, format(sum(latency) * 1000 / len(latency), '.2f')))

我无法理解的是，在ort_input字典中，.cpu()...numpy()是在输入上调用的。但是，print语句声明推理会话正在GPU上运行。这有什么意义？这是否不会调用主机设备通信？