Commit Graph

12888 Commits

Author SHA1 Message Date
Helena Kloosterman
10fc881fe5 Small fix for GPU memory allocation documentation (#20394) 2023-11-23 14:42:07 +01:00
Pawel Raasz
08ab7da931 [core]Migrate TopK operator to new API (#20254)
* Migrate TopK to new API

* Refactor compare_max for TopK

* Unify check of k for const and non-const input

* Update src/core/include/openvino/op/util/evaluate_helpers.hpp

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>

* Move `get_tensors_partial_shapes` to dev API

---------

Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
2023-11-23 14:42:07 +01:00
Katarzyna Mitrus
146b0c0be8 [Opset13][pyAPI] Python API Multinomial-13 (#20400)
* Init Multinomial op python API

* Add python tests for Multinomial op

* Update num_samples input description
2023-11-23 14:42:07 +01:00
Pawel Raasz
e8d80f9b0d [core]Shape and Node util functions size optimization (#20206)
* Refactor shape_size util to reduce bin size

* Make `check_new_args_count` non-template function

* Use as not template check_new_args_count
in multi-nominal
2023-11-23 14:42:06 +01:00
Andrei Gorbachev
387bfdebef [GPU] Refactor CTCGreedyDecoderSeqLen, CTCGreedyDecoder, CTCLoss (#20432)
* CTCGreedyDecoderSeqLen, CTCGreedyDecoder

* CTCLoss

---------

Co-authored-by: Pavel Durandin <pavel.durandin@intel.com>
2023-11-23 14:42:06 +01:00
Ilya Churaev
3c20ff09df Migrate subgraph tests till quantized subgraph (#20351)
* Migrate subgraph tests till quatized subgraph

* Fixed code style

* Fixed code style

* Try to fix build

* Remove run method

* Remove GNA test
2023-11-23 14:42:06 +01:00
Ilya Churaev
7985fa5106 Migrated all subgraph tests after quantization graphs (#20381)
* Migrated all subgraph tests after quantization graphs

* Fixed skip tests config

* Add alias for NPU

* Try to fix NPU

* Remove unsupported precisions

* Remove GNA test

* Remove more tests
2023-11-23 14:42:06 +01:00
Ivan Novoselov
41658a38c9 [CPU] Improve Commit slider's handling of non-decodable characters (#20149) 2023-11-23 14:42:05 +01:00
Nesterov Alexander
da2769ec30 [ARM CPU] Update TBB ACL Scheduler (#18885) 2023-11-23 14:42:05 +01:00
Wilson Seok
2f067337f1 [GPU] fix issue of optimized out reorder during event sync (#20223)
* fix confliction

* remove debug code

* fix unit test failure

* update condition of reorder check

* apply the condition for only opt out reorder user
2023-11-23 14:42:05 +01:00
Ilya Lavrenov
f617c2c38c Relocatable developer package (#20327)
* Merge Linux CC + static build + clang compiler

* Improvements

* Removed ie prefixes from cmake scripts

* Fixes for NPU

* Initial relocatable OpenVINO Developer package

* Improvements

* Try to fix

* improvements

* Export a lot of headers

* Removed NVIDIA pipeline; make it to be a job

* Fixes

* Fixes 2

* Try ilya-lavrenov repo

* Clean-up

* More imrpovements

* Even more improvements

* Override export, install

* Override export, install

* Disable pythonwheel generation for relocatable OV dev package

* Fixed issues with versions

* Fixed android build

* Fixed android build

* Fixed NPU build

* Update src/bindings/python/CMakeLists.txt
2023-11-23 14:42:05 +01:00
Oleg Pipikin
c9facab1ba Refactor CumSumLayerTest, DeformablePSROIPoolingLayerTest, DepthToSpaceLayerTest (#19870)
* Refactor CumSumLayerTest

* Refactor DeformablePSROIPoolingLayerTest

* Refactor DepthToSpaceLayerTest
2023-11-23 14:42:04 +01:00
Oleg Pipikin
a96a1f5f7c Refactor NonZeroLayerTest, NormalizeL2LayerTest, OneHotLayerTest, PadLayerTest (#20318)
* Refactor NonZeroLayerTest

* Refactor NormalizeL2LayerTest

* Refactor OneHotLayerTest

* Refactor PadLayerTest

* Apply comments
2023-11-23 14:42:04 +01:00
Irina Efode
8158e8ca5e [CONFORMANCE][TOOLS] Repeat pattern extractor API (#20293)
* Prepare API

* Refactor api

* Move model comparation to separate component

* Cover by tests

* Move align_in_info to utils

* Change arch diagram
2023-11-23 14:42:04 +01:00
Katarzyna Mitrus
4cffbe8b4d BitwiseElementwise ops init in MO (#20386) 2023-11-23 14:42:03 +01:00
Ilya Lavrenov
5010dcec56 Removed check for openvini::runtime::c in samples (#20425) 2023-11-23 14:42:03 +01:00
Oleg Pipikin
303ca313fd Disable f16 LSTMCellTest and LSTMSequenceTest for Apple arm64 (#20422) 2023-11-23 14:42:03 +01:00
Evgenya Nugmanova
5acf0e0175 Avoid dynamic rank in Snippets (#20387)
* Avoid dynamic rank in Snippets

* Update src/common/snippets/src/pass/collapse_subgraph.cpp

Co-authored-by: Alexandra Sidorova <alexa.sanechka@ya.ru>

---------

Co-authored-by: Alexandra Sidorova <alexa.sanechka@ya.ru>
2023-11-23 14:42:03 +01:00
Vladislav Golubev
b655811e97 [Snippets] Changed BrgemmCopyB shape inference (#19957) 2023-11-23 14:42:02 +01:00
Irina Efode
b6bee4a884 [CONFORMANCE][PRECOMMIT] Add one sporadically interapted test to expected failures (#20420) 2023-11-23 14:42:02 +01:00
Ilya Lavrenov
2231f35aa0 Disabled sporadic test_backend.py::OnnxBackendNodeModelTest::test_div_uint8_cpu test (#20419) 2023-11-23 14:42:02 +01:00
Pawel Raasz
27229201bb [core]Migrate Tile operator to new API (#20255)
* Migrate Tile to new API

* Remove visit_attributes as is same as base class
2023-11-23 14:42:02 +01:00
Tatiana Savina
8f15501b5f [DOCS] Pypi pages description change (#20352)
* pypi pages change

* add description

* change command order

* Update docs/install_guides/pypi-openvino-rt.md

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>

* change column name

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-11-23 14:42:01 +01:00
Ilya Lavrenov
3632414801 Removed macOS post-commit pipeline (#20415) 2023-11-23 14:42:01 +01:00
Maxim Vafin
f94d60a1f9 [PT FE] Fix pad default value (#20401) 2023-11-23 14:42:01 +01:00
Ilya Lavrenov
8e4b3e29c7 Don't add mxnet extras for openvino-dev on macOS arm64 (#20403) 2023-11-23 14:42:01 +01:00
Vladimir Paramuzov
b6ffc5c7b1 [TESTS] Fix random generator for custom signed types (#20393)
* [TESTS] Fix random generator for custom signed types

* Increase threashold for bf16 CPU tests
2023-11-23 14:42:00 +01:00
Sebastian Golebiewski
e45515f835 Update 247-code-language-id-with-output.rst (#20412) 2023-11-23 14:42:00 +01:00
Ilya Lavrenov
8e86d4d5d7 Disable OMP threading on macOS (#20405) 2023-11-23 14:42:00 +01:00
Alexander Kozlov
700c65f47b Added a of Gen AI landing page (#20253)
* Added a draft of Gen AI landing page

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>

* Applied comments

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Changed the placement of Gen AI doc

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>

* Added examples with Optimum-Intel

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Update docs/articles_en/openvino_workflow/gen_ai.md

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

---------

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Nico Galoppo <nico.galoppo@intel.com>
2023-11-23 14:42:00 +01:00
Andrei Gorbachev
34a3689b3b [GPU] Refactor AdaptivePooling, BatchNorm, BatchToSpace (#20357)
* adaptive_pooling

* batch_norm

* batch_to_space
2023-11-23 14:41:59 +01:00
Ilya Lavrenov
38cf9fb1f9 Revert "[CI] [GHA] Skip test_div_uint8_cpu on macOS only; unskip test_onnx/test_backend.py in GHA workflows (#20367)" (#20402)
This reverts commit a3d6d0bca9.
2023-11-23 14:41:59 +01:00
Tomasz Jankowski
4e4d29e42f [Template plugin] Unify headers inclusion (#20326)
* Use precise op version - Parameter

* Use precise op version - Constant

* Use precise op version - Result

* Use precise op version - Add, Concat, Subtract

* Use precise op version - NMS

* Use precise op version - TopK, Broadcast

* Use precise op version

* Include openvino headers in quotes

* Use precise op version - LSTMCell

* Fix code style
2023-11-23 14:41:59 +01:00
Ilya Lavrenov
a93167f925 Updated ade submodule (#20392) 2023-11-23 14:41:59 +01:00
Alexandra Sidorova
f4cdd6f84a [Snippets][CPU] Disabled MHA tokenization with infer precision f16 (#20308) 2023-11-23 14:41:58 +01:00
Ekaterina Aidova
c64c009a63 [PT FE]: support aten::erf and aten::adaptive_avg_pool1d (#20350)
* [PT FE]: support aten::erf and aten::adaptive_avg_pool1d

* align adaptive avg pools for different sizes

* refactor adaptive max pool
2023-11-23 14:41:58 +01:00
Przemyslaw Wysocki
fd21998ac7 Add torch lower bound (#20362) 2023-11-23 14:41:58 +01:00
Vladislav Golubev
65da8693b2 [CPU] Group & NF4 decompression transformation support (#20039) 2023-11-23 14:41:58 +01:00
Roman Kazantsev
3940f79b59 [TF FE] Support TF 2.14 and add OnesLike translator (#20385)
* [TF FE] Support TF 2.14 and add OnesLike translator

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

* Update tests constraints

* Update open_model_zoo

* Adopt TF Lite test to 2.14 TF

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

* Support TF Lite layer tests for diffrent TF versions

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-23 14:41:57 +01:00
Roman Lyamin
4b7e03085e [GPU] Fix high latency for LLMs on dGPU (#20328) 2023-11-23 14:41:57 +01:00
Andrey Kashchikhin
6fc3c3fd7d [CI] [GHA] Skip test_div_uint8_cpu on macOS only; unskip test_onnx/test_backend.py in GHA workflows (#20367)
* only skip test if mac

* unskip

* unskip trigger

* skip for onnx fe as well

* do not skip

* return skips and unskip test_backend in Python API 1.0

* rm pr trigger

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-11-23 14:41:57 +01:00
Pawel Raasz
edd607976f [core]Migrate Eye to new API (#20258)
* Migrate Eye to new API

* Fix `matrix_offset` initialization

* get_tensors_shapes -> get_tensors_partial_shapes
2023-11-23 14:41:57 +01:00
Maciej Smyk
bcfca0096b Update openvino_intro.md (#20383) 2023-11-23 14:41:56 +01:00
Jan Iwaszkiewicz
607a3ba43c [PyOV] Propagate errors on imports from runtime module (#20273)
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2023-11-23 14:41:56 +01:00
Ilya Churaev
c9a1ff6a1f Move cpu subgraph to new api (#20335)
* Move ConvEltwiseFuse to new API

* Move subgraph tests till LSTM to new API

* Fixed GPU initialization

* Remove unsupported GNA tests
2023-11-23 14:41:56 +01:00
Sergey Shlyapnikov
18bb1cd7f5 [GPU] Fix device tensors reallocation in case of host user's tensors (#20306) 2023-11-23 14:41:55 +01:00
Ilya Lavrenov
df0895f57e Removed np.int usage (#20378) 2023-11-23 14:41:55 +01:00
Ilya Churaev
e5ede0ff4f Reduce ngraph namespace usage from core component (#20309)
* Reduce ngraph namespace usage from core component

* Fixed build

* Fixed build 2

* Added missed opset to legacy API
2023-11-23 14:41:55 +01:00
Ilya Lavrenov
3ee23e0456 Use np.float32 instead of np.float (#20377) 2023-11-23 14:41:55 +01:00
Piotr Krzemiński
f34172735c [BUGFIX][Core][Template] Multinomial shape filling for 1D input (#20359)
* [BUGFIX] Fix incorrect shape filling for 1D tensor smaller than requested sample size

* [FIX] Remove redeclaration
2023-11-23 14:41:55 +01:00