* Support auto broadcast in FakeQuantize op

* style fix

* add pdpd unit test to plaidml manifest

* Make axis for TopK dynamic

* set_input_is_relevant_to_shape

* Proper handling of output shape with dynamic top_k_axis

* fix ut

* remove unused line

* check is_constant

* add v0 version

* update provenance

* use set_argument

* fix clang

* Minor cleanup

* Add support for ONNX 1.5 version of TopK

* Add unit tests

* Style apply

* Exclude failing tests

* Exclude failing tests

* Add support for ONNX 1.6 TopK attribures: larges and sorted

* Support for ONNX 1.6 TopK

* If k_node is a Constant, recreate as constant with Shape{}

* Extend `interpret_as_scalar` function

* Extend `interpret_as_scalar` function

* Remove merge artifact

* Add doc string

* Exclude failing tests

* Exclude failing tests

* Refactor function

* Remove unnecessary template param

* Use get_k function in OpSet 10 TopK

* Style apply

* Remove merge artifact

* Add tests for `interpret_as_scalar`

* Revert "Add tests for `interpret_as_scalar`"

This reverts commit 8b85965acb39c75ff9e66b06ad8f64df16e1a9da.

* - Added support for v1 Broadcast op specification
- Added upgrade/downgrade conversions between v0 and v1

* Added unit test for pdpd broadcast

* Make numpy default autobroadcast type and some style fixes

* Added support in Dynamic wrapper for dyn elimination and copied over unit tests from DynBroadcast

* Addressed PR feedback

* Addressed PR feedback on documentation

* Added a callback registration to the event class so that frameworks can decide how to write the events. Note: This is FULLY backwards compatible i.e., no change in the API so - won't break existing users

* Fixed compilation error

* Attempting to fix broken Windows build

* Fixed a race condition in the test

* Attempt to fix windows build again

* Create a variant schema and allow nodes to have a rt info

* Use map for rt_info

* style

* Another variant

* variant

* style

* Macro didn't work in gcc

* Compiler issues

* Skip shape inference for fused ops in the presence of dynamic-shaped inputs

* Added unit test to check fused op construction with dynamic input shapes

* Update changelog

* Title casing requested for documentation landpage

* Note new minimum version of Clang is 6

* Unify test names for opset transformation passes

* Unify downgrade test names

* [ONNX] Added Expand op to ONNX importer.

* Added support only for static broadcating.

* Changed version of set from 8 to 1.

* Added test for expand op.

* [Py] Added operators GroupConvolution and RNNCell to Pythpn API

* [Py] Removed code unrealated to branch.

* [Py] Undo removed test.

* [Py] Added removed decorator.

* [Py] Code formatting.

* [Py] Added ops to documentation's list.

* [Py] Added skipped file.

* [Py] Code formatting.

* [Py] Code formatting.

* Revert "Merge branch 'master' into etusien/GroupConv_RNNCell"

This reverts commit a1848ea48916b293d5260869b2a52827bea21981, reversing
changes made to 6a60068abf8e5391bf875ee22573eb1aa388b047.

* [Py] Reverted changes.

* [Py] Changed imports' list

* [Py] Added missed imports.

* [Py] Added operators GroupConvolution and RNNCell to Pythpn API

* [Py] Removed code unrealated to branch.

* [Py] Undo removed test.

* [Py] Added removed decorator.

* [Py] Added ops to documentation's list.

* [Py] Added skipped file.

* [Py] Code formatting.

* [Py] Code formatting.

* [Py] Reverted changes.

* Revert "Revert "Merge branch 'master' into etusien/GroupConv_RNNCell""

This reverts commit 9c46ce5d289dadc4979e4712c79fff84bb538652.

* [Py] Reverted changes.

* [Py] Code formatting.

* [Py] Code formatting.

* [Py] Added PadType to Group Conv op.

* make axes dynamic

* add ut

* update softmax deserializer

* check axes to be constant

* remove duplicates

* Implemented downgrade pass

* Using Pad:v1 in onnx_importer

* Downgrade transformation doc fixed

* Added downgrade pass for reduce_prod

* Using ReduceProd:v1 in onnx_importer

* Added ReduceProd:1 downgrade support

* Clang styles applied

* Downgrade pass added for all backends

* Added downgrade pass for reduce_prod

* Using ReduceProd:v1 in onnx_importer

* Added ReduceProd:1 downgrade support

* Clang styles applied

* Apply suggestions from code review

Changed pad_opset_pass to opset_downgrade
Co-Authored-By: Tomasz Socha <tomasz.socha@intel.com>

* Fix names

* Apply suggestions from code review

Removed redundant include, renamed tests
Co-Authored-By: Tomasz Socha <tomasz.socha@intel.com>

* Changed order of passes

* Changed way of op casting

* Changed order of passes

* Changed downgrade pass order of CPU backend

* Changed downgrade pass order of CPU backend

* styles applied

* [SPEC] Fixed NormalizeL2 (#3695)

* Fixed NormalizeL2

* style applied

* Fixed axes rank checking

* removed redundant comma

* Set keep_dims by function argument

* Improved error message

* Fixed casting method

* fix styles

* styles applied

* Fixed normalize tests

* unit tests names refactor
Co-Authored-By: Michał Karzyński <postrational@users.noreply.github.com>

* Disable not supported PlaidML tests

* Added missing EOF

Bump MLIR version

* Change order of gemm operation

* Add Dot lit test

* style-apply

* Fix captures to avoid escapes on []

* Release notes 0.26.0-rc.3 and revise bridges overview

* Fix version module and add latest release notes; update some doc menus

* Let release notes be discoverable

* Documentation master index

* Documentation index pg

* Update ops for version

* Update illustration

* Remove old illustration

* Add note for 0-rc.4

* Add section on NGRAPH_PROFILE_PASS to backend API

* rc-0.5

* Final preview 0.26 release notes

* Note changes on Sum validation

* Fix link syntax that breaks on Sphinx 3.0

* Revert file that triggers unnecessary review

* Typo fix

* PR feedback

* Consistency on section title capitalizations

* Update link

* Section title consistency

* Implemented downgrade pass

* Using Pad:v1 in onnx_importer

* Downgrade transformation doc fixed

* Downgrade pass added for all backends

* Apply suggestions from code review

Changed pad_opset_pass to opset_downgrade
Co-Authored-By: Tomasz Socha <tomasz.socha@intel.com>

* Changed order of passes

* Changed downgrade pass order of CPU backend

* Added reverse:v1 downgrade

* Code review remakrs introduced

* Fixed problem with foward declaration

* Modify convert op to convert from bf16 to float and vice-versa

* Add a check

* Remove conversion routines and use the convert op for casting

* disable unit tests for plaidml

* add get_default_pipeline_depth to executable

* use get_preferred_pipeline_depth