Karol Blaszczak
32e0e859b2
[DOCS] update prereleasenotes ( #18946 )
2023-08-03 13:11:45 +02:00
Przemyslaw Wysocki
211c27d0b7
Add MO to PYTHONPATH in lin-debian Azure job ( #18959 )
...
* Add MO
* Update .ci/azure/linux_debian.yml
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
* Add MO reqs
* Fix deps
---------
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
2023-08-03 14:36:03 +04:00
Anastasia Kuporosova
3adb6d4cd2
[DOCS] Update PYTHONPATH in docs ( #18961 )
2023-08-03 11:46:34 +02:00
Yuan Hu
d445f9ec95
[CPU] Added unit tests for custom shape infer ( #17162 )
2023-08-03 12:41:27 +04:00
Ilya Churaev
e64f84d88e
Remove legacy API from op/util ( #18951 )
2023-08-03 08:18:04 +00:00
Oleg Pipikin
fb45deb65e
Refactor engines utils ( #18856 )
...
* Refactor engines utils
* Apply comments
* Apply comments 2
2023-08-03 12:13:05 +04:00
Anastasia Kuporosova
83d7b9d372
[PyOV] unskip test_ops_matmul ( #18934 )
2023-08-03 12:06:07 +04:00
HARI CHAND BALASUBRAMANIAM
c38638ee43
Update pre_release_feedback.yml ( #18957 )
...
Remove the check-box and amend the description
2023-08-03 12:03:04 +04:00
Nesterov Alexander
040951bfa1
[ARM CPU] Skip autobatch tests on arm32 arch ( #18937 )
2023-08-03 11:30:38 +04:00
Ilya Churaev
aa4cbf36e5
Extend loading frontend error message ( #18950 )
2023-08-03 07:19:18 +00:00
Andrew Kwangwoong Park
1501e29cfe
[GPU] Allow StridedSlice as predecessor for in place concat ( #18836 )
...
* Allow StridedSlice as predecessor for in place concat
* Enable padding support for strided slice
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add prepare_buffer_fusing TC for ov_gpu_unit_tests
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
2023-08-03 05:50:26 +00:00
Aleksandr Voron
8846b5ddd0
[CPU] Disabled MLAS FC impl on ARM ( #18947 )
...
Fixes regression introduced in PR18879
2023-08-03 08:59:31 +04:00
Taylor Yeonbok Lee
31e46ea255
[GPU] Skip reorder at runtime if data type and format are not changed ( #18859 )
...
* Skip reorder at runtime if data type and format are not changedt
* Update shape of reorder user at predecessor node so that we can allocate pred nodes' output to host mem if needed
* Reinterpret reorder memory at runtime if needed
(e.g., input is fake-aligned fc and reorder uses that memory)
* Add debug config
* Fix CI test failure
* Do not skip after optimized reshape
* Do not skip user reorder if the user reorder is output and current node is static, and the memory is allocated to device
* Disable skip reorder user if current node has fused node
* Update src/plugins/intel_gpu/src/graph/include/reorder_inst.h
Co-authored-by: Eddy Kim <eddy.kim@intel.com>
* Minor fix for compilation error
* Do not skip reorder if the reorder's user is optimizable concat
* Fix CI failures
* No need to wait for input_layout because the events is already resolved in dgpu
* Fixed corner case where only some of the multiple output layouts are static
---------
Co-authored-by: Eddy Kim <eddy.kim@intel.com>
2023-08-02 20:59:52 -07:00
Nesterov Alexander
f3bafef128
[ARM CPU] Add ACL deconvolution operation ( #18655 )
2023-08-02 21:02:01 +00:00
Wilson Seok
d51fc7adad
add num_classes=-1 support in cpu_impl of detection_output ( #18924 )
2023-08-02 11:37:19 -07:00
Eddy Kim
9e9cf72973
updated to reset variable memory when shape is changed ( #18941 )
2023-08-02 11:24:58 -07:00
Eddy Kim
1fd598c303
onednn-gpu update to fix caching issue ( #18935 )
2023-08-02 11:14:30 -07:00
Alexandra Sidorova
5b82c6f08d
[Snippets][CPU] Enabled MHA tokenization for quant and bf16 cases ( #18403 )
2023-08-02 21:16:27 +04:00
Roman Kazantsev
b44f915a9d
[TF FE] Support ShapeN operation ( #18913 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-08-02 15:28:39 +02:00
Aleksandr Voron
7b4a7e5eb4
[CPU][ARM] MLAS Transpose executor ( #18879 )
2023-08-02 12:48:09 +00:00
Przemyslaw Wysocki
62fa09a181
[PyOV] Add torchvision to OpenVINO preprocessing converter ( #17934 )
...
* Some progress
* refactoring
* Refactor tests, run black
* Refactor, flake
* Minor change
* Add support for num_output_channels
* WIP
* Add dependency
* Almost done
* Fix flake
* Add MO convert
* Minor changes
* Add interpolation mode tests
* Add requirements for preprocessing
* Fix linter
* Update tests
* Fix type error
* Introduce typing
* Rename module
* Code review
* Update src/bindings/python/src/openvino/preprocess/torchvision/torchvision_preprocessing.py
Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
* Update src/bindings/python/src/openvino/preprocess/torchvision/preprocess_converter.py
Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
* CR changes
* Fix mypy
* Minor change
* Minor change
* Fix flake
* typing change
* Update types
* Add tools to pythonpath
* Add MO reqs
* Minor change
* Fix PT FE issue
* bugfix
* Use absolute path
* Debug
* Debug req path
* Change MO to OVC
* Enable PT FE building
* Debug
* Skip some tests on ARM
* ADd ticket numbers
* Some progress
* refactoring
* Refactor tests, run black
* Refactor, flake
* Minor change
* Add support for num_output_channels
* WIP
* Add dependency
* Almost done
* Fix flake
* Add MO convert
* Minor changes
* Add interpolation mode tests
* Add requirements for preprocessing
* Fix linter
* Update tests
* Fix type error
* Introduce typing
* Rename module
* Code review
* Update src/bindings/python/src/openvino/preprocess/torchvision/torchvision_preprocessing.py
Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
* Update src/bindings/python/src/openvino/preprocess/torchvision/preprocess_converter.py
Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
* CR changes
* Fix mypy
* Minor change
* Minor change
* Fix flake
* typing change
* Update types
* Add tools to pythonpath
* Add MO reqs
* Minor change
* Fix PT FE issue
* bugfix
* Use absolute path
* Debug
* Debug req path
* Change MO to OVC
* Enable PT FE building
* Debug
* Skip some tests on ARM
* ADd ticket numbers
* Update test val
* Change pytest version
* Modify GH workflow
* Update cmake
* Update cmake
* fix cmake
* Skip tests on ARM
* Fix after OVC MO changes
* Limit torch requirements
* Raise allowed diff in test
* Debug - remove new bindings
* Debug - remove interpolation modes
* Debug - change test
* Cleanup
* Minor change
* Disable on ARM and Py<38
* Update ARM marker
* limit torchvision for ARM
---------
Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
Co-authored-by: gklodkox <gracjanx.klodkowski@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2023-08-02 16:44:30 +04:00
Ilya Lavrenov
7be660e551
Fixed CPU build ( #18805 )
2023-08-02 16:28:00 +04:00
Ilya Churaev
af8e41bcea
Removed legacy headers from pass implementations ( #18921 )
...
* Removed legacy headers from pass implementations
* Fixed build
* Remove std and ov usings
2023-08-02 12:01:52 +00:00
Wanglei Shen
0cad2f1324
[CPU] Move streams calculation before transformation pipeline ( #18911 )
2023-08-02 11:38:34 +00:00
Ilya Lavrenov
2b12780588
Use prebuilt TBB on macos arm64 ( #18923 )
2023-08-02 14:34:59 +04:00
Przemyslaw Wysocki
7e5877fdaf
[PyOV] Restore ONNX requirement for Python tests ( #18904 )
2023-08-02 12:24:44 +02:00
Ilya Churaev
0475c7270e
Change linker flags to fix ngraph_obj build in Debug mode ( #18922 )
2023-08-02 13:51:01 +04:00
HARI CHAND BALASUBRAMANIAM
9d27b34ce6
Update bug.yml ( #18919 )
...
* Update bug.yml
removed some unnecessary wording #start here
* Update bug.yml
* Update bug.yml
* Update bug.yml
2023-08-02 13:38:05 +04:00
Anastasiia Pnevskaia
0769af959e
"static_shape" parameter fix. ( #18843 )
...
* Fixed static_shape param.
* Removed wrong change.
* Fixed unit test.
* Corrected mistakes in tests, switched on smart_reshape.
* Removed not used method.
* Corrected test.
2023-08-02 13:03:38 +04:00
HARI CHAND BALASUBRAMANIAM
099aaf5228
Create feature_request.yml ( #18839 )
...
Adding template for Feature Request
2023-08-02 12:31:48 +04:00
Pawel Raasz
1f08d3520c
Review multiclass nms class for shape inference aspects ( #18908 )
...
* Review NMS shape inference
* Fix test issues
* Review MatrixNms shape inference
* Unregister NMS with dynamic output from CPU plugin
* Review MulticlassNms for shape inference
2023-08-02 08:01:06 +00:00
Wang Kai
a2039e8410
Fixing a typo in core/shape_inference ( #18912 )
2023-08-02 11:43:15 +04:00
HARI CHAND BALASUBRAMANIAM
b774561b98
Create pre_release_feedback.yml ( #18840 )
...
* Create pre_release_feedback.yml
Adding pre-release feedback template submission
* Update pre_release_feedback.yml
2023-08-02 11:41:43 +04:00
Anastasia Kuporosova
6dd88d76d3
[PyOV] try to run add_extension_test ( #18900 )
...
* [PyOV] try to run add_extension_test
* rename flag
* try to run extension test on linux
* run on linux
2023-08-02 11:14:03 +04:00
Fang Xu
902a953b06
update sha256 of oneTBB2021.2.1 on mac arm64 ( #18907 )
2023-08-02 11:13:30 +04:00
Ekaterina Aidova
968edc9375
[PT FE]: support aten::broadcast_to ( #18899 )
2023-08-02 08:38:34 +04:00
Wilson Seok
86b8e0a930
[GPU] Add autopad option in CreateOp of groupconvolution ( #18897 )
...
* add autopad option in CreateOp of groupnormalization
* add autopad option in CreateOp of GroupConvolution
2023-08-01 20:41:05 -07:00
HARI CHAND BALASUBRAMANIAM
b0b6a38ecc
Delete bug.md ( #18918 )
...
Since we already have bug.yml, we can delete this template.
2023-08-02 07:35:24 +04:00
Taylor Yeonbok Lee
db8c29ee6f
[GPU] Release unused internal memory from pool ( #18917 )
...
* * Not to reuse internal memory for dynamic shape because of the current inefficiency in the pool
* Added a new debug config for dump runtime memory pool
* Apply DisableMemoryReuse for all usages
* Resolved perf issue of memory reuse from pool : Previously original ibuf record was not released when we allocate new memory for that buf.
After releasing the memory, # of the memory pool record does not increase => no longer inefficient memory pool retireval.
* Added test
2023-08-01 20:25:05 -07:00
Ilya Churaev
0e13b99a3d
Remove ngraph headers from some core source files ( #18894 )
...
* Remove ngraph headers from some core source files
* Suppress some warnings
* Suppress more warnings
* Try to fix some compilation issues
* Suppress more warnings
* Supress clone_model
* Suppress warnings for Windows
* Suppress more warnings for Windows
* Suppress more warnings for Windows
* Additional suppress
* More Windows warnings
* Additional warning
* Suppress more warnings
* Suppress warning from python API
2023-08-02 07:22:17 +04:00
mei, yang
8619d6d749
Enable paddle dino ( #18111 )
...
* Enable paddle op reduce_all, share_data; Support bool type for paddle op elementwise_mul
* Support bool/int16 for fill_any_like
2023-08-02 09:24:28 +08:00
Andrey Kashchikhin
b6a32694a5
unskip tests in GHA ( #18906 )
2023-08-02 00:42:37 +04:00
Ilya Churaev
996f10394c
Extend error messages from proxy plugin ( #18902 )
2023-08-01 17:47:57 +00:00
Pawel Raasz
9067a1fead
Review NMS, MatrixNms shape inference ( #18869 )
...
* Review NMS shape inference
* Fix test issues
* Review MatrixNms shape inference
* Unregister NMS with dynamic output from CPU plugin
2023-08-01 19:44:55 +04:00
Mikhail Ryzhov
3dc96738e1
[GNA] Fixed absent node_id crash ( #18874 )
2023-08-01 13:33:57 +00:00
Maxim Vafin
361367393b
[MO] Raise exception for older nncf models ( #18890 )
...
* [PT FE] Call strip() for older nncf models
* Raise excception on older nncf models
* Update legacy mo too
2023-08-01 13:00:12 +00:00
Chen Xu
74a608592a
[CPU] Fix Reduce node bug regarding fusing with low precision ( #18835 )
2023-08-01 11:56:36 +00:00
Jan Iwaszkiewicz
7fd6563827
[PyOV] Add Range-4 as part of opset12 ( #18884 )
2023-08-01 11:51:35 +00:00
Chenhu Wang
0608ece0ae
[CPU] MVN kernel: fixed tails processing on SSE ( #18893 )
2023-08-01 09:29:18 +00:00
Sebastian Golebiewski
c2052b0424
[DOCS] Compile CPU plugin for ARM platforms. ( #18764 )
...
* Update build_raspbian.md
* update-instructions
* remove-cross-compilation
* Update build_raspbian.md
2023-08-01 11:10:04 +02:00
