Update the cli option for OVEP for setting device and inference precision as seperate components.
Motivation and Context
The model can be inferenced with following precisions:
with its original input precision
With optimized precision (FP16 for GPU)
With user specified precision.
To facilitate the user in selecting the preferred precision this PR introduces a new session option "precision".
The usage will be to specify "device_type" session option with supported HW options from CPU, GPU and NPU.
Supported values for "precision" session option will be FP32, FP16, ACCURACY.
If precision is not specified, default optimized precision will be chosen for the specified hardware device.
Description
Update the cli option for OVEP for setting device and inference precision as seperate components.
Motivation and Context
The model can be inferenced with following precisions:
To facilitate the user in selecting the preferred precision this PR introduces a new session option "precision". The usage will be to specify "device_type" session option with supported HW options from CPU, GPU and NPU. Supported values for "precision" session option will be FP32, FP16, ACCURACY. If precision is not specified, default optimized precision will be chosen for the specified hardware device.
device_id session option is deprecated