Maxim Vafin
73d25a0f99
[PT FE] Add readme for pytorch frontend ( #20610 )
...
* Add readme for pytorch frontend
* Mension fx decoder
* Apply suggestions from code review
* Update src/frontends/pytorch/README.md
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* Update src/frontends/pytorch/README.md
* Update src/frontends/pytorch/README.md
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
---------
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
2023-10-20 14:23:13 +04:00
rsato10
9edbcb1d4d
[TF FE] Support ToBool operation ( #20511 )
...
* [TF FE][TF Hub] Support ToBool operations
* [TF FE][TF Hub] Support ToBool operations
* fixing select operation Support ToBool operations for TF Hub models
* added false and true const for tobool operations
* added reduction axes
* Apply suggestions from code review
* Update tests/layer_tests/tensorflow_tests/test_tf_ToBool.py
* Update tests/layer_tests/tensorflow_tests/test_tf_ToBool.py
* Update tests/layer_tests/tensorflow_tests/test_tf_ToBool.py
* Update src/frontends/tensorflow_common/src/op/tobool.cpp
* added second zero constant
* added correct types src\frontends\tensorflow_common\src\op\tobool.cpp
* added includes src\frontends\tensorflow_common\src\op\tobool.cpp
* Update src/frontends/tensorflow_common/src/op/tobool.cpp
* remove select and not_equal src/frontends/tensorflow_common/src/op/tobool.cpp
* Apply suggestions from code review
* Update src/frontends/tensorflow_common/src/op/tobool.cpp
* Apply suggestions from code review
* Update src/frontends/tensorflow_common/src/op/tobool.cpp
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-10-20 14:22:30 +04:00
Ilya Lavrenov
2b8827abd0
Updated urllib3 to resolve CVE ( #20620 )
2023-10-20 11:37:13 +04:00
Ilya Lavrenov
361b250fc4
WA issues with dynamic protobuf usage in Fes ( #20612 )
2023-10-20 10:44:42 +04:00
Siddhant Chauhan
ec2ae003aa
[TF FE][TF Hub] Support TruncateDiv operation ( #20615 )
...
* [TF FE][TF Hub] Support TruncateDiv operation
* [TF FE][TF Hub] Support TruncateDiv operation
* Update src/frontends/tensorflow_common/src/op/truncate_div.cpp
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-10-20 01:58:58 +04:00
Anastasiia Pnevskaia
cb8fac1576
Updated OMZ submodule. ( #20611 )
2023-10-20 01:15:24 +04:00
Siddhant Chauhan
070678fc19
[TF FE][TF Hub] Support TruncateMod operation ( #20468 )
...
* [TF FE][TF Hub] Support TruncateMod operation
* Update truncate_mod.cpp
* fix
2023-10-19 22:40:38 +04:00
Mustafa Cavus
3d5fe8d446
Llm and sd additional ops ( #20435 )
...
* TorchFX: New ops added (baddbbmm, leaky_relu_)
* TorchFX: Initial scaled_dot_product_flash_attention
* Code Formatting: scaled_fot_product_attention translation
* TorchFX unit test enabled for SDPA
* Typo fix in comment line
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
---------
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-10-19 21:21:28 +04:00
Mustafa Cavus
5018be82c3
TorchFX: Constant value pass without copy ( #20380 )
...
* TorchFX: Constant value pass optimization
* Replace op.Constant with make_constant in fx_decoder
* Using shared memory for constant value passing
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
---------
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
2023-10-19 19:35:10 +04:00
Andrey Kashchikhin
f6aa2ab7af
fix yml ( #20614 )
2023-10-19 19:17:16 +04:00
Andrey Kashchikhin
e4a83b9b77
[CI] [GHA] Extend Win CC pipeline with tests, make it static ( #20579 )
...
* start with transferring
* add CPU fun tests stage; complete CC stage
* start tests in comd
* uncomment
* fix step
* rm restore key
* align cmake
* add tbb path setting, continue on error
* add logs; add missing dir; add extension for ov cpu test bin
* add missing slash for path; explicitely set BUILD_TYPE
* correct paths for layer tests summary files; add tbb as target
* correct path to tbb
* rm triggers; add nightly trigger; rm debug conditions
* rm comment on cache
2023-10-19 18:05:55 +04:00
Sebastian Golebiewski
818c78d80a
[DOCS] Fix command for Building with Ninja ( #20605 )
...
* Fix command for Building with Ninja
Removing current directory from the command.
* Update docs/dev/build_windows.md
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-10-19 15:31:03 +04:00
Anastasiia Pnevskaia
be177021b0
Switching telemetry to opt-out and disabling telemetry in CI jobs ( #20391 )
...
* Added disabling telemetry script to linux azure job, added debug checks to convert_model.
* Telemetry disabling.
* Disabling telemetry.
* Config corrections.
* Config corrections.
* Update .github/workflows/mac.yml
Co-authored-by: Andrey Kashchikhin <andrey.kashchikhin@intel.com>
* Debug output.
* Win config correction.
* Win config correction.
* Debug output.
* Debug output.
* Added turning off telemetry to onnx azure tests config.
* Corrected config.
* Removed debug output.
* Switch telemetry to opt-out.
* Removed not needed blank lines.
* Text correction.
* Debug output.
* Remove changes from CI configs, add CI var to dockers.
* Config correction.
* Debug output.
* Config corrected.
* Readme corrected.
* Config changed.
* Config changed.
* Debug output.
* Required version changed.
* Remove debug output.
---------
Co-authored-by: Andrey Kashchikhin <andrey.kashchikhin@intel.com>
2023-10-19 15:26:21 +04:00
Ilya Lavrenov
1aebf6df5f
Add prefixes to proto files to avoid ODR conflicts ( #20588 )
2023-10-19 14:45:19 +04:00
Fang Xu
6bec4fc6df
build onetbb with hwloc2.9.3 ( #20481 )
2023-10-19 11:57:27 +04:00
Ilya Lavrenov
ad9a146f94
Enabled LC_RPATH for brew ( #20587 )
2023-10-19 11:44:38 +04:00
Irina Efode
137c8e896f
[OP CONFORMANCE] Fix op version operations in conformance report ( #20502 )
...
* [OP CONFORMANCE] Fix op version operations in conformance report
* Code style + SD test
2023-10-19 11:22:44 +04:00
Ilya Lavrenov
5fb6785f9e
Enabled FrontendLibCloseTest FE test suite ( #20592 )
2023-10-19 11:18:42 +04:00
Katarzyna Mitrus
dc9ec1ee9d
Fix MO multinomial shape array ( #20548 )
2023-10-19 04:53:38 +04:00
Sergey Lyalin
46935e0a00
Partial GPTQ int4 models conversion support + Swap nibbles in u4/i4 element type ( #20371 )
...
* Reference implementation for u4 constant compression from pytorch model based on bitwise ops pattern
* Fixed order of 4-bit halfs in byte
* Switched PyTorch FE to dev mode: in case if model cannot be fully converted, give partially converted model with PTFrameworkNode's with a printed warning (normally would raise an exception in case).
* Moved u4 compression to utils_quantize. Implemented not-interleaved version of u4 compression
* Removed debug output
* Added aten::matmul to the list of exceptions in may_produce_alias as a workaround for gptq models
* Added patching for gptq models applied automatically in convert_model
* WA for an inssue with u4 with earlier convert to fp16
* U4 blocked repacking for gptq patched model layout
* Deleted obsolete u4 re-packing based on aten::cat. Fixed the resulting u4 constant shape. Removed debug output.
* Revert "Switched PyTorch FE to dev mode: in case if model cannot be fully converted, give partially converted model with PTFrameworkNode's with a printed warning (normally would raise an exception in case)."
This reverts commit 0ef1455e70
2023-10-18 21:06:17 +04:00
Mikhail Ryzhov
cf9791e3e0
[GHA] Temporary disable win workflows ( #20568 )
...
* moved win workflow to nightly
* reset redundant files
* removed redundant files
2023-10-18 20:43:46 +04:00
Anastasia Kuporosova
491454103e
[Docs] fix failure of python snippet ( #20516 )
...
* [Docs] fix failure of python snippet
* trigger python snippets
* fix ga
* Update .github/workflows/linux.yml
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
* Update .github/workflows/linux.yml
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
* return back fix
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
2023-10-18 14:23:52 +00:00
Pawel Raasz
f2549f2d59
[core]Migrate VariadicSplit op to new API ( #20416 )
...
* Migrate VariadicSlice to new API
- refactor to reduce bin size
* Move `get_tensors_partial_shapes` to dev API
* Use get_tensors_partial_shapes in VariadicSplit
* Remove `visit_attributes` is same as base
2023-10-18 15:02:18 +02:00
Sergey Shlyapnikov
6c396fac9d
[GPU] Deferred events deallocation and tuning for FC bf_tiled kernel ( #20519 )
2023-10-18 16:28:27 +04:00
Sergey Shlyapnikov
6e97b91a77
[GPU] UsmHostTensor implementation ( #20518 )
...
Co-authored-by: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
2023-10-18 16:12:15 +04:00
Vladimir Paramuzov
90ad4c618d
[GPU] Grouped decompression scale/zp support ( #20491 )
2023-10-18 15:56:35 +04:00
Tatiana Savina
4574fb112c
change snippet name ( #20538 )
2023-10-18 13:27:10 +04:00
Zhang Yi
d82cd839ce
[PaddleFT]Simplify slice converter by opset8::slice ( #20508 )
2023-10-18 13:21:53 +04:00
Pawel Raasz
9fb40b0007
[core]Migrate LogicalNot to new API ( #20438 )
...
* Migrate LogicalNot to new API
* Rename file not.hpp -> logical_not.hpp
* Apply code style
2023-10-18 09:16:12 +00:00
Pawel Raasz
2415f0c7cf
[core]Migrate BatchToSpace to new API ( #20450 )
...
* Migrate BatchToSpace to new API
* Remove not required suppression macro
2023-10-18 09:09:27 +00:00
Ekaterina Aidova
222fbb1aec
[PT FE]: support aten::fill_diagonal_, aten::fill ( #20395 )
...
* [PT FE]: support aten::fill_diagonal_, aten::fill
* remove xfail
* Update src/frontends/pytorch/src/op/full.cpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Update tests/model_hub_tests/torch_tests/test_hf_transformers.py
---------
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-10-18 10:58:54 +02:00
Nikolay Shchegolev
4eab5b4635
[CPU] RandomUniform-8 implementation. ( #20171 )
2023-10-18 12:50:46 +04:00
hyunback kim
5f336a6870
[GPU] Support o_is_yx_isv2 ( #20521 )
...
216-attention-center model in notebooks needs o_is_yx_isv2 with onednn3.3
Signed-off-by: hyunback <hyunback.kim@intel.com>
2023-10-18 07:54:09 +00:00
Sungeun Kim
30a038c776
[GPU] Gather needs to keep the original input/output rank ( #20042 )
...
* Gather needs to keep the original input/output rank
- because the parameters as indices, batch_dims and axis depend on the rank.
- add input_rank to gather primitive.
* don't query on set_preferred_formats pass
-when the force_implementations is set.
-when forcing_impl is not onednn.
2023-10-18 16:28:22 +09:00
Andrei Gorbachev
c8b64f6a95
[GPU] Refactor BroadcastLayer, Bucketize, Concat ( #20369 )
...
* BroadcastLayer
* Bucketize
* Concat
* fix incorrect fill_random_unique_sequence fo f16
* Update src/plugins/intel_gpu/tests/functional/shared_tests_instances/single_layer_tests/broadcast.cpp
Co-authored-by: Roman Lyamin <Roman.Lyamin@intel.com>
* fix after review
---------
Co-authored-by: Roman Lyamin <Roman.Lyamin@intel.com>
2023-10-18 10:02:18 +04:00
Siddhant Chauhan
a30e25c725
[TF FE][TF Hub] Support BatchMatMulV3 operation ( #20528 )
...
* [TF FE][TF Hub] Support BatchMatMulV3 operation
* Update src/frontends/tensorflow_common/src/op/matmul.cpp
* Update src/frontends/tensorflow_common/src/op/matmul.cpp
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-10-18 09:49:33 +04:00
Nesterov Alexander
3b2ad48d79
[ARM CPU] Common fixes for fp16 ( #20504 )
2023-10-18 07:04:39 +02:00
Wang, Yang
f723f90100
fixing the issue of importing property from openvino. ( #20531 )
2023-10-18 10:36:20 +08:00
Maxim Vafin
f3b61d77e3
[GHA] Filter timm scope for model hub tests ( #20525 )
...
* Filter timm scope
* Apply suggestions from code review
2023-10-17 23:01:50 +04:00
Pawel Raasz
7515b042e8
[core]Migrate squeeze operator to new API ( #20282 )
...
* Migrate Squeeze to new API
* Remove visit_attributes as same as base class
2023-10-17 19:17:49 +02:00
Katarzyna Mitrus
33a97740b2
[MO][Opset13] Multinomial-13 support in MO IR Reader ( #20446 )
...
* Add Multinomial-13 to MO
* Add Multinomial tests for MO IR reader
* Move convert_type check
* Imports clean up
* Update pacgage BOM file
* Avoid files collision in tests
2023-10-17 17:50:42 +02:00
Tatiana Savina
f78e206ecb
[DOCS] Update components in readme ( #20524 )
...
* update readme
* add space
* add space
2023-10-17 17:49:07 +02:00
Tatiana Savina
b270e36590
add AMX ( #20523 )
2023-10-17 17:48:20 +02:00
Oleg Pipikin
a5fb3823f6
Refactor EinsumLayerTest, EyeLayerTest ( #20288 )
...
* Refactor EinsumLayerTest
* Refator EyeLayerTest
* Apply comments
* Fix
---------
Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com>
2023-10-17 17:35:24 +02:00
Georgy Krivoruchko
1e7977332b
Fixed naming and comments in ReduceProd ( #20512 )
2023-10-17 17:30:22 +02:00
Vitaliy Urusovskij
8fff47caf9
ROIPooling, ROIAlign layer tests to API2.0 (#20086 )
...
* `ROIPoolingLayerTest` to API2.0
* `ROIAlignLayerTest` to API2.0
2023-10-17 14:35:19 +00:00
Aleksandr Voron
e87d147f4c
[CPU] [ARM] Enable Pooling SLT tests on ARM ( #18013 )
2023-10-17 18:09:44 +04:00
Katz Sasaki
404f4e29b7
fix typo of config check error message ( #20517 )
2023-10-17 17:26:37 +04:00
Oleg Pipikin
a1daedc2e1
Disable NormalizeL2 and NonZero f16 tests on MacOs Arm64 ( #20451 )
2023-10-17 14:43:55 +04:00
Tomasz Jankowski
e1a29ae96e
[core] Migrate MaxPool operator to new API ( #20424 )
...
* Use API 2.0 in MaxPool v1
* Use API 2.0 in MaxPool v8
* Fix type selection
* Fix type selection
* Avoid redundant local copies
2023-10-17 13:30:18 +04:00
