`clip` behaviour with NaN values is different between GPU and CPU onnx inference about onnx HOT 5 OPEN

import torch  # Not used but initializing the CUDA execution provider fails without it...

import numpy as np
import onnx
from onnx.onnx_pb import TensorProto
import onnxruntime

input = onnx.helper.make_tensor_value_info("input", TensorProto.FLOAT, ["N", 10])
output = onnx.helper.make_tensor_value_info("output", TensorProto.FLOAT, ["N", 10])

min_const = onnx.helper.make_node(
        "Constant",
        inputs=[],
        outputs=["min_const"],
        value=onnx.numpy_helper.from_array(np.array([10.0] * 10, dtype=np.float32)))

min_node = onnx.helper.make_node(
        "Min",
        inputs=["input", "min_const"],
        outputs=["output"],
        )

graph_def = onnx.helper.make_graph(
        nodes=[min_const, min_node],
        name="test-model",
        inputs=[input],
        outputs=[output])

opset_import = onnx.helper.make_opsetid("", 17)

model_def = onnx.helper.make_model(
        graph_def,
        opset_imports=[opset_import],
        producer_name="test")

onnx.checker.check_model(model_def, full_check=True)

model_path = 'test_min.onnx'
onnx.save(model_def, model_path)

input = np.random.randn(3, 10).astype(np.float32)
input[0, :] = np.nan

cpu_session = onnxruntime.InferenceSession(model_path, providers=["CPUExecutionProvider"])
output = cpu_session.run(["output"], {"input": input})
print("CPU session output:")
print(output)

gpu_session = onnxruntime.InferenceSession(model_path, providers=["CUDAExecutionProvider"])
output = gpu_session.run(["output"], {"input": input})
print("GPU session output:")
print(output)

class ONNXModel(nn.Module):
    def forward(self, x):
        lower = torch.scalar_tensor(-10.0)
        upper = torch.scalar_tensor(10.0)
        x = x.clip(lower, upper)
        x[torch.isnan(x)] = 0.0
        return x