IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
13,457 Commits 38 Branches 54 Tags
6ab5ef72d5208a9217e283f2a0227819016e1f88
Commit Graph
13457 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrey Kashchikhin 6ab5ef72d5 [CI] [GHA] Skip failing tests in the Windows workflow (#21349) 
* always run tests, enable pr trigger

* skip tests

* provide ticket numbers

* rm pr trigger; rm unused schedule trigger
 2023-11-30 15:50:01 +04:00
Anastasiia Pnevskaia b0b28e3853 Disable memory sharing for GPU. (#21370) 2023-11-30 11:05:25 +00:00
Tomasz Jankowski a9d2dd0b02 [core] Migrate ShuffleChannels operator to new API (#21340) 
* Drop legacy stuff

* Repalce HostTensor with ov::Tensor

* Remove redundant call

* Revert safer axis normalilzation
 2023-11-30 11:43:01 +01:00
River Li ec239b3d5f [Fixing]Fix some scan coverity issues (#21378) 
* Fix some scan coverity issues

* Fix an error
 2023-11-30 14:39:55 +04:00
Maksim Kutakov 405d97e4a5 [CPU] Add optimized memory management for SDPA KV cache (#21242) 2023-11-30 14:07:43 +04:00
Vitaliy Urusovskij 718b5a60bf Remove legacy API from tests/ov_helpers/ (#21254) 
* Remove legacy API from `tests/ov_helpers/`

* Build fix

* `ngraph::Function`->`ov::Model`

* ClangFormat

* Remove extra `#include <ngraph/ngraph.hpp>`

* Clean up headers

* `NGRAPH_CHECK` -> `OPENVINO_ASSERT`

* Refactor includes

* Fix precommit
 2023-11-30 12:40:52 +04:00
Evgenya Nugmanova 243898560f Reducing ShapeOf sub-graphs for Flatten-like Reshapes (#21365) 
* Extends SharedOpsOptimization with ScatterUpdate support

* Introduces Flatten operation symbolic optimization

* Code Style: tests

* Test fix

* Refactor
 2023-11-30 12:21:18 +04:00
Pawel Raasz 51b5bc5ec4 [core]Add IF_TYPE_OF to enable CC for IfTypeOf class (#21240) 
* Integrate `IfTypeOf` class with CC
- Add macro to warp class to add support for CC
- Update `ccheader.py` to created PP symbols for template parameter list
- Use new macro in Convert operator

* Correct symbols generation

* Update OV PP macros

* Wrap TestVisitor into namespace{}

* Removed not required macros, update comments

* Update element_visitor.hpp
 2023-11-30 11:28:45 +04:00
Pawel Raasz 8ee8f4e112 [core]Migrate Range operator to new API (#21259) 
* Migrate Range operator to new API
- remove legacy function an duplicated shape inference
- Minor change range reference implementation

* Move accessing tensors after validation
 2023-11-30 11:27:08 +04:00
Tomasz Jankowski eec370a88b [core] Migrate StridedSlice operator to new API (#21342) 
* Drop legacy stuff

* Repalce HostTensor with ov::Tensor
 2023-11-30 11:26:22 +04:00
Sofya Balandina fa1cc89cf3 [sibgraph_dumper] Fix sporadic cache volume growth (#21352) 2023-11-30 11:05:43 +04:00
Maxim Vafin 3cae6e7aea [PT FE] Fix timm model list according to newest version (#21376) 
* [PT FE] Fix timm model list according to newest version

* Remove xfail for hf model passed in latest nightly

* Fix code for loading vit_h model

* Restore torchvision
 2023-11-30 08:17:21 +04:00
Maxim Vafin 007b6fd82c [PT FE] Add support for GFPGAN model (#21371) 
* [PT FE] Add support for GFPGAN model

* Remove logs

* Fix codestyle

* Add support for aten::normal
 2023-11-29 23:05:46 +00:00
Roman Kazantsev cb5377fb1d [TF FE] Correct ArgMinMax translators and add tests (#21364) 
* [TF FE] Correct ArgMinMax translators and add tests

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Update tests/layer_tests/tensorflow_tests/test_tf_ArgMinMax.py

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-11-30 00:00:43 +04:00
Maxim Vafin b3a13af9ef [PT FE] Support aten::softplus (#21367) 
* [PT FE] Support aten::softplus

* Fix name
 2023-11-29 14:38:31 +00:00
jmacekx 54e61ac9f5 refactor docs build process (#21239) 2023-11-29 15:30:05 +04:00
Xuejun ZhaiandRiver Li a6ea22ad0e [CPU Plugin][Func Test] Upgrade Fuse related to API 2.0 (#21359) 
* [CPU Plugin][Func Test] Upgrade Fuse related to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Update src/plugins/intel_cpu/tests/functional/subgraph_tests/src/fuse_non0_output_port.cpp

Co-authored-by: River Li <river.li@intel.com>

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
Co-authored-by: River Li <river.li@intel.com>
 2023-11-29 10:43:10 +00:00
Ekaterina Aidova 2b14ea97fc [PT FE]: support aten:resolve_neg, aten::resolve_conj (#21362) 
* [PT FE]: support aten:resolve_neg, aten::resolve_conj

* Update src/frontends/pytorch/src/op_table.cpp
 2023-11-29 10:34:46 +00:00
Xuejun Zhai 97588dc118 Xuejun/concat related tests 2.0 (#21334) 
* [CPU Plugin][Func Test] Upgrade ConcatConstantInPlaceTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade ReLuConcatConvSumInPlaceTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade ConcatReorderInPlaceTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] fix enforce_bf16

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Update concat_conv_sum_inplace.cpp

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-29 10:31:11 +00:00
River Li 0ab0d42f2b [CPU Tests] migrate ConcatResizeConcatTest to be 2.0 (#21300) 
* [CPU Tests] migrate ConcatResizeConcatTest to be 2.0

* [CPU Tests] migate matmul test cases to be api 2.0

* Update

* Revert "[CPU Tests] migate matmul test cases to be api 2.0"

This reverts commit b5fe09b3fa.

* Remove Node type
 2023-11-29 10:23:21 +00:00
Maxim Vafin 258c72555c [PT FE] Support bool in aten::prod (#21351) 2023-11-29 11:07:21 +01:00
Sungeun Kim 07bcb8b6ed This case will check the layout of condition in these conditions. (#21335) 
- it re-allocated at primitive_inst::realloc_if_needed().
- it can be skip subgraph.
 2023-11-29 09:42:16 +00:00
Xuejun Zhai c1a28d0942 Upgrade CPU func tests to 2.o (#21344) 
* [CPU Plugin][Func Test] Upgrade ConvPoolActivTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade Conv3dReshapeTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade ConvsAndSums to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade FQScaleshiftWithConstantShiftTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade FullyConnectedStridedInputsOutputsTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade FuseScaleShiftAndFakeQuantizeTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade FuseSplitConcatPairToInterpolateTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] remove ngraph namespace

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] fix error

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-29 13:32:05 +04:00
Nesterov Alexander 1b43b3c566 [ARM CPU] Fix debug fails in acl tbb scheduler (#20842) 2023-11-29 13:06:44 +04:00
Ilya Lavrenov d553d4cd55 Fixed extensions loading on Windows (#21355) 2023-11-29 12:40:42 +04:00
Maksim Proshin 39ba1ed03f [DOCS] Update reference in quantization_w_accuracy_control.md (#21337) 
* Update quantization_w_accuracy_control.md

avoid 404

* Update quantization_w_accuracy_control.md
 2023-11-29 09:40:25 +01:00
Maxim Vafin f3fe6b3f00 [PT FE] Add EDSR models to GHA tests (#21350) 
* [PT FE] Add EDSR models to GHA tests

* Apply suggestions from code review
 2023-11-28 21:05:33 +00:00
Sofya Balandina 0aa466e094 [apiConformance] Update expected err message for inference_precision (#21156) 2023-11-28 19:56:11 +01:00
Ilya Lavrenov 28208c6c9a Fixed conan RISC-V build (#21280) 2023-11-28 19:02:43 +04:00
Nikolay Shchegolev c6d78def6e [CPU] Fixed NMS output memory redifinition logic (#21126) 
CPU graph always adds Result node for outputs which don't have consumers. If Conversion is inserted between such output and Result this Conversion became consumer and require defined memory.
 2023-11-28 13:58:33 +00:00
Edward Shogulin d3d3ee55ef [CPU] Skip 32 bit tests for i32 Bitwise (#21328) 2023-11-28 17:06:16 +04:00
Roman Kazantsev 7c590bf180 [Hub Tests] Apply Python code formatting (#21286) 
* Apply Python code formatting

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Apply Python code formatting

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-11-28 16:54:02 +04:00
Andrey Babushkin a7de95a8a4 Rename AKS runners' labels for consistency (#21282) 2023-11-28 12:13:28 +00:00
Roman Kazantsev 42245fc7c3 [OVC] Apply Python code formatting to OVC (#21339) 
* [OVC] Apply Python code formatting to OVC

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Recover init.py file

* Update tools/ovc/openvino/__init__.py

* Update tools/ovc/openvino/__init__.py

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-11-28 12:06:46 +00:00
Pawel Raasz 0905c763dd [core]Migrate ReadValue operator to new API (#21336) 
* Migrate ReadValue to new API

* Fix build errors
 2023-11-28 13:02:39 +01:00
Xuejun Zhai 409ed190de [CPU Plugin][Func Test] Upgrade FuseMulAddAndEwSimpleTest to API 2.0 (#21331) 
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-28 12:06:20 +01:00
Vladimir Paramuzov 7ab79be0f6 [GPU] Stateful LLMs initial support (#21235) 2023-11-28 14:59:54 +04:00
Pawel Raasz 76b1861f86 Remove old API leftovers in Reshape operator (#21298) 2023-11-28 10:47:45 +01:00
Maxim Vafin f90a4b9d31 Add transformation to fuse Concat sequence (#21310) 
* Add transformation to fuse Concat sequence

* Update src/common/transformations/src/transformations/common_optimizations/concat_fusion.cpp
 2023-11-28 13:34:27 +04:00
Pawel Raasz 685ac0d0a1 Migrate Reverse operator to new API (#21277) 2023-11-28 09:41:56 +01:00
Tomasz Jankowski 21201833ec [core] Migrate ScatterUpdate operator to new API (#21241) 
* Drop legacy stuff

* Repalce HostTensor with ov::Tensor

* Use dedicated function to obtain Tensor data
 2023-11-28 12:34:43 +04:00
Tomasz Jankowski cf58a83094 [core] Migrate ScatterElementsUpdate operator to new API (#21212) 
* Remove redundant code

* Repalce HostTensor with ov::Tensor for v12

* Repalce HostTensor with ov::Tensor for v3

* Add Tensors count assertion

* Rename

* Revert axis normalization

* Don't duplicate the code
 2023-11-28 12:32:30 +04:00
Katarzyna Mitrus 37bac6ebcd [Opset13][FP8][Spec] FakeConvert op specification (#21039) 
* FakeConvert spec init

* Add spec files to the opset docs

* Remove apply_scale attribute and update inputs description

* Experimental op notice

* Update short description

* Update detailed description.

* Add BF16 type to supported inputs

* Update  note about "Fake"

* Add more details

* Add formula of the operation
 2023-11-28 09:14:06 +01:00
Alexander Suslov be5c755c32 migrate to new convert API (#21323) 2023-11-28 11:36:25 +04:00
Ilya Lavrenov c241405c5e Update docs (#21326) 2023-11-28 11:26:09 +04:00
Xuejun Zhai 441427abc8 [CPU Plugin][Func Test] Upgrade ConvWithZeroPointFuseSubgraphTest to API 2.0 (#21330) 
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-28 10:52:09 +04:00
Pawel Raasz 164d101295 [core]Refactor leftovers after migration to new API (#21304) 
* Refactor leftovers after migration to new API

* Restore output tensors count check
 2023-11-28 10:48:12 +04:00
Wanglei Shen acecf31642 [CPU][ARM] Enable multi-stream execution (#21009) 2023-11-28 10:41:56 +04:00
Xuejun Zhai 9320fa7c86 [CPU Plugin][Func Test] Upgrade ConvConcatSubgraphTest to API 2.0 (#21301) 
* [CPU Plugin][Func Test] Upgrade ConvConcatSubgraphTest to API 2.0

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [CPU Plugin][Func Test] Upgrade ConvConcatSubgraphTest, remove ngraph namespace

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-11-28 10:39:29 +04:00
Pawel Raasz 53baeacc2e [core]Remove deprecated function from Loop (#21299) 
* Migrate leftovers in Loop operator to new API
- use new version of `get_constant_from_source`
- migrate `is_rank_compatible_any_of` to dev API
- Improve rank compatibility checks

* Use new version of `is_rank_compatible_any_of`
instead deprecated to reduce bin-size

* Remove deprecated `is_rank_compatible_any_of`
 2023-11-28 10:37:15 +04:00