* builds

* pass unit test

* cleanup

* -   check to verify if the data_slices shares the same weights

* add the serialized graph

* - explicitly fuse the data slices, so all the parameter partitioned by slices are in contigous memory location
- fixes all the failing test cases

* Fix inconsistent ifdefs that broke macos build
Add quant ops to op table
Define serialize/deserialize for Quant con, avg pool, max pool
Add empty cases to interpreter

* iGPU cases.

* Include quant ops

* Define ngpu emitters

* Use pre-built tbb on macos

* Review comments

* Only copy lib when changed

* IntelGPU backend: fix online build

* PR2323. Comments addressed

* Update external_cldnn.cmake

* Update CMakeLists.txt

Update CODEOWNERS

* Add error check for user setting CMAKE_BUILD_TYPE

* fix case where CMAKE_BUILD_TYPE is not set

* update hybrid unit test

* remove unused files

* add graphviz to test

* add ability to add attributes to graphviz nodes

* tweak colors

* more interesting graph

* update test model

* add memory management passes

* add Dump

* wip

* remove in-place code from memory layout

* Check if the pointer returned by malloc is nullptr.

* Use ngraph_error.

* Add more pointer checks.

* Replace malloc and free with ngraph_malloc and ngraph_free.

* Divert dynamic offset to reference

* update gpu manifest

* Avoid dynamic cast

* Add table with status of supported operators.

* Update comments for unimplemented operators.

* Update comment to tables.

* Update table with Jira tickets.

* Update supported_ops.md

* Fix typo.

* [ONNX] Enable softmax test

* Update onnx_import.in.cpp

* change __expf to exp for accuracy