Add fp16 support for split cache

[PatriceVignola]

What does this PR do?

It fixes the following error when using a fp16 model with split fp16 input/output cache:

onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Unexpected input data type. Actual: (tensor(float)) , expected: (tensor(float16))

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[fxmarty]

Thank you for the fix!