Print properties of compile model

[wgzintel]

print properties of compiled model:

Compiling the model to CPU ...
CPU SUPPORTED_PROPERTIES:
NETWORK_NAME: Model0
OPTIMAL_NUMBER_OF_INFER_REQUESTS: 1
NUM_STREAMS: 1
AFFINITY: Affinity.CORE
INFERENCE_NUM_THREADS: 96
PERF_COUNT: NO
INFERENCE_PRECISION_HINT: <Type: 'bfloat16'>
PERFORMANCE_HINT: LATENCY
EXECUTION_MODE_HINT: ExecutionMode.PERFORMANCE
PERFORMANCE_HINT_NUM_REQUESTS: 0
ENABLE_CPU_PINNING: True
SCHEDULING_CORE_TYPE: SchedulingCoreType.ANY_CORE
ENABLE_HYPER_THREADING: False
EXECUTION_DEVICES: CPU
CPU_DENORMALS_OPTIMIZATION: False
CPU_SPARSE_WEIGHTS_DECOMPRESSION_RATE: 1.0

[helena-intel]

Thanks @wgzintel ! Could you run make style in the repo root to fix the code quality check? Install requirements for that with pip install .[quality]

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[wgzintel]

Thanks @wgzintel ! Could you run make style in the repo root to fix the code quality check? Install requirements for that with pip install .[quality]

Done @helena-intel

[helena-intel]

Thanks for this PR @wgzintel this is really useful. It would be great if you could add a simple test to https://github.com/huggingface/optimum-intel/blob/main/tests/openvino/test_modeling.py. Nothing complicated, just that the function to print properties is run in the tests so we are alerted if it breaks at some point.

[echarlaix]

thanks for the addition @wgzintel