[OV] Introduce support of quantization If operation

[kshpv]

Changes

Add support of quantization for OpenVINO models with If operation - https://docs.openvino.ai/2023.0/openvino_docs_ops_infrastructure_If_8.html

Reason for changes

Customer request / Obtain the maximum performance for models with inner subgraphs under If operation

Related tickets

113826

Tests

Tested on a model attached to a ticket
Add synthetic model with If operation

[codecov]

Codecov Report

Merging #2101 (36381a7) into develop (b95e71c) will decrease coverage by 0.15%.
The diff coverage is 3.72%.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #2101      +/-   ##
===========================================
- Coverage    36.24%   36.09%   -0.15%     
===========================================
  Files          477      478       +1     
  Lines        42570    42757     +187     
===========================================
+ Hits         15428    15432       +4     
- Misses       27142    27325     +183     

Files Changed	Coverage Δ
...ncf/openvino/graph/metatypes/openvino_metatypes.py	0.00% <0.00%> (ø)
nncf/openvino/graph/model_transformer.py	0.00% <0.00%> (ø)
nncf/openvino/graph/node_utils.py	0.00% <0.00%> (ø)
nncf/openvino/graph/transformations/commands.py	0.00% <0.00%> (ø)
nncf/openvino/quantization/quantize_ifmodel.py	0.00% <0.00%> (ø)
nncf/openvino/quantization/quantize_model.py	0.00% <0.00%> (ø)
nncf/common/logging/track_progress.py	86.27% <100.00%> (-3.73%)	⬇️
nncf/quantization/algorithms/min_max/algorithm.py	95.30% <100.00%> (+0.06%)	⬆️

[KodiaqQ]

Need to have explanations for each method that was added. Also, the changes for the PostTrainingQuantization are not clear, including adding the backend entity for it.
The general approach and reasons for it are not clear.

[alexsu52]

LGTM