Transformations: API 2.0 transition part 3 for LPT transformations (#19610)

* lpt transformations: transition to api 2.0, ngraph -> openvino * use ov namespace for lpt transformations * fix low_precision usings * includes refactoring * delete RecurrentGraphRewrite and RecurrentMatcher as unused classes * use ov header for itt; delete the disabled test * delete the unused function * suppress doxygen warning * fix link in the documentation
2023-09-13 16:30:31 +04:00
parent 3454139931
commit d0213301a5
547 changed files with 2797 additions and 3176 deletions
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step2_markup.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step2_markup.md
@@ -105,7 +105,7 @@ Model display features (here and below):

 The transformation is required and includes two tasks:

-1. Mark operation input ports (create ``Precision`` attribute instance) by provided restrictions: input port index and required precisions. Restrictions are provided as input argument in ``:ref:`ngraph::pass::low_precision::LowPrecision <doxid-classngraph_1_1pass_1_1low__precision_1_1_low_precision>``` constructor. 
+1. Mark operation input ports (create ``Precision`` attribute instance) by provided restrictions: input port index and required precisions. Restrictions are provided as input argument in ``:ref:`ov::pass::low_precision::LowPrecision <doxid-classov_1_1pass_1_1low__precision_1_1_low_precision>``` constructor. 
 2. Mark precision preserved operations. 

 No attributes are required before the transformation. Changes in the example model after ``MarkupPrecisions`` transformation:
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step1_prerequisites/convert_subtract_constant.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step1_prerequisites/convert_subtract_constant.md
@@ -1,3 +1,3 @@
 # ConvertSubtractConstant transformation {#openvino_docs_OV_UG_lpt_ConvertSubtractConstant}

-ngraph::pass::low_precision::ConvertSubtractConstant class represents the `ConvertSubtractConstant` transformation.
+ov::pass::low_precision::ConvertSubtractConstant class represents the `ConvertSubtractConstant` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step1_prerequisites/pull_reshape_through_dequantization.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step1_prerequisites/pull_reshape_through_dequantization.md
@@ -1,3 +1,3 @@
 # PullReshapeThroughDequantization transformation {#openvino_docs_OV_UG_lpt_PullReshapeThroughDequantization}

-ngraph::pass::low_precision::PullReshapeThroughDequantization class represents the `PullReshapeThroughDequantization` transformation.
+ov::pass::low_precision::PullReshapeThroughDequantization class represents the `PullReshapeThroughDequantization` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step1_prerequisites/pull_transpose_through_dequantization.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step1_prerequisites/pull_transpose_through_dequantization.md
@@ -1,3 +1,3 @@
 # PullTransposeThroughDequantization transformation {#openvino_docs_OV_UG_lpt_PullTransposeThroughDequantization}

-ngraph::pass::low_precision::PullTransposeThroughDequantization class represents the `PullTransposeThroughDequantization` transformation.
+ov::pass::low_precision::PullTransposeThroughDequantization class represents the `PullTransposeThroughDequantization` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/align_quantization_intervals.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/align_quantization_intervals.md
@@ -1,3 +1,3 @@
 # AlignQuantizationIntervals transformation {#openvino_docs_OV_UG_lpt_AlignQuantizationIntervals}

-ngraph::pass::low_precision::AlignQuantizationIntervals class represents the `AlignQuantizationIntervals` transformation.
+ov::pass::low_precision::AlignQuantizationIntervals class represents the `AlignQuantizationIntervals` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/align_quantization_parameters.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/align_quantization_parameters.md
@@ -1,3 +1,3 @@
 # AlignQuantizationParameters transformation {#openvino_docs_OV_UG_lpt_AlignQuantizationParameters}

-ngraph::pass::low_precision::AlignQuantizationParameters class represents the `AlignQuantizationParameters` transformation.
+ov::pass::low_precision::AlignQuantizationParameters class represents the `AlignQuantizationParameters` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/create_attribute.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/create_attribute.md
@@ -1,3 +1,3 @@
 # CreateAttribute transformation {#openvino_docs_OV_UG_lpt_CreateAttribute}

-ngraph::pass::low_precision::CreateAttribute class represents the `CreateAttribute` transformation.
+ov::pass::low_precision::CreateAttribute class represents the `CreateAttribute` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/create_precisions_dependent_attribute.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/create_precisions_dependent_attribute.md
@@ -1,3 +1,3 @@
 # CreatePrecisionsDependentAttribute transformation {#openvino_docs_OV_UG_lpt_CreatePrecisionsDependentAttribute}

-ngraph::pass::low_precision::CreatePrecisionsDependentAttribute class represents the `CreatePrecisionsDependentAttribute` transformation.
+ov::pass::low_precision::CreatePrecisionsDependentAttribute class represents the `CreatePrecisionsDependentAttribute` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_avg_pool_precision_preserved.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_avg_pool_precision_preserved.md
@@ -1,3 +1,3 @@
 # MarkupAvgPoolPrecisionPreserved transformation {#openvino_docs_OV_UG_lpt_MarkupAvgPoolPrecisionPreserved}

-ngraph::pass::low_precision::MarkupAvgPoolPrecisionPreserved class represents the `MarkupAvgPoolPrecisionPreserved` transformation.
+ov::pass::low_precision::MarkupAvgPoolPrecisionPreserved class represents the `MarkupAvgPoolPrecisionPreserved` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_bias.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_bias.md
@@ -1,3 +1,3 @@
 # MarkupBias transformation {#openvino_docs_OV_UG_lpt_MarkupBias}

-ngraph::pass::low_precision::MarkupBias class represents the `MarkupBias` transformation.
+ov::pass::low_precision::MarkupBias class represents the `MarkupBias` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_can_be_quantized.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_can_be_quantized.md
@@ -1,3 +1,3 @@
 # MarkupCanBeQuantized transformation {#openvino_docs_OV_UG_lpt_MarkupCanBeQuantized}

-ngraph::pass::low_precision::MarkupCanBeQuantized class represents the `MarkupCanBeQuantized` transformation.
+ov::pass::low_precision::MarkupCanBeQuantized class represents the `MarkupCanBeQuantized` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_per_tensor_quantization.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_per_tensor_quantization.md
@@ -1,3 +1,3 @@
 # MarkupPerTensorQuantization transformation {#openvino_docs_OV_UG_lpt_MarkupPerTensorQuantization}

-ngraph::pass::low_precision::MarkupPerTensorQuantization class represents the `MarkupPerTensorQuantization` transformation.
+ov::pass::low_precision::MarkupPerTensorQuantization class represents the `MarkupPerTensorQuantization` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_precisions.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/markup_precisions.md
@@ -1,3 +1,3 @@
 # MarkupPrecisions transformation {#openvino_docs_OV_UG_lpt_MarkupPrecisions}

-ngraph::pass::low_precision::MarkupPrecisions class represents the `MarkupPrecisions` transformation.
+ov::pass::low_precision::MarkupPrecisions class represents the `MarkupPrecisions` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_precisions.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_precisions.md
@@ -1,3 +1,3 @@
 # PropagatePrecisions transformation {#openvino_docs_OV_UG_lpt_PropagatePrecisions}

-ngraph::pass::low_precision::PropagatePrecisions class represents the `PropagatePrecisions` transformation.
+ov::pass::low_precision::PropagatePrecisions class represents the `PropagatePrecisions` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_shared_value.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_shared_value.md
@@ -1,3 +1,3 @@
 # PropagateSharedValue transformation {#openvino_docs_OV_UG_lpt_PropagateSharedValue}

-ngraph::pass::low_precision::PropagateSharedValue class represents the `PropagateSharedValue` transformation.
+ov::pass::low_precision::PropagateSharedValue class represents the `PropagateSharedValue` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_through_precision_preserved.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_through_precision_preserved.md
@@ -1,3 +1,3 @@
 # PropagateThroughPrecisionPreserved transformation {#openvino_docs_OV_UG_lpt_PropagateThroughPrecisionPreserved}

-ngraph::pass::low_precision::PropagateThroughPrecisionPreserved class represents the `PropagateThroughPrecisionPreserved` transformation.
+ov::pass::low_precision::PropagateThroughPrecisionPreserved class represents the `PropagateThroughPrecisionPreserved` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_to_input.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/propagate_to_input.md
@@ -1,3 +1,3 @@
 # PropagateToInput transformation {#openvino_docs_OV_UG_lpt_PropagateToInput}

-ngraph::pass::low_precision::PropagateToInput class represents the `PropagateToInput` transformation.
+ov::pass::low_precision::PropagateToInput class represents the `PropagateToInput` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/update_shared_precision_preserved.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step2_markup/update_shared_precision_preserved.md
@@ -1,3 +1,3 @@
 # UpdateSharedPrecisionPreserved transformation {#openvino_docs_OV_UG_lpt_UpdateSharedPrecisionPreserved}

-ngraph::pass::low_precision::UpdateSharedPrecisionPreserved class represents the `UpdateSharedPrecisionPreserved` transformation.
+ov::pass::low_precision::UpdateSharedPrecisionPreserved class represents the `UpdateSharedPrecisionPreserved` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/activation/clamp.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/activation/clamp.md
@@ -1,3 +1,3 @@
 # ClampTransformation transformation {#openvino_docs_OV_UG_lpt_ClampTransformation}

-ngraph::pass::low_precision::ClampTransformation class represents the `Clamp` operation transformation.
+ov::pass::low_precision::ClampTransformation class represents the `Clamp` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/activation/prelu.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/activation/prelu.md
@@ -1,3 +1,3 @@
 # PReluTransformation transformation {#openvino_docs_OV_UG_lpt_PReluTransformation}

-ngraph::pass::low_precision::PReluTransformation class represents the `PRelu` operation transformation.
+ov::pass::low_precision::PReluTransformation class represents the `PRelu` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/activation/relu.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/activation/relu.md
@@ -1,3 +1,3 @@
 # ReluTransformation transformation {#openvino_docs_OV_UG_lpt_ReluTransformation}

-ngraph::pass::low_precision::ReluTransformation class represents the `Relu` operation transformation.
+ov::pass::low_precision::ReluTransformation class represents the `Relu` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/arithmetic/add.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/arithmetic/add.md
@@ -1,6 +1,6 @@
 # AddTransformation transformation {#openvino_docs_OV_UG_lpt_AddTransformation}

-ngraph::pass::low_precision::AddTransformation class represents the `Add` operation transformation.
+ov::pass::low_precision::AddTransformation class represents the `Add` operation transformation.

 The transformation propagates dequantization subtraction from one input branch to another and propagates dequantization multiplication from the same branch through `Add` operation. In transformation result, one `Add` operation input branch is in low precision without dequantization operations (empty branch), another input branch is in original precision with updated dequantization operations (full branch).

--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/arithmetic/multiply.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/arithmetic/multiply.md
@@ -1,3 +1,3 @@
 # MultiplyTransformation transformation {#openvino_docs_OV_UG_lpt_MultiplyTransformation}

-ngraph::pass::low_precision::MultiplyTransformation class represents the `Multiply` operation transformation.
+ov::pass::low_precision::MultiplyTransformation class represents the `Multiply` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/arithmetic/subtract.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/arithmetic/subtract.md
@@ -1,3 +1,3 @@
 # SubtractTransformation transformation {#openvino_docs_OV_UG_lpt_SubtractTransformation}

-ngraph::pass::low_precision::SubtractTransformation class represents the `Subtract` operation transformation.
+ov::pass::low_precision::SubtractTransformation class represents the `Subtract` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/convolution/convolution.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/convolution/convolution.md
@@ -1,6 +1,6 @@
 # ConvolutionTransformation transformation {#openvino_docs_OV_UG_lpt_ConvolutionTransformation}

-ngraph::pass::low_precision::ConvolutionTransformation class represents the `Convolution` operation transformation.
+ov::pass::low_precision::ConvolutionTransformation class represents the `Convolution` operation transformation.

 The transformation propagates dequantization operations on activations and weights through the `Convolution` operation. The transformation supports several weights quantization approaches:
 * quantized weights in low precision with dequantization operations,
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/convolution/convolution_backprop_data.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/convolution/convolution_backprop_data.md
@@ -1,3 +1,3 @@
 # ConvolutionBackpropDataTransformation transformation {#openvino_docs_OV_UG_lpt_ConvolutionBackpropDataTransformation}

-ngraph::pass::low_precision::ConvolutionBackpropDataTransformation class represents the `ConvolutionBackpropData` operation transformation.
+ov::pass::low_precision::ConvolutionBackpropDataTransformation class represents the `ConvolutionBackpropData` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/convolution/group_convolution.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/convolution/group_convolution.md
@@ -1,3 +1,3 @@
 # GroupConvolutionTransformation transformation {#openvino_docs_OV_UG_lpt_GroupConvolutionTransformation}

-ngraph::pass::low_precision::GroupConvolutionTransformation class represents the `GroupConvolution` operation transformation.
+ov::pass::low_precision::GroupConvolutionTransformation class represents the `GroupConvolution` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/image/interpolate.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/image/interpolate.md
@@ -1,3 +1,3 @@
 # InterpolateTransformation transformation {#openvino_docs_OV_UG_lpt_InterpolateTransformation}

-ngraph::pass::low_precision::InterpolateTransformation class represents the `Interpolate` operation transformation.
+ov::pass::low_precision::InterpolateTransformation class represents the `Interpolate` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/matrix/mat_mul.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/matrix/mat_mul.md
@@ -1,3 +1,3 @@
 # MatMulTransformation transformation {#openvino_docs_OV_UG_lpt_MatMulTransformation}

-ngraph::pass::low_precision::MatMulTransformation class represents the `MatMul` operation transformation.
+ov::pass::low_precision::MatMulTransformation class represents the `MatMul` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/concat.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/concat.md
@@ -1,3 +1,3 @@
 # ConcatTransformation transformation {#openvino_docs_OV_UG_lpt_ConcatTransformation}

-ngraph::pass::low_precision::ConcatTransformation class represents the `Concat` operation transformation.
+ov::pass::low_precision::ConcatTransformation class represents the `Concat` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/depth_to_space.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/depth_to_space.md
@@ -1,3 +1,3 @@
 # DepthToSpaceTransformation transformation {#openvino_docs_OV_UG_lpt_DepthToSpaceTransformation}

-ngraph::pass::low_precision::DepthToSpaceTransformation class represents the `DepthToSpace` operation transformation.
+ov::pass::low_precision::DepthToSpaceTransformation class represents the `DepthToSpace` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/gather.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/gather.md
@@ -1,3 +1,3 @@
 # GatherTransformation transformation {#openvino_docs_OV_UG_lpt_GatherTransformation}

-ngraph::pass::low_precision::GatherTransformation class represents the `Gather` operation transformation.
+ov::pass::low_precision::GatherTransformation class represents the `Gather` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/pad.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/pad.md
@@ -1,3 +1,3 @@
 # PadTransformation transformation {#openvino_docs_OV_UG_lpt_PadTransformation}

-ngraph::pass::low_precision::PadTransformation class represents the `Pad` operation transformation.
+ov::pass::low_precision::PadTransformation class represents the `Pad` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/shuffle_channels.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/shuffle_channels.md
@@ -1,3 +1,3 @@
 # ShuffleChannelsTransformation transformation {#openvino_docs_OV_UG_lpt_ShuffleChannelsTransformation}

-ngraph::pass::low_precision::ShuffleChannelsTransformation class represents the `ShuffleChannels` operation transformation.
+ov::pass::low_precision::ShuffleChannelsTransformation class represents the `ShuffleChannels` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/split.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/split.md
@@ -1,3 +1,3 @@
 # SplitTransformation transformation {#openvino_docs_OV_UG_lpt_SplitTransformation}

-ngraph::pass::low_precision::SplitTransformation class represents the `Split` operation transformation.
+ov::pass::low_precision::SplitTransformation class represents the `Split` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/strided_slice.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/strided_slice.md
@@ -1,3 +1,3 @@
 # StridedSliceTransformation transformation {#openvino_docs_OV_UG_lpt_StridedSliceTransformation}

-ngraph::pass::low_precision::StridedSliceTransformation class represents the `StridedSlice` operation transformation.
+ov::pass::low_precision::StridedSliceTransformation class represents the `StridedSlice` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/transpose.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/transpose.md
@@ -1,3 +1,3 @@
 # TransposeTransformation transformation {#openvino_docs_OV_UG_lpt_TransposeTransformation}

-ngraph::pass::low_precision::TransposeTransformation class represents the `Transpose` operation transformation.
+ov::pass::low_precision::TransposeTransformation class represents the `Transpose` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/variadic_split.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/movement/variadic_split.md
@@ -1,3 +1,3 @@
 # VariadicSplitTransformation transformation {#openvino_docs_OV_UG_lpt_VariadicSplitTransformation}

-ngraph::pass::low_precision::VariadicSplitTransformation class represents the `VariadicSplit` operation transformation.
+ov::pass::low_precision::VariadicSplitTransformation class represents the `VariadicSplit` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/normalization/mvn.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/normalization/mvn.md
@@ -1,3 +1,3 @@
 # MVNTransformation transformation {#openvino_docs_OV_UG_lpt_MVNTransformation}

-ngraph::pass::low_precision::MVNTransformation class represents the `MVN` operation transformation.
+ov::pass::low_precision::MVNTransformation class represents the `MVN` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/normalization/normalize_l2.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/normalization/normalize_l2.md
@@ -1,3 +1,3 @@
 # NormalizeL2Transformation transformation {#openvino_docs_OV_UG_lpt_NormalizeL2Transformation}

-ngraph::pass::low_precision::NormalizeL2Transformation class represents the `NormalizeL2` operation transformation.
+ov::pass::low_precision::NormalizeL2Transformation class represents the `NormalizeL2` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/pooling/avg_pool.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/pooling/avg_pool.md
@@ -1,3 +1,3 @@
 # AvgPoolTransformation transformation {#openvino_docs_OV_UG_lpt_AvgPoolTransformation}

-ngraph::pass::low_precision::AvgPoolTransformation class represents the `AvgPool` operation transformation.
+ov::pass::low_precision::AvgPoolTransformation class represents the `AvgPool` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/pooling/max_pool.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/pooling/max_pool.md
@@ -1,3 +1,3 @@
 # MaxPoolTransformation transformation {#openvino_docs_OV_UG_lpt_MaxPoolTransformation}

-ngraph::pass::low_precision::MaxPoolTransformation class represents the `MaxPool` operation transformation.
+ov::pass::low_precision::MaxPoolTransformation class represents the `MaxPool` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/quantization/fake_quantize.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/quantization/fake_quantize.md
@@ -1,3 +1,3 @@
 # FakeQuantizeTransformation transformation {#openvino_docs_OV_UG_lpt_FakeQuantizeTransformation}

-ngraph::pass::low_precision::FakeQuantizeTransformation class represents the `FakeQuantize` operation transformation.
+ov::pass::low_precision::FakeQuantizeTransformation class represents the `FakeQuantize` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/quantization/fold_fake_quantize.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/quantization/fold_fake_quantize.md
@@ -1,3 +1,3 @@
 # FoldFakeQuantizeTransformation transformation {#openvino_docs_OV_UG_lpt_FoldFakeQuantizeTransformation}

-ngraph::pass::low_precision::FoldFakeQuantizeTransformation class represents the `FoldFakeQuantize` operation transformation.
+ov::pass::low_precision::FoldFakeQuantizeTransformation class represents the `FoldFakeQuantize` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_max.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_max.md
@@ -1,3 +1,3 @@
 # ReduceMaxTransformation transformation {#openvino_docs_OV_UG_lpt_ReduceMaxTransformation}

-ngraph::pass::low_precision::ReduceMaxTransformation class represents the `ReduceMax` operation transformation.
+ov::pass::low_precision::ReduceMaxTransformation class represents the `ReduceMax` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_mean.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_mean.md
@@ -1,3 +1,3 @@
 # ReduceMeanTransformation transformation {#openvino_docs_OV_UG_lpt_ReduceMeanTransformation}

-ngraph::pass::low_precision::ReduceMeanTransformation class represents the `ReduceMean` operation transformation.
+ov::pass::low_precision::ReduceMeanTransformation class represents the `ReduceMean` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_min.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_min.md
@@ -1,3 +1,3 @@
 # ReduceMinTransformation transformation {#openvino_docs_OV_UG_lpt_ReduceMinTransformation}

-ngraph::pass::low_precision::ReduceMinTransformation class represents the `ReduceMin` operation transformation.
+ov::pass::low_precision::ReduceMinTransformation class represents the `ReduceMin` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_sum.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/reduction/reduce_sum.md
@@ -1,3 +1,3 @@
 # ReduceSumTransformation transformation {#openvino_docs_OV_UG_lpt_ReduceSumTransformation}

-ngraph::pass::low_precision::ReduceSumTransformation class represents the `ReduceSum` operation transformation.
+ov::pass::low_precision::ReduceSumTransformation class represents the `ReduceSum` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/shape/reshape.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/shape/reshape.md
@@ -1,3 +1,3 @@
 # ReshapeTransformation transformation {#openvino_docs_OV_UG_lpt_ReshapeTransformation}

-ngraph::pass::low_precision::ReshapeTransformation class represents the `Reshape` operation transformation.
+ov::pass::low_precision::ReshapeTransformation class represents the `Reshape` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/shape/squeeze.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/shape/squeeze.md
@@ -1,3 +1,3 @@
 # SqueezeTransformation transformation {#openvino_docs_OV_UG_lpt_SqueezeTransformation}

-ngraph::pass::low_precision::SqueezeTransformation class represents the `Squeeze` operation transformation.
+ov::pass::low_precision::SqueezeTransformation class represents the `Squeeze` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/shape/unsqueeze.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step3_main/shape/unsqueeze.md
@@ -1,3 +1,3 @@
 # UnsqueezeTransformation transformation {#openvino_docs_OV_UG_lpt_UnsqueezeTransformation}

-ngraph::pass::low_precision::UnsqueezeTransformation class represents the `Unsqueeze` operation transformation.
+ov::pass::low_precision::UnsqueezeTransformation class represents the `Unsqueeze` operation transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/eliminate_fake_quantize.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/eliminate_fake_quantize.md
@@ -1,3 +1,3 @@
 # EliminateFakeQuantizeTransformation transformation {#openvino_docs_OV_UG_lpt_EliminateFakeQuantizeTransformation}

-ngraph::pass::low_precision::EliminateFakeQuantizeTransformation class represents the `EliminateFakeQuantizeTransformation` transformation.
+ov::pass::low_precision::EliminateFakeQuantizeTransformation class represents the `EliminateFakeQuantizeTransformation` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fake_quantize_decomposition.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fake_quantize_decomposition.md
@@ -1,3 +1,3 @@
 # FakeQuantizeDecompositionTransformation transformation {#openvino_docs_OV_UG_lpt_FakeQuantizeDecompositionTransformation}

-ngraph::pass::low_precision::FakeQuantizeDecompositionTransformation class represents the `FakeQuantizeDecompositionTransformation` transformation.
+ov::pass::low_precision::FakeQuantizeDecompositionTransformation class represents the `FakeQuantizeDecompositionTransformation` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fold_convert.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fold_convert.md
@@ -1,3 +1,3 @@
 # FoldConvertTransformation transformation {#openvino_docs_OV_UG_lpt_FoldConvertTransformation}

-ngraph::pass::low_precision::FoldConvertTransformation class represents the `FoldConvertTransformation` transformation.
+ov::pass::low_precision::FoldConvertTransformation class represents the `FoldConvertTransformation` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fuse_convert.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fuse_convert.md
@@ -1,3 +1,3 @@
 # FuseConvertTransformation transformation {#openvino_docs_OV_UG_lpt_FuseConvertTransformation}

-ngraph::pass::low_precision::FuseConvertTransformation class represents the `FuseConvertTransformation` transformation.
+ov::pass::low_precision::FuseConvertTransformation class represents the `FuseConvertTransformation` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fuse_multiply_to_fake_quantize.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fuse_multiply_to_fake_quantize.md
@@ -1,3 +1,3 @@
 # FuseMultiplyToFakeQuantizeTransformation transformation {#openvino_docs_OV_UG_lpt_FuseMultiplyToFakeQuantizeTransformation}

-ngraph::pass::low_precision::FuseMultiplyToFakeQuantizeTransformation class represents the `FuseMultiplyToFakeQuantizeTransformation` transformation.
+ov::pass::low_precision::FuseMultiplyToFakeQuantizeTransformation class represents the `FuseMultiplyToFakeQuantizeTransformation` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fuse_subtract_to_fake_quantize.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/fuse_subtract_to_fake_quantize.md
@@ -1,3 +1,3 @@
 # FuseSubtractToFakeQuantizeTransformation transformation {#openvino_docs_OV_UG_lpt_FuseSubtractToFakeQuantizeTransformation}

-ngraph::pass::low_precision::FuseSubtractToFakeQuantizeTransformation class represents the `FuseSubtractToFakeQuantizeTransformation` transformation.
+ov::pass::low_precision::FuseSubtractToFakeQuantizeTransformation class represents the `FuseSubtractToFakeQuantizeTransformation` transformation.
--- a/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/multiply_to_group_convolution.md
+++ b/docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/transformations/step4_cleanup/multiply_to_group_convolution.md
@@ -1,3 +1,3 @@
 # MultiplyToGroupConvolutionTransformation transformation {#openvino_docs_OV_UG_lpt_MultiplyToGroupConvolutionTransformation}

-ngraph::pass::low_precision::MultiplyToGroupConvolutionTransformation class represents the `MultiplyToGroupConvolutionTransformation` transformation.
+ov::pass::low_precision::MultiplyToGroupConvolutionTransformation class represents the `MultiplyToGroupConvolutionTransformation` transformation.
--- a/docs/snippets/lpt_intel_cpu_plugin.cpp
+++ b/docs/snippets/lpt_intel_cpu_plugin.cpp
@@ -33,9 +33,9 @@ ov::pass::Manager manager;
 auto pass_config = manager.get_pass_config();
 //! [lpt_common]
 // check if the function is quantized to ignore LPT transformations for not quantized function to speed up model loading
-const bool useLpt = ngraph::pass::low_precision::LowPrecision::isFunctionQuantized(nGraphFunc);
+const bool useLpt = ov::pass::low_precision::LowPrecision::isFunctionQuantized(nGraphFunc);
 auto defaultPrecisions =
-    useLpt ? ngraph::pass::low_precision::precision_set::int8_support : std::vector<ov::element::Type>{};
+    useLpt ? ov::pass::low_precision::precision_set::int8_support : std::vector<ov::element::Type>{};
 if (useLpt) {
    // disable constant folding on dequantization subgraphs so they can be processed by LPT
    manager.register_pass<ov::pass::MarkDequantizationSubgraph>(defaultPrecisions);
@@ -45,7 +45,7 @@ if (useLpt) {

 if (useLpt) {
    // convert subtract constant to INT8 to prevent unnecessary FP16 to FP32 conversion
-    manager.register_pass<ngraph::pass::low_precision::ConvertSubtractConstant>(defaultPrecisions);
+    manager.register_pass<ov::pass::low_precision::ConvertSubtractConstant>(defaultPrecisions);
 }

 // nGraph common transformations happen here
@@ -53,12 +53,12 @@ if (useLpt) {
 if (useLpt) {
    // convert not supported cases FakeQuantize -> Convert -> Convert -> Subtract -> Multiply to a single FakeQuantize
    pass_config->set_callback<ov::pass::ConvertQuantizeDequantize>([&defaultPrecisions](const std::shared_ptr<const ngraph::Node> &node) -> bool {
-        return ngraph::pass::low_precision::NetworkHelper::areQuantizeAndDequantizeSupportedForMultiply(node, defaultPrecisions);
+        return ov::pass::low_precision::NetworkHelper::areQuantizeAndDequantizeSupportedForMultiply(node, defaultPrecisions);
    });

    // convert not supported cases FakeQuantize -> Convert -> Convert -> Subtract -> Multiply to a single FakeQuantize
    pass_config->set_callback<ov::pass::ConvertSubtract>([&defaultPrecisions](const std::shared_ptr<const ngraph::Node> &node) -> bool {
-        return ngraph::pass::low_precision::NetworkHelper::areQuantizeAndDequantizeSupportedForSubtract(node, defaultPrecisions);
+        return ov::pass::low_precision::NetworkHelper::areQuantizeAndDequantizeSupportedForSubtract(node, defaultPrecisions);
    });
 }

@@ -66,7 +66,7 @@ manager.run_passes(nGraphFunc);
 //! [lpt_common]

 //! [lpt_execution]
-using namespace ngraph::pass::low_precision;
+using namespace ov::pass::low_precision;
 if (useLpt) {
    // Low precision transformations plugin specific configuration: restrictions definition
    auto supportedPrecisions = std::vector<PrecisionsRestriction>({
@@ -96,7 +96,7 @@ if (useLpt) {

    // Low precision transformations instantiation and registration in pass manager
    ov::pass::Manager lptManager;
-    lptManager.register_pass<ngraph::pass::low_precision::LowPrecision>(supportedPrecisions, perTensorQuantization);
+    lptManager.register_pass<ov::pass::low_precision::LowPrecision>(supportedPrecisions, perTensorQuantization);

    // Low precision transformations plugin specific configuration: transformation callbacks definition
    lptManager.get_pass_config()->set_callback<MarkupPrecisions>([](const std::shared_ptr<const ngraph::Node>& node) -> bool {
@@ -130,7 +130,7 @@ int lpt_supported_precisions() {
 std::shared_ptr<ov::Model> nGraphFunc;
 ov::pass::Manager manager;

-using namespace ngraph::pass::low_precision;
+using namespace ov::pass::low_precision;
 //! [lpt_supported_precisions]
 auto supportedPrecisions = std::vector<PrecisionsRestriction>({
    PrecisionsRestriction::create<ov::opset1::Convolution>({
@@ -140,7 +140,7 @@ auto supportedPrecisions = std::vector<PrecisionsRestriction>({
 });

 ov::pass::Manager lptManager;
-lptManager.register_pass<ngraph::pass::low_precision::LowPrecision>(supportedPrecisions);
+lptManager.register_pass<ov::pass::low_precision::LowPrecision>(supportedPrecisions);
 lptManager.run_passes(nGraphFunc);
 //! [lpt_supported_precisions]

@@ -154,7 +154,7 @@ return 0;
 int per_tensor_quantization() {
 std::shared_ptr<ov::Model> nGraphFunc;
 //! [per_tensor_quantization]
-using namespace ngraph::pass::low_precision;
+using namespace ov::pass::low_precision;

 const std::vector<PrecisionsRestriction> emptyRestrictions;

@@ -163,7 +163,7 @@ auto perTensorQuantization = std::vector<QuantizationGranularityRestriction>({
 });

 ov::pass::Manager lptManager;
-lptManager.register_pass<ngraph::pass::low_precision::LowPrecision>(emptyRestrictions, perTensorQuantization);
+lptManager.register_pass<ov::pass::low_precision::LowPrecision>(emptyRestrictions, perTensorQuantization);
 lptManager.run_passes(nGraphFunc);
 //! [per_tensor_quantization]

@@ -177,10 +177,10 @@ auto pass_config = manager.get_pass_config();


 //! [asymmetric_quantization]
-using namespace ngraph::pass::low_precision;
+using namespace ov::pass::low_precision;
 ov::pass::Manager lptManager;

-lptManager.register_pass<ngraph::pass::low_precision::LowPrecision>();
+lptManager.register_pass<ov::pass::low_precision::LowPrecision>();
 lptManager.get_pass_config()->set_callback<ConvolutionBackpropDataTransformation>([&defaultPrecisions](const std::shared_ptr<const ngraph::Node>& node) -> bool {
    return LayerTransformation::isAsymmetricQuantization(node, defaultPrecisions) || WeightableLayerTransformation::isAsymmetricOnWeights(node);
 });
@@ -194,7 +194,7 @@ int lpt_markup_pipeline() {
 std::shared_ptr<ov::Model> nGraphFunc;
 ov::pass::Manager manager;

-using namespace ngraph::pass::low_precision;
+using namespace ov::pass::low_precision;
 //! [lpt_markup_pipeline]
 auto supportedPrecisions = std::vector<PrecisionsRestriction>({
    PrecisionsRestriction::create<ov::opset1::Convolution>({
@@ -208,7 +208,7 @@ auto perTensorQuantization = std::vector<QuantizationGranularityRestriction>({
 });

 ov::pass::Manager lptManager;
-lptManager.register_pass<ngraph::pass::low_precision::LowPrecision>(supportedPrecisions, perTensorQuantization);
+lptManager.register_pass<ov::pass::low_precision::LowPrecision>(supportedPrecisions, perTensorQuantization);
 lptManager.run_passes(nGraphFunc);
 //! [lpt_markup_pipeline]

--- a/docs/suppress_warnings.txt
+++ b/docs/suppress_warnings.txt
@@ -16,6 +16,7 @@ no uniquely matching class member found for
 example was already documented\. ignoring documentation found here\.
 documentation for unknown define
 detected potential recursive class relation between class
+no matching class member found for
 no matching file member found for
 documented empty return type of
 documented symbol
--- a/src/common/low_precision_transformations/include/itt.hpp
+++ b/src/common/low_precision_transformations/include/itt.hpp
@@ -9,11 +9,11 @@

 #pragma once

-#include <openvino/cc/selective_build.h>
-#include <openvino/itt.hpp>
-#include <openvino/cc/ngraph/itt.hpp>
+#include "openvino/cc/selective_build.h"
+#include "openvino/itt.hpp"
+#include "openvino/cc/pass/itt.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {
 namespace itt {
--- a/src/common/low_precision_transformations/include/low_precision/add.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/add.hpp
@@ -4,10 +4,10 @@

 #pragma once

-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/eltwise_base_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,10 +24,10 @@ class LP_TRANSFORMATIONS_API AddTransformation : public EltwiseBaseTransformatio
 public:
    OPENVINO_RTTI("AddTransformation", "0");
    AddTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/align_quantization_intervals.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/align_quantization_intervals.hpp
@@ -9,7 +9,7 @@
 #include "low_precision/layer_transformation.hpp"
 #include "openvino/pass/pass.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -17,7 +17,7 @@ class LP_TRANSFORMATIONS_API AlignQuantizationIntervals;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 /**
 * @ingroup ie_transformation_common_api
@@ -28,11 +28,11 @@ class LP_TRANSFORMATIONS_API AlignQuantizationIntervals;
 * [AlignQuantizationIntervals](@ref openvino_docs_OV_UG_lpt_AlignQuantizationIntervals) page
 * in the Inference Engine Developer Guide.
 */
-class ngraph::pass::low_precision::AlignQuantizationIntervals : public ov::pass::ModelPass {
+class ov::pass::low_precision::AlignQuantizationIntervals : public ov::pass::ModelPass {
 public:
    OPENVINO_RTTI("AlignQuantizationIntervals", "0");
-    AlignQuantizationIntervals(const std::vector<ov::element::Type>& defaultPrecisions = ngraph::pass::low_precision::precision_set::int8_support);
+    AlignQuantizationIntervals(const std::vector<ov::element::Type>& defaultPrecisions = ov::pass::low_precision::precision_set::int8_support);
    bool run_on_model(const std::shared_ptr<ov::Model>& m) override;
 private:
-    const std::vector<ngraph::element::Type> defaultPrecisions;
+    const std::vector<ov::element::Type> defaultPrecisions;
 };
--- a/src/common/low_precision_transformations/include/low_precision/align_quantization_parameters.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/align_quantization_parameters.hpp
@@ -6,11 +6,11 @@

 #include <memory>

-#include <ngraph/pass/pass.hpp>
+#include "openvino/pass/pass.hpp"
 #include "low_precision/lpt_visibility.hpp"
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -18,7 +18,7 @@ class LP_TRANSFORMATIONS_API AlignQuantizationParameters;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 /**
 * @ingroup ie_transformation_common_api
@@ -29,11 +29,11 @@ class LP_TRANSFORMATIONS_API AlignQuantizationParameters;
 * [AlignQuantizationParameters](@ref openvino_docs_OV_UG_lpt_AlignQuantizationParameters) page
 * in the Inference Engine Developer Guide.
 */
-class ngraph::pass::low_precision::AlignQuantizationParameters : public ov::pass::ModelPass {
+class ov::pass::low_precision::AlignQuantizationParameters : public ov::pass::ModelPass {
 public:
    OPENVINO_RTTI("AlignQuantizationParameters", "0");
-    AlignQuantizationParameters(const std::vector<ngraph::element::Type> defaultPrecisions = ngraph::pass::low_precision::precision_set::int8_support);
-    bool run_on_model(const std::shared_ptr<ngraph::Function>& m) override;
+    AlignQuantizationParameters(const std::vector<ov::element::Type> defaultPrecisions = ov::pass::low_precision::precision_set::int8_support);
+    bool run_on_model(const std::shared_ptr<ov::Model>& m) override;
 private:
-    const std::vector<ngraph::element::Type> defaultPrecisions;
+    const std::vector<ov::element::Type> defaultPrecisions;
 };
--- a/src/common/low_precision_transformations/include/low_precision/assign_and_read_value.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/assign_and_read_value.hpp
@@ -4,24 +4,24 @@

 #pragma once

-#include <ngraph/ngraph.hpp>
+
 #include "layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

 class LP_TRANSFORMATIONS_API AssignAndReadValueTransformation : public LayerTransformation {
 public:
    OPENVINO_RTTI("AssignAndReadValueTransformation", "0");
-    AssignAndReadValueTransformation(const std::shared_ptr<ngraph::Function> function, const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher& m) override;
+    AssignAndReadValueTransformation(const std::shared_ptr<ov::Model> model, const Params& params = Params());
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher& m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> op) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 private:
-    std::shared_ptr<ngraph::Function> function;
+    std::shared_ptr<ov::Model> model;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/avg_pool.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/avg_pool.hpp
@@ -7,7 +7,7 @@
 #include <algorithm>
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -30,4 +30,4 @@ public:

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/base_matcher_pass.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/base_matcher_pass.hpp
@@ -3,11 +3,11 @@
 //

 #pragma once
-#include <ngraph/node.hpp>
-#include <ngraph/pass/graph_rewrite.hpp>
+#include "openvino/core/node.hpp"
+#include "openvino/pass/graph_rewrite.hpp"
 #include "rt_info/attribute_parameters.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -15,9 +15,9 @@ class LP_TRANSFORMATIONS_API BaseMatcherPass;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

-class LP_TRANSFORMATIONS_API ngraph::pass::low_precision::BaseMatcherPass : public ov::pass::MatcherPass {
+class LP_TRANSFORMATIONS_API ov::pass::low_precision::BaseMatcherPass : public ov::pass::MatcherPass {
 public:
    BaseMatcherPass(const AttributeParameters& params = AttributeParameters());
    AttributeParameters params;
--- a/src/common/low_precision_transformations/include/low_precision/clamp.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/clamp.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/ngraph.hpp>
+
 #include "layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,11 +24,11 @@ class LP_TRANSFORMATIONS_API ClampTransformation : public LayerTransformation {
 public:
    OPENVINO_RTTI("ClampTransformation", "0");
    ClampTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher& m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher& m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> op) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/common/fake_quantize_dequantization.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/common/fake_quantize_dequantization.hpp
@@ -6,11 +6,11 @@

 #include <memory>
 #include <tuple>
-#include <low_precision/lpt_visibility.hpp>
+#include "low_precision/lpt_visibility.hpp"
 #include "openvino/core/node.hpp"
 #include "openvino/opsets/opset1.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -35,17 +35,17 @@ public:
    bool isLowPrecision() const;
    std::shared_ptr<Node> copyWithNewInput(const std::shared_ptr<Node>& input) const;

-    bool checkElementwise(const std::shared_ptr<ngraph::Node>& elementwise) const;
+    bool checkElementwise(const std::shared_ptr<ov::Node>& elementwise) const;

-    static bool checkShape(const std::shared_ptr<ngraph::Node>& elementwise);
+    static bool checkShape(const std::shared_ptr<ov::Node>& elementwise);

    static int fillDequantizationParams(
-        const std::shared_ptr<ngraph::Node>& elementwise,
+        const std::shared_ptr<ov::Node>& elementwise,
        std::shared_ptr<ov::opset1::Convert>& convert,
        std::shared_ptr<ov::opset1::Constant>& constant);

    static int fillDequantizationParams(
-        const std::shared_ptr<ngraph::Node>& elementwise,
+        const std::shared_ptr<ov::Node>& elementwise,
        std::shared_ptr<ov::opset1::Constant>& constant);

    size_t channelDimIndex;
@@ -60,4 +60,4 @@ public:

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/common/ie_lpt_exception.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/common/ie_lpt_exception.hpp
@@ -6,16 +6,16 @@

 #include <exception>
 #include <string>
-#include <ngraph/node.hpp>
-#include <low_precision/lpt_visibility.hpp>
+#include "openvino/core/node.hpp"
+#include "low_precision/lpt_visibility.hpp"

 /**
 * @def THROW_TRANSFORMATION_EXCEPTION_LPT
 * @brief A macro used to throw the exception with a notable description for low precision transformations
 */
-#define THROW_IE_LPT_EXCEPTION(node) throw ::ngraph::pass::low_precision::InferenceEngineLptException(__FILE__, __LINE__, node)
+#define THROW_IE_LPT_EXCEPTION(node) throw ::ov::pass::low_precision::InferenceEngineLptException(__FILE__, __LINE__, node)

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -39,7 +39,7 @@ public:
    }
 };

-#define THROW_TRANSFORMATION_EXCEPTION throw ::ngraph::pass::low_precision::Exception() << __FILE__ << ":" << __LINE__ << " "
+#define THROW_TRANSFORMATION_EXCEPTION throw ::ov::pass::low_precision::Exception() << __FILE__ << ":" << __LINE__ << " "


 class LP_TRANSFORMATIONS_API InferenceEngineLptException : public Exception {
@@ -53,4 +53,4 @@ public:

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/common/port_quantization_granularity_restriction.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/common/port_quantization_granularity_restriction.hpp
@@ -11,7 +11,7 @@
 #include "low_precision/lpt_visibility.hpp"
 #include "low_precision/rt_info/quantization_granularity_attribute.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -27,4 +27,4 @@ public:

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/common/precisions_restriction.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/common/precisions_restriction.hpp
@@ -9,10 +9,10 @@
 #include <unordered_set>
 #include <vector>

-#include <low_precision/lpt_visibility.hpp>
+#include "low_precision/lpt_visibility.hpp"
 #include "openvino/core/node.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {
 /**
@@ -21,30 +21,30 @@ namespace low_precision {
 * the same precision for mentioned
 *
 * // One restriction for each port
-* PrecisionsRestriction::create<ngraph::opset1::Convolution>({
-*      {{0}, {ngraph::element::u8}},
-*      {{1}, {ngraph::element::i8}},
+* PrecisionsRestriction::create<ov::opset1::Convolution>({
+*      {{0}, {ov::element::u8}},
+*      {{1}, {ov::element::i8}},
 *  }),
 *
 * // Common precision restriction for several ports:
 * // both inputs will have the same precision
-* PrecisionsRestriction::create<ngraph::opset5::LSTMSequence>({
-*      {{0, 1}, {ngraph::element::u8, ngraph::element::i8}}
+* PrecisionsRestriction::create<ov::opset5::LSTMSequence>({
+*      {{0, 1}, {ov::element::u8, ov::element::i8}}
 *  }),
 */
 class PrecisionsRestriction {
 public:
-    using PrecisionsByPorts = std::vector<std::pair<std::vector<size_t>, std::vector<ngraph::element::Type>>>;
+    using PrecisionsByPorts = std::vector<std::pair<std::vector<size_t>, std::vector<ov::element::Type>>>;
    using PrecisionsByPortsFunction = std::function<PrecisionsByPorts(const std::shared_ptr<Node>&)>;

-    ngraph::Node::type_info_t operationType;
+    ov::Node::type_info_t operationType;
    bool specifyVersion;
    PrecisionsByPorts precisionsByPorts;
    PrecisionsByPortsFunction precisionsByPortsFunction;

    PrecisionsRestriction() = default;
    PrecisionsRestriction(
-        const ngraph::Node::type_info_t& operationType,
+        const ov::Node::type_info_t& operationType,
        const bool specifyVersion,
        const PrecisionsByPorts& precisionsByPorts) :
        operationType(operationType),
@@ -52,7 +52,7 @@ public:
        precisionsByPorts(precisionsByPorts) {}

    PrecisionsRestriction(
-        const ngraph::Node::type_info_t& operationType,
+        const ov::Node::type_info_t& operationType,
        const bool specifyVersion,
        const PrecisionsByPortsFunction& precisionsByPortsFunction) :
        operationType(operationType),
@@ -86,4 +86,4 @@ public:

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/common/quantization_granularity_restriction.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/common/quantization_granularity_restriction.hpp
@@ -6,26 +6,26 @@

 #include <vector>

-#include <ngraph/node.hpp>
+#include "openvino/core/node.hpp"

-#include <low_precision/lpt_visibility.hpp>
-#include <low_precision/rt_info/quantization_granularity_attribute.hpp>
-#include <low_precision/common/port_quantization_granularity_restriction.hpp>
+#include "low_precision/lpt_visibility.hpp"
+#include "low_precision/rt_info/quantization_granularity_attribute.hpp"
+#include "low_precision/common/port_quantization_granularity_restriction.hpp"


-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

 class LP_TRANSFORMATIONS_API QuantizationGranularityRestriction {
 public:
-    ngraph::Node::type_info_t operationType;
+    ov::Node::type_info_t operationType;
    bool specifyVersion;
    std::vector<PortQuantizationGranularityRestriction> restrictions;

    QuantizationGranularityRestriction() = default;
    QuantizationGranularityRestriction(
-        const ngraph::Node::type_info_t operationType,
+        const ov::Node::type_info_t operationType,
        const bool specifyVersion,
        const std::vector<PortQuantizationGranularityRestriction>& restrictions) :
        operationType(operationType),
@@ -48,7 +48,7 @@ public:
        for (auto i = 0ul; i < restrictedPorts.size(); ++i) {
            restrictions.push_back(PortQuantizationGranularityRestriction(
                restrictedPorts[i],
-                ngraph::QuantizationGranularityAttribute::Granularity::PerTensor));
+                ov::QuantizationGranularityAttribute::Granularity::PerTensor));
        }
        return QuantizationGranularityRestriction(T::get_type_info_static(), specifyVersion, restrictions);
    }
@@ -66,4 +66,4 @@ public:

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/concat.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/concat.hpp
@@ -10,12 +10,12 @@
 #include <string>
 #include <vector>

-#include <ngraph/ngraph.hpp>
+

 #include "layer_transformation.hpp"
 #include "common/fake_quantize_dequantization.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -31,7 +31,7 @@ class LP_TRANSFORMATIONS_API ConcatTransformation : public LayerTransformation {
 public:
    OPENVINO_RTTI("ConcatTransformation", "0");
    ConcatTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
    static bool isQuantizedStatic(const std::shared_ptr<const Node>& layer);
@@ -39,4 +39,4 @@ public:

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/convert.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/convert.hpp
@@ -4,10 +4,10 @@

 #pragma once

-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -15,10 +15,10 @@ class LP_TRANSFORMATIONS_API ConvertTransformation : public LayerTransformation
 public:
    OPENVINO_RTTI("ConvertTransformation", "0");
    ConvertTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/convert_subtract_constant.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/convert_subtract_constant.hpp
@@ -7,10 +7,10 @@
 #include <memory>
 #include <utility>

-#include <low_precision/lpt_visibility.hpp>
+#include "low_precision/lpt_visibility.hpp"
 #include "openvino/pass/graph_rewrite.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -18,7 +18,7 @@ class LP_TRANSFORMATIONS_API ConvertSubtractConstant;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 /**
 * @ingroup ie_transformation_common_api
@@ -29,8 +29,8 @@ class LP_TRANSFORMATIONS_API ConvertSubtractConstant;
 * [ConvertSubtractConstant](@ref openvino_docs_OV_UG_lpt_ConvertSubtractConstant) page
 * in the Inference Engine Developer Guide.
 */
-class ngraph::pass::low_precision::ConvertSubtractConstant : public ov::pass::MatcherPass {
+class ov::pass::low_precision::ConvertSubtractConstant : public ov::pass::MatcherPass {
 public:
    OPENVINO_RTTI("ConvertSubtractConstant", "0");
-    ConvertSubtractConstant(const std::vector<ngraph::element::Type>& constantPrecisions = {});
+    ConvertSubtractConstant(const std::vector<ov::element::Type>& constantPrecisions = {});
 };
--- a/src/common/low_precision_transformations/include/low_precision/convolution.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/convolution.hpp
@@ -6,7 +6,7 @@

 #include "weightable_layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,14 +24,14 @@ public:
    ConvolutionTransformation(const Params& params = Params());
    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool isQuantized(const std::shared_ptr<const Node>& layer,
-        const std::vector<ngraph::element::Type>&defaultPrecisions) const override;
+        const std::vector<ov::element::Type>&defaultPrecisions) const override;
    static bool isQuantizedStatic(const std::shared_ptr<const Node>& layer,
-        const std::vector<ngraph::element::Type>& defaultPrecisions);
+        const std::vector<ov::element::Type>& defaultPrecisions);

 protected:
-    size_t getInputChannels(const std::shared_ptr<ngraph::Node> conv) const override;
+    size_t getInputChannels(const std::shared_ptr<ov::Node> conv) const override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/convolution_backprop_data.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/convolution_backprop_data.hpp
@@ -6,7 +6,7 @@

 #include "weightable_layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,14 +24,14 @@ public:
    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> op) const override;
    bool isQuantized(const std::shared_ptr<const Node>& layer,
-        const std::vector<ngraph::element::Type>&defaultPrecisions) const override;
+        const std::vector<ov::element::Type>&defaultPrecisions) const override;
    static bool isQuantizedStatic(const std::shared_ptr<const Node>& layer,
-        const std::vector<ngraph::element::Type>& defaultPrecisions);
+        const std::vector<ov::element::Type>& defaultPrecisions);

 protected:
-    size_t getInputChannels(const std::shared_ptr<ngraph::Node> conv) const override;
+    size_t getInputChannels(const std::shared_ptr<ov::Node> conv) const override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/create_attribute.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/create_attribute.hpp
@@ -8,13 +8,13 @@
 #include <memory>
 #include <vector>

-#include <ngraph/pass/graph_rewrite.hpp>
-#include <ngraph/pattern/op/wrap_type.hpp>
+#include "openvino/pass/graph_rewrite.hpp"
+#include "openvino/pass/pattern/op/wrap_type.hpp"
 #include "low_precision/lpt_visibility.hpp"
 #include "low_precision/base_matcher_pass.hpp"
 #include "low_precision/lpt_itt.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -23,7 +23,7 @@ class CreateAttribute;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 enum class AttributeSource {
    Node,
@@ -37,8 +37,8 @@ enum class AttributeSource {
 * For more details about the transformation, refer to
 * [CreateAttribute](@ref openvino_docs_OV_UG_lpt_CreateAttribute) page in the Inference Engine Developer Guide.
 */
-template <typename AttributeType, typename OperationType = ngraph::pattern::op::Label>
-class ngraph::pass::low_precision::CreateAttribute : public ngraph::pass::low_precision::BaseMatcherPass {
+template <typename AttributeType, typename OperationType = ov::pass::pattern::op::Label>
+class ov::pass::low_precision::CreateAttribute : public ov::pass::low_precision::BaseMatcherPass {
 public:
    CreateAttribute(const AttributeParameters& params = AttributeParameters(), const AttributeSource source = AttributeSource::Node) : BaseMatcherPass(params) {
        assert((source == AttributeSource::Node) || (source == AttributeSource::OutputPort));
@@ -46,7 +46,7 @@ public:
            pattern::any_input() :
            pattern::wrap_type<OperationType>();

-        ngraph::graph_rewrite_callback callback = [&](pattern::Matcher& m) {
+        ov::graph_rewrite_callback callback = [&](pattern::Matcher& m) {
            auto op = m.get_match_root();
            if (transformation_callback(op)) {
                return false;
@@ -61,7 +61,7 @@ public:
            return true;
        };

-        auto matcher = std::make_shared<ngraph::pattern::Matcher>(operation, "CreateAttribute");
+        auto matcher = std::make_shared<ov::pass::pattern::Matcher>(operation, "CreateAttribute");
        this->register_matcher(matcher, callback);
    }
 };
--- a/src/common/low_precision_transformations/include/low_precision/create_precisions_dependent_attribute.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/create_precisions_dependent_attribute.hpp
@@ -7,17 +7,17 @@
 #include <memory>
 #include <vector>

-#include <ngraph/node.hpp>
-#include <ngraph/pattern/op/wrap_type.hpp>
+#include "openvino/core/node.hpp"
+#include "openvino/pass/pattern/op/wrap_type.hpp"

-#include <low_precision/lpt_visibility.hpp>
-#include <ngraph/pass/graph_rewrite.hpp>
-#include <ngraph/opsets/opset1.hpp>
+#include "low_precision/lpt_visibility.hpp"
+#include "openvino/pass/graph_rewrite.hpp"
+#include "openvino/opsets/opset1.hpp"
 #include "rt_info/precision_preserved_attribute.hpp"
 #include "network_helper.hpp"
 #include "lpt_itt.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -26,7 +26,7 @@ class CreatePrecisionsDependentAttribute;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 /**
 * @ingroup ie_transformation_common_api
@@ -38,12 +38,12 @@ class CreatePrecisionsDependentAttribute;
 * in the Inference Engine Developer Guide.
 */
 template <typename AttributeType, typename OperationType>
-class ngraph::pass::low_precision::CreatePrecisionsDependentAttribute : public ov::pass::MatcherPass {
+class ov::pass::low_precision::CreatePrecisionsDependentAttribute : public ov::pass::MatcherPass {
 public:
    CreatePrecisionsDependentAttribute() {
        auto operation = pattern::wrap_type<OperationType>();

-        ngraph::graph_rewrite_callback callback = [&](pattern::Matcher& m) {
+        ov::graph_rewrite_callback callback = [&](pattern::Matcher& m) {
            auto node = m.get_match_root();
            if (transformation_callback(node)) {
                return false;
@@ -65,7 +65,7 @@ public:
                rt[AttributeType::get_type_info_static()] = attribute;

                // Step #3: assign the same shared value to enable PrecisionPreservedAttribute update during AttributeType propagation
-                ngraph::pass::low_precision::NetworkHelper::reassign<AttributeType>(
+                ov::pass::low_precision::NetworkHelper::reassign<AttributeType>(
                    targetSharedValue,
                    {
                        attribute.attribute,
@@ -75,7 +75,7 @@ public:
            return true;
        };

-        auto matcher = std::make_shared<ngraph::pattern::Matcher>(operation, "CreatePrecisionsDependentAttribute");
+        auto matcher = std::make_shared<ov::pass::pattern::Matcher>(operation, "CreatePrecisionsDependentAttribute");
        this->register_matcher(matcher, callback);
    }
 };
--- a/src/common/low_precision_transformations/include/low_precision/depth_to_space.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/depth_to_space.hpp
@@ -6,7 +6,7 @@

 #include "transparent_base_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -27,4 +27,4 @@ public:

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/eliminate_fake_quantize.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/eliminate_fake_quantize.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,11 +24,11 @@ class LP_TRANSFORMATIONS_API EliminateFakeQuantizeTransformation : public LayerT
 public:
    OPENVINO_RTTI("EliminateFakeQuantizeTransformation", "0");
    EliminateFakeQuantizeTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/eltwise_base_transformation.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/eltwise_base_transformation.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/ngraph.hpp>
+
 #include "layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -33,4 +33,4 @@ protected:

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/fake_quantize.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/fake_quantize.hpp
@@ -7,7 +7,7 @@
 #include <memory>
 #include "layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -37,4 +37,4 @@ public:

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/fake_quantize_decomposition.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/fake_quantize_decomposition.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/ngraph.hpp>
+
 #include "layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -25,10 +25,10 @@ class LP_TRANSFORMATIONS_API FakeQuantizeDecompositionTransformation : public La
 public:
    OPENVINO_RTTI("FakeQuantizeDecompositionTransformation", "0");
    FakeQuantizeDecompositionTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/fold_convert.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/fold_convert.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,11 +24,11 @@ class LP_TRANSFORMATIONS_API FoldConvertTransformation : public LayerTransformat
 public:
    OPENVINO_RTTI("FoldConvertTransformation", "0");
    FoldConvertTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/fold_fake_quantize.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/fold_fake_quantize.hpp
@@ -4,10 +4,10 @@

 #pragma once

-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -23,12 +23,12 @@ class LP_TRANSFORMATIONS_API FoldFakeQuantizeTransformation : public LayerTransf
 public:
    OPENVINO_RTTI("FoldFakeQuantizeTransformation", "0");
    FoldFakeQuantizeTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
-    bool isConstantOutput(std::shared_ptr<ngraph::Node> op) const;
+    bool isConstantOutput(std::shared_ptr<ov::Node> op) const;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/fuse_convert.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/fuse_convert.hpp
@@ -4,11 +4,11 @@

 #pragma once

-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/layer_transformation.hpp"
 #include "low_precision/eltwise_base_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,11 +24,11 @@ class LP_TRANSFORMATIONS_API FuseConvertTransformation : public LayerTransformat
 public:
    OPENVINO_RTTI("FuseConvertTransformation", "0");
    FuseConvertTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/fuse_multiply_to_fake_quantize.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/fuse_multiply_to_fake_quantize.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,11 +24,11 @@ class LP_TRANSFORMATIONS_API FuseMultiplyToFakeQuantizeTransformation : public L
 public:
    OPENVINO_RTTI("FuseMultiplyToFakeQuantizeTransformation", "0");
    FuseMultiplyToFakeQuantizeTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/fuse_subtract_to_fake_quantize.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/fuse_subtract_to_fake_quantize.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/ngraph.hpp>
+
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -24,11 +24,11 @@ class LP_TRANSFORMATIONS_API FuseSubtractToFakeQuantizeTransformation : public L
 public:
    OPENVINO_RTTI("FuseSubtractToFakeQuantizeTransformation", "0");
    FuseSubtractToFakeQuantizeTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/gather.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/gather.hpp
@@ -7,7 +7,7 @@
 #include <algorithm>
 #include "low_precision/layer_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -22,4 +22,4 @@ public:

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/group_convolution.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/group_convolution.hpp
@@ -4,10 +4,10 @@

 #pragma once

-#include <ngraph/ngraph.hpp>
+
 #include "convolution.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -23,16 +23,16 @@ class LP_TRANSFORMATIONS_API GroupConvolutionTransformation : public Convolution
 public:
    OPENVINO_RTTI("GroupConvolutionTransformation", "0");
    GroupConvolutionTransformation(const Params& params = Params());
-    bool transform(TransformationContext& context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext& context, ov::pass::pattern::Matcher &m) override;
    bool isQuantized(const std::shared_ptr<const Node>& layer,
-        const std::vector<ngraph::element::Type>& defaultPrecisions) const override;
+        const std::vector<ov::element::Type>& defaultPrecisions) const override;
    static bool isQuantizedStatic(const std::shared_ptr<const Node>& layer,
-        const std::vector<ngraph::element::Type>& defaultPrecisions);
+        const std::vector<ov::element::Type>& defaultPrecisions);

 protected:
-    size_t getInputChannels(const std::shared_ptr<ngraph::Node> conv) const override;
+    size_t getInputChannels(const std::shared_ptr<ov::Node> conv) const override;
 };

 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/interpolate.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/interpolate.hpp
@@ -6,7 +6,7 @@

 #include "transparent_base_transformation.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -22,11 +22,11 @@ class LP_TRANSFORMATIONS_API InterpolateTransformation : public LayerTransformat
 public:
    OPENVINO_RTTI("InterpolateTransformation", "0");
    InterpolateTransformation(const Params& params = Params());
-    bool transform(TransformationContext &context, ngraph::pattern::Matcher &m) override;
+    bool transform(TransformationContext &context, ov::pass::pattern::Matcher &m) override;
    bool isPrecisionPreserved(std::shared_ptr<Node> layer) const noexcept override;
    bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const override;
 };

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/layer_transformation.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/layer_transformation.hpp
@@ -34,17 +34,17 @@
 // #define LPT_PRINT_DEQUANTIZATION_INFO
 // #define LPT_DISPLAY_PRECISION

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {
 namespace precision_set {
    const std::vector<element::Type> int8_support  = {
-            ngraph::element::u8,  ngraph::element::i8
+            ov::element::u8,  ov::element::i8
    };
    const std::vector<element::Type> int8_int16_int32_support = {
-            ngraph::element::u8,  ngraph::element::i8,
-            ngraph::element::u16, ngraph::element::i16,
-            ngraph::element::u32, ngraph::element::i32
+            ov::element::u8,  ov::element::i8,
+            ov::element::u16, ov::element::i16,
+            ov::element::u32, ov::element::i32
    };
 }
 enum levels : size_t {
@@ -151,9 +151,9 @@ public:
            case element::f32:
                return std::numeric_limits<float>::lowest();
            default:
-                NGRAPH_CHECK(false, "unexpected precision ", precision);
+                OPENVINO_ASSERT(false, "unexpected precision ", precision);
        }
-        NGRAPH_CHECK(false, "unexpected levels ", levels, " for precision ", precision);
+        OPENVINO_ASSERT(false, "unexpected levels ", levels, " for precision ", precision);
    }

    static float getMaxValue(const element::Type precision, const size_t levels) {
@@ -189,7 +189,7 @@ public:
            case element::f32:
                return std::numeric_limits<float>::max();
            default:
-                NGRAPH_CHECK(false, "unexpected precision ", precision);
+                OPENVINO_ASSERT(false, "unexpected precision ", precision);
        }
    }

@@ -258,8 +258,8 @@ public:
        Params(
            const bool updatePrecisions = true,
            element::Type deqPrecision = element::f32,
-            const std::vector<ngraph::element::Type> defaultPrecisions =
-            { ngraph::element::u8,  ngraph::element::i8 },
+            const std::vector<ov::element::Type> defaultPrecisions =
+            { ov::element::u8,  ov::element::i8 },
            const bool reshapeIgnorePerTensorQuantizationCheck = false) :
            updatePrecisions(updatePrecisions),
            deqPrecision(deqPrecision),
@@ -276,14 +276,14 @@ public:
            return *this;
        }

-        Params& setDefaultPrecisions(const std::vector<ngraph::element::Type>& defaultPrecisions) {
+        Params& setDefaultPrecisions(const std::vector<ov::element::Type>& defaultPrecisions) {
            this->defaultPrecisions = defaultPrecisions;
            return *this;
        }

        bool updatePrecisions;
        element::Type deqPrecision;
-        std::vector<ngraph::element::Type> defaultPrecisions;
+        std::vector<ov::element::Type> defaultPrecisions;
        // to support GPU workarround to keep Reshape and MatMul in FP32
        bool reshapeIgnorePerTensorQuantizationCheck;
    };
@@ -308,11 +308,11 @@ public:

    void setUpdatePrecisions(const bool updatePrecisions);

-    void setDefaultPrecisions(const std::vector<ngraph::element::Type>& defaultPrecisions);
+    void setDefaultPrecisions(const std::vector<ov::element::Type>& defaultPrecisions);

    virtual bool canBeTransformed(const TransformationContext& context, std::shared_ptr<Node> layer) const;
    static bool canBeTransformedStatic(const std::shared_ptr<Node>& layer,
-        const std::vector<ngraph::element::Type>& defaultPrecisions = precision_set::int8_support);
+        const std::vector<ov::element::Type>& defaultPrecisions = precision_set::int8_support);

    bool canSubtractBeHandled(const std::shared_ptr<Node>& op, const FakeQuantizeDequantization& dequantization) const;

@@ -326,13 +326,13 @@ public:
    static PrecisionDetails getPrecisionDetails(const QuantizationDetails& quantizationDetails);

    static bool isAsymmetricQuantization(const std::shared_ptr<const Node>& node,
-        const std::vector<ngraph::element::Type>& defaultPrecisions = precision_set::int8_support);
+        const std::vector<ov::element::Type>& defaultPrecisions = precision_set::int8_support);

    // return true if operation can be quantized and false otherwise
    // for example: if convolution operation weights are not quantized, then isQuantize returns false and true otherwise
    // note: dequantization operations on activations are absent during method execution
    virtual bool isQuantized(const std::shared_ptr<const Node>& layer,
-        const std::vector<ngraph::element::Type>& defaultPrecisions) const;
+        const std::vector<ov::element::Type>& defaultPrecisions) const;

    // return true if operation can be preserved for precision
    // note: dequantization operations on activations are absent during method execution
@@ -355,35 +355,35 @@ protected:

    bool updatePrecisions;
    element::Type deqPrecision;
-    std::vector<ngraph::element::Type> defaultPrecisions;
+    std::vector<ov::element::Type> defaultPrecisions;
    bool reshapeIgnorePerTensorQuantizationCheck;

    static constexpr char originalLayerPostfix[] = "_original";
    TransformationContext* context;

 protected:
-    std::shared_ptr<ngraph::Node> moveDequantizationAfter(
+    std::shared_ptr<ov::Node> moveDequantizationAfter(
        TransformationContext &context,
-        const std::shared_ptr<ngraph::Node>& operation,
+        const std::shared_ptr<ov::Node>& operation,
        const FakeQuantizeDequantization& dequantization,
        const bool updatePrecision,
        const bool moveSubtract = true) const;

-    std::shared_ptr<ngraph::Node> moveDequantizationBefore(
+    std::shared_ptr<ov::Node> moveDequantizationBefore(
        TransformationContext& context,
-        const std::shared_ptr<ngraph::Node>& operation,
+        const std::shared_ptr<ov::Node>& operation,
        const FakeQuantizeDequantization& dequantization,
        const bool updatePrecision,
        const bool moveSubtract = true) const;

    void updateOutput(
        TransformationContext &context,
-        std::shared_ptr<ngraph::Node> lastNode,
-        std::shared_ptr<ngraph::Node> originalNode) const;
+        std::shared_ptr<ov::Node> lastNode,
+        std::shared_ptr<ov::Node> originalNode) const;

    void updateOutput(
        TransformationContext& context,
-        std::shared_ptr<ngraph::Node> lastNode,
+        std::shared_ptr<ov::Node> lastNode,
        std::string originalName) const;

    void addPattern(ov::pass::GraphRewrite& pass, TransformationContext& context, std::shared_ptr<Node> patternRoot);
@@ -393,7 +393,7 @@ protected:

    template <typename Operation>
    void addSingleNodePattern(ov::pass::GraphRewrite& pass, TransformationContext& context) const {
-        using namespace ngraph;
+        using namespace ov;

        auto is_op_type = [](std::shared_ptr<Node> n) {
            return !!as_type_ptr<Operation>(n);
@@ -408,4 +408,4 @@ typedef std::shared_ptr<LayerTransformation> LayerTransformationPtr;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/low_precision.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/low_precision.hpp
@@ -7,27 +7,27 @@
 #include <vector>
 #include <memory>

-// one place to include all Low Precision Transformations from ngraph::pass::low_precision
-#include <low_precision/rt_info/intervals_alignment_attribute.hpp>
-#include <low_precision/rt_info/quantization_alignment_attribute.hpp>
-#include <low_precision/rt_info/precisions_attribute.hpp>
-#include <low_precision/rt_info/precision_preserved_attribute.hpp>
+// one place to include all Low Precision Transformations from ov::pass::low_precision
+#include "low_precision/rt_info/intervals_alignment_attribute.hpp"
+#include "low_precision/rt_info/quantization_alignment_attribute.hpp"
+#include "low_precision/rt_info/precisions_attribute.hpp"
+#include "low_precision/rt_info/precision_preserved_attribute.hpp"

-#include <low_precision/markup_precisions.hpp>
-#include <low_precision/markup_avg_pool_precision_preserved.hpp>
-#include <low_precision/propagate_precisions.hpp>
-#include <low_precision/align_quantization_intervals.hpp>
+#include "low_precision/markup_precisions.hpp"
+#include "low_precision/markup_avg_pool_precision_preserved.hpp"
+#include "low_precision/propagate_precisions.hpp"
+#include "low_precision/align_quantization_intervals.hpp"


-#include <low_precision/lpt_visibility.hpp>
-#include <low_precision/common/quantization_granularity_restriction.hpp>
-#include <low_precision/common/precisions_restriction.hpp>
+#include "low_precision/lpt_visibility.hpp"
+#include "low_precision/common/quantization_granularity_restriction.hpp"
+#include "low_precision/common/precisions_restriction.hpp"
 #include "low_precision/layer_transformation.hpp"
 #include "low_precision/markup_precisions.hpp"
 #include "openvino/pass/graph_rewrite.hpp"
 #include "openvino/pass/pass.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -37,9 +37,9 @@ class LP_TRANSFORMATIONS_API LowPrecision;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

-class ngraph::pass::low_precision::MarkupOptimizations : public ov::pass::ModelPass {
+class ov::pass::low_precision::MarkupOptimizations : public ov::pass::ModelPass {
 public:
    OPENVINO_RTTI("MarkupOptimizations", "0");
    MarkupOptimizations(
@@ -53,23 +53,23 @@ private:
    const AttributeParameters& params;
 };

-class ngraph::pass::low_precision::TypeRelaxedReplacer : public ov::pass::GraphRewrite {
+class ov::pass::low_precision::TypeRelaxedReplacer : public ov::pass::GraphRewrite {
 public:
    OPENVINO_RTTI("TypeRelaxedReplacer", "0");
    TypeRelaxedReplacer();
 };

-class ngraph::pass::low_precision::LowPrecision : public ov::pass::ModelPass {
+class ov::pass::low_precision::LowPrecision : public ov::pass::ModelPass {
 public:
    OPENVINO_RTTI("LowPrecision", "0");
    LowPrecision(
        const std::vector<PrecisionsRestriction>& precisionRestrictions = {},
        const std::vector<QuantizationGranularityRestriction>& quantizationRestrictions = {},
        const LayerTransformation::Params = LayerTransformation::Params());
-    bool run_on_model(const std::shared_ptr<ngraph::Function>& m) override;
+    bool run_on_model(const std::shared_ptr<ov::Model>& m) override;

-    static bool isFunctionQuantized(const std::shared_ptr<const ngraph::Function>& function);
-    static bool isFQLevelsPresent(const std::shared_ptr<const ngraph::Function>& function, const std::set<size_t>& levels);
+    static bool isFunctionQuantized(const std::shared_ptr<const ov::Model>& model);
+    static bool isFQLevelsPresent(const std::shared_ptr<const ov::Model>& model, const std::set<size_t>& levels);

 protected:
    std::vector<PrecisionsRestriction> precisionRestrictions;
--- a/src/common/low_precision_transformations/include/low_precision/lpt_itt.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/lpt_itt.hpp
@@ -10,9 +10,9 @@
 #pragma once


-#include <openvino/itt.hpp>
+#include "openvino/itt.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {
 namespace itt {
@@ -25,4 +25,4 @@ OV_ITT_DOMAIN(LPT_LT);
 } // namespace itt
 } // namespace low_precision
 } // namespace pass
-} // namespace ngraph
+} // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/markup_avg_pool_precision_preserved.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/markup_avg_pool_precision_preserved.hpp
@@ -5,11 +5,11 @@
 #pragma once

 #include <memory>
-#include <low_precision/lpt_visibility.hpp>
+#include "low_precision/lpt_visibility.hpp"
 #include "low_precision/layer_transformation.hpp"
 #include "openvino/pass/pass.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -17,7 +17,7 @@ class LP_TRANSFORMATIONS_API MarkupAvgPoolPrecisionPreserved;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 /**
 * @ingroup ie_transformation_common_api
@@ -27,11 +27,11 @@ class LP_TRANSFORMATIONS_API MarkupAvgPoolPrecisionPreserved;
 * [MarkupAvgPoolPrecisionPreserved](@ref openvino_docs_OV_UG_lpt_MarkupAvgPoolPrecisionPreserved) page
 * in the Inference Engine Developer Guide.
 */
-class ngraph::pass::low_precision::MarkupAvgPoolPrecisionPreserved : public ov::pass::ModelPass {
+class ov::pass::low_precision::MarkupAvgPoolPrecisionPreserved : public ov::pass::ModelPass {
 public:
    OPENVINO_RTTI("MarkupAvgPoolPrecisionPreserved", "0");
-    MarkupAvgPoolPrecisionPreserved(const std::vector<ov::element::Type> defaultPrecisions = ngraph::pass::low_precision::precision_set::int8_support);
+    MarkupAvgPoolPrecisionPreserved(const std::vector<ov::element::Type> defaultPrecisions = ov::pass::low_precision::precision_set::int8_support);
    bool run_on_model(const std::shared_ptr<ov::Model>& m) override;
 private:
-    const std::vector<ngraph::element::Type> defaultPrecisions;
+    const std::vector<ov::element::Type> defaultPrecisions;
 };
--- a/src/common/low_precision_transformations/include/low_precision/markup_bias.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/markup_bias.hpp
@@ -4,12 +4,12 @@

 #pragma once

-#include <low_precision/lpt_visibility.hpp>
+#include "low_precision/lpt_visibility.hpp"
 #include <memory>
-#include <openvino/pass/graph_rewrite.hpp>
-#include <openvino/pass/pattern/matcher.hpp>
+#include "openvino/pass/graph_rewrite.hpp"
+#include "openvino/pass/pattern/matcher.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -29,4 +29,4 @@ public:

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov
--- a/src/common/low_precision_transformations/include/low_precision/markup_can_be_quantized.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/markup_can_be_quantized.hpp
@@ -5,10 +5,10 @@
 #pragma once

 #include <memory>
-#include <ngraph/pass/pass.hpp>
+#include "openvino/pass/pass.hpp"
 #include "low_precision/lpt_visibility.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -16,7 +16,7 @@ class LP_TRANSFORMATIONS_API MarkupCanBeQuantized;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 /**
 * @ingroup ie_transformation_common_api
@@ -28,11 +28,11 @@ class LP_TRANSFORMATIONS_API MarkupCanBeQuantized;
 * [MarkupCanBeQuantized](@ref openvino_docs_OV_UG_lpt_MarkupCanBeQuantized) page
 * in the Inference Engine Developer Guide.
 */
-class ngraph::pass::low_precision::MarkupCanBeQuantized : public ov::pass::ModelPass {
+class ov::pass::low_precision::MarkupCanBeQuantized : public ov::pass::ModelPass {
 public:
    OPENVINO_RTTI("MarkupCanBeQuantized", "0");
-    MarkupCanBeQuantized(const std::vector<ngraph::element::Type> defaultPrecisions = { ngraph::element::u8, ngraph::element::i8 });
-    bool run_on_model(const std::shared_ptr<ngraph::Function>& m) override;
+    MarkupCanBeQuantized(const std::vector<ov::element::Type> defaultPrecisions = { ov::element::u8, ov::element::i8 });
+    bool run_on_model(const std::shared_ptr<ov::Model>& m) override;
 private:
-    const std::vector<ngraph::element::Type> defaultPrecisions;
+    const std::vector<ov::element::Type> defaultPrecisions;
 };
--- a/src/common/low_precision_transformations/include/low_precision/markup_precisions.hpp
+++ b/src/common/low_precision_transformations/include/low_precision/markup_precisions.hpp
@@ -12,7 +12,7 @@
 #include "low_precision/common/precisions_restriction.hpp"
 #include "openvino/pass/pass.hpp"

-namespace ngraph {
+namespace ov {
 namespace pass {
 namespace low_precision {

@@ -20,7 +20,7 @@ class LP_TRANSFORMATIONS_API MarkupPrecisions;

 }  // namespace low_precision
 }  // namespace pass
-}  // namespace ngraph
+}  // namespace ov

 // Transformation is used to add customization options runtime
 /**
@@ -34,7 +34,7 @@ class LP_TRANSFORMATIONS_API MarkupPrecisions;
 * [MarkupPrecisions](@ref openvino_docs_OV_UG_lpt_MarkupPrecisions) page
 * in the Inference Engine Developer Guide.
 */
-class ngraph::pass::low_precision::MarkupPrecisions : public ov::pass::ModelPass {
+class ov::pass::low_precision::MarkupPrecisions : public ov::pass::ModelPass {
 public:
    class Restriction {
    public:
@@ -67,12 +67,12 @@ public:

    OPENVINO_RTTI("MarkupPrecisions", "0");
    explicit MarkupPrecisions(const std::vector<PrecisionsRestriction>& restrictions = {},
-        const std::vector<ngraph::element::Type>& defaultPrecisions = { ngraph::element::u8, ngraph::element::i8 });
+        const std::vector<ov::element::Type>& defaultPrecisions = { ov::element::u8, ov::element::i8 });
    bool run_on_model(const std::shared_ptr<ov::Model>& m) override;

 private:
    static bool isPrecisionPreserved(const std::shared_ptr<Node>& node);
    static bool isSupported(const std::shared_ptr<Node>& node);
    std::unordered_map<std::string, Restriction> restrictionsByOperation;
-    std::vector<ngraph::element::Type> defaultPrecisions;
+    std::vector<ov::element::Type> defaultPrecisions;
 };
--- a/Show More
+++ b/Show More