problem in converting fp32 to fp16

[Macsim2]

Hi guys,
I'm trying to convert onnx model fp32 to fp16.
but I faced This messages in the function 'remove_unnecessary_cast_node'

"The downstream node of the second cast node should be graph output" (onnxconverter_common/float16.py:557)

I knew That message caused by None of Downstream node
I am trying to use the FP16 model as much as possible.
Is there any other method I can try?
Would using TensorRT instead of ONNX improve the situation?
thank you

[LeoZDong]

Could you attach the model? I think this error is saying that you have a cast node with no downstream node, which might be unexpected

[Macsim2]

@LeoZDong How can I attach the model? Can I just send the onnx file?
and also As a temporary solution, I solved it by changing from torch to float16.