resolve args datatype mismatch for split LPT (#33160)
We are enabling CoPilot models on OV GPU. The models are quantized in
uint8/int8 or uint16/int16 datatypes.
FQ layers with int16/uint16 data types are stripped.
https://github.com/openvinotoolkit/openvino/blob/master/src/common/low_precision_transformations/src/qdq_stripping.cpp
With one model, we observer the below error which happens at split LPT
transformation.
One input (Gather output) is in FP32 since DQ layers after Gather are
stripped and the other input is in FP16 which cause mismatch between
input data types during multiplication.
https://github.com/openvinotoolkit/openvino/blob/master/src/common/low_precision_transformations/src/split.cpp
<img width="1911" height="1018" alt="split-args-elem-type"
src="https://github.com/user-attachments/assets/d390178e-1ec5-42f2-aaf5-907c389a25da"
/>
<img width="1903" height="1067" alt="split"
src="https://github.com/user-attachments/assets/bdada859-7bf8-454d-a2ad-be14b7a7308c"
/>
To resolve that issue, conversion between data types happen before
elementwise (mult) operation.
### Tickets:
- *CVS-177905*
---------
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
