Pawel Raasz
38a5ee719d
Remove unused lambda capture ( #17160 )
2023-04-25 00:39:40 +00:00
Egor Duplenskii
8879ef53a7
[CPU] Fix data race in concurrent compile_model calls ( #17164 )
2023-04-25 00:01:03 +00:00
Anastasiia Pnevskaia
00847cba7d
Fix of tf.GenericFunction conversion in convert_model() ( #17125 )
...
* Added GenericFunction support, fixed tf.Function test.
* Added test, added TF version checks.
* Small correction
* Removed Trackable type support.
* Small correction.
2023-04-24 22:57:56 +00:00
Taylor Yeonbok Lee
ce23ce00f1
[GPU] Fixed fused_primitive_desc to have -1 value for dep_start_idx ( #17099 )
...
* Fixed fused_primitive_desc to have -1 value for dep_start_idxt b
* Fixed dgpu i8 errors
2023-04-24 22:21:58 +00:00
Roman Kazantsev
3830125e3b
[TF FE] Report the full list of unsupported operations ( #17143 )
2023-04-24 21:33:07 +00:00
Eddy Kim
d972a71b4c
[GPU] Fixed the prepare_quantization pass to support grouped_weights_shape ( #17093 )
...
* fixed to support grouped_weights_shape
* added grouped_weights unit tests
2023-04-24 14:21:50 -07:00
Piotr Krzemiński
22a81e0e58
[PT FE] Enable stable tests for sort & argsort ( #16415 )
...
* [PT FE] Enable stable tests for sort & argsort
* Update test_argsort.py
* [PT FE] Update to opset11
* [PT FE] Remove redundant argument from argsort test
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2023-04-25 01:21:16 +04:00
Maksim Kutakov
9fce01f8cc
[CPU] Remove legacy dynamic batch processing from the plugin ( #17052 )
...
* Intermediate state
* Remove old dyn batch path in the new api
* Remove legacy dyn batch support
* Remove dyn batch support field from the config
* Revert changes to the common part
* Revert accidental change in the test file
* Minor fixes
* Fix support for dyn batch without setting current
* Typo fix
2023-04-25 01:18:10 +04:00
Evgenya Stepyreva
758ec32001
CVS-108963 Coverity fixes ( #17161 )
2023-04-25 01:03:56 +04:00
yanlan song
64b5a4595a
Bell/use cpu for dynamic models ( #17149 )
...
* clean up multi code path
Signed-off-by: fishbell <bell.song@intel.com>
* clang
Signed-off-by: fishbell <bell.song@intel.com>
* potential locking issue
Signed-off-by: fishbell <bell.song@intel.com>
* remove unecessary variable
Signed-off-by: fishbell <bell.song@intel.com>
* clear redundunt return syntax
Signed-off-by: fishbell <bell.song@intel.com>
* still use cpu for dynamic models
Signed-off-by: fishbell <bell.song@intel.com>
* merge master
Signed-off-by: fishbell <bell.song@intel.com>
---------
Signed-off-by: fishbell <bell.song@intel.com>
2023-04-25 01:01:11 +04:00
Jade Cho
5c21dcec4d
[GPU] Fix detection output kernel build error on dGPU ( #17150 )
...
+ Check local memory size used in the kernel and choose proper kernel.
+ Select DO_STAGE_0_CAFFE instead of DO_STAGE_0_CAFFE_OPT
2023-04-25 01:00:26 +04:00
Vladislav Golubev
a6b1544acf
Review comments applied ( #17168 )
2023-04-25 00:59:03 +04:00
Mateusz Mikolajczyk
8e5b0650a0
[PT FE] Fix for prim::Constant optional or containing list of tensors ( #16754 )
...
* Fix Constant list of tensor
* Write TorchScript transformation
* Handle Optional Tensor Constants
* Improve tests
* Add comments
* Try fix flake
2023-04-24 22:56:42 +02:00
Evgenya Stepyreva
b452dab8f0
TypeRelaxed<>::clone_with_new_inputs thread safety fix ( #16881 )
...
* TypeRelaxed<>::clone_with_new_inputs thread safety fix
* Style
* Make TypeRelaxed<BaseOp>::clone_with_new_inputs copy node the same way as copy ctor of ov::Node
* Removed mutex field from intel_cpu::GraphContext
* Removed all about has_type_relaxed_ops field from the snippets subgraph
* Clonning test
2023-04-25 00:51:18 +04:00
Ilya Lavrenov
83cc2277b4
Fixed compilation with sanitizer ( #17175 )
2023-04-25 00:44:16 +04:00
Alina Kladieva
f39ab0dbc9
Upper-bound for patchelf ( #17177 )
2023-04-24 19:52:55 +02:00
Wanglei Shen
10c56708fd
update auto architecture document in GitHub for 2023.0 release ( #17141 )
...
* update auto architecture doc
* update auto architecture doc
* Apply suggestions from code review
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
* update for comments
---------
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2023-04-24 15:44:34 +00:00
Tomasz Adamowicz
86ed1e93b6
[Gna] [coverity]fixes ( #17122 )
...
* [Coverity] Fix: CID 1502468 - Not restoring ostream format
* [Coverity] Fix: CID 1502524 - Dereference null return value
* [Coverity] Fix: CID 1509007 - Uncaught exception
* [Coverity] Fix: CID 1505779, 1505781, 1505783 and 1505786 - Dereference null return value
* [Coverity] Fix: CID 1502503 - Using invalid iterator
* Revert "[Coverity] Fix: CID 1502524 - Dereference null return value"
This reverts commit b605a493ae
2023-04-24 14:04:30 +01:00
Maksim Kutakov
f8522a6ea1
[CPU] Rnn weights repacking ( #16992 )
2023-04-24 15:48:57 +04:00
Vladislav Golubev
f410658d32
[LPT] AddTransformation fix ( #17076 )
...
* [LPT] AddTransformation: constants on 0's input support
* AddTransformation: new test instances
* codestyle
2023-04-24 12:15:01 +01:00
Edward Shogulin
a3f14366d9
[LPT] Extending EliminateFakeQuantize transformation (two interval boundaries) ( #17140 )
...
* [LPT] EliminateFakeQuantize extending
* tests
* folding quick fix
2023-04-24 11:58:00 +01:00
Ilya Lavrenov
a34ef680f2
Made plugins.hpp generation to be CONFIG dependent ( #17139 )
2023-04-24 14:48:45 +04:00
Vladimir Paramuzov
faba5fb71e
[Transformations] Add threshold for const comparison in Gelu fusion pass to fuse with fp16 precision ( #17042 )
2023-04-24 14:37:31 +04:00
Vladimir Paramuzov
e8ae1e41ea
[GPU] Skip FC fake alignment for some vector by matrix multiplications ( #17051 )
2023-04-24 14:34:50 +04:00
dependabot[bot]
eac265722f
Update networkx requirement from <=2.8.8 to <=3.1 in /tools/pot ( #16745 )
...
Updates the requirements on [networkx](https://github.com/networkx/networkx ) to permit the latest version.
- [Release notes](https://github.com/networkx/networkx/releases )
- [Commits](https://github.com/networkx/networkx/compare/networkx-0.23...networkx-3.1 )
---
updated-dependencies:
- dependency-name: networkx
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-04-24 13:37:35 +04:00
hyunback kim
63f5c2f0e7
[GPU] Fix levit-128s accuracy issue ( #17136 )
...
* [GPU] Fix levit-128s accuracy issue
Wrong batch dims for fused eltwise of gemm.
-> The issue is getting incorrect batch size of fused eltwise used by gemm.
Its rank is different from src tensor. Eltwise tensor rank was reduced by mistake.
It is only reproduce in batch 1 and full tensor.
The batch size in here means all of non spatial dims, but previous implementation was default batch dim role.
Signed-off-by: hyunback <hyunback.kim@intel.com>
2023-04-24 18:16:00 +09:00
Pavel Esir
6ff0cad127
Fix mixed precision inference for quantized IRs ( #16785 )
...
* disable mixed precision inference for quantized IRs
* typo fix
* improved solution, disable mixed precision in quantized IRs selectively only for float nodes
* minor typos correction
* added unit-tests
* renamed rt_info
* updated list of nodes for which FQ is propagated; updated unit-tests
* fix failing build
2023-04-24 13:13:04 +04:00
Maxim Vafin
01065338ef
Fix MO IR Reader extender for StridedSlice to support empty begin and end masks ( #17019 )
2023-04-24 13:08:28 +04:00
Tatiana Savina
aa5b6ecac2
DOCS shift to rst - Opset S ( #17158 )
...
* ops to rst
* fix errors
* formula fix
* change code
* console directive
* vsplit try hoghlight
* fix code snippets
* comment fixes
* fix list
2023-04-24 11:02:30 +02:00
Tatiana Savina
b3ea6ceefa
DOCS shift to rst - Opset R ( #17159 )
...
* ops to rst
* sphinx transition
* try html tag
* try comment
* try code directive
* try code directive
* try highlight
* try concole directive
* try line directive
* add highlight for code
* another directive
* introduce consoke directive
* add code format
2023-04-24 11:02:09 +02:00
Fang Xu
656d7fe380
prebuilt oneTBB binaries for ARM64 ( #16904 )
...
* use oneTBB for arm64
* force THREADING=TBB
* test: remove TBB_DIR for linux arm64
* update linux and mac arm64 packages
* update SHA256
* add comment
* disable add_rpath for tbb libraries on mac arm64
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
2023-04-24 09:48:47 +04:00
Daniil Lyakhov
7997354359
POT is depricated ( #16758 )
2023-04-24 09:37:57 +04:00
Vladimir Paramuzov
219a0eebdc
[GPU] Fix 1d onednn convolutions ( #17038 )
2023-04-24 09:24:56 +04:00
Min, Byungil
bb0be3c177
[GPU] Resolve failed onednn tests ( #16990 )
...
* [GPU] Resolve failed unit-tests on dGPU
+ Modified unit-tests of asymetric conv with per channel(WA for oneDNN issue)
+ Modified conv unit-tests with padded input or output
+ For testing oneDNN conv, it needs to query oneDNN about format. Applied this to conv tests.
+ Modified accuracy checking logic in unit-tests which have different format on dGPU.
+ reorder from fsv16 to bfyx should not be optimized out if not aligned by 16
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2023-04-24 14:11:35 +09:00
Ilya Lavrenov
11c3623ebb
Fixed compilation errors on Linux arm64 ( #17138 )
2023-04-23 21:34:37 +04:00
yanlan song
fed06fcb91
resubmit PR#17006 ( #17137 )
...
* clean up multi code path
Signed-off-by: fishbell <bell.song@intel.com>
* clang
Signed-off-by: fishbell <bell.song@intel.com>
* potential locking issue
Signed-off-by: fishbell <bell.song@intel.com>
* remove unecessary variable
Signed-off-by: fishbell <bell.song@intel.com>
* clear redundunt return syntax
Signed-off-by: fishbell <bell.song@intel.com>
* WR build issue on buntu 2004
Signed-off-by: fishbell <bell.song@intel.com>
---------
Signed-off-by: fishbell <bell.song@intel.com>
2023-04-23 11:56:07 +00:00
Gorokhov Dmitriy
2c450ced24
[CPU] Fixed JIT Reorder impl on Apple targets ( #17134 )
2023-04-23 01:09:03 +04:00
Ilya Lavrenov
26029c2d48
Enabled runtime model tests ( #17131 )
2023-04-22 11:07:36 +04:00
Ilya Lavrenov
462cdb54f8
Enabled convolution_backprop_quantize_type CPU tests on non-x64 ( #17123 )
2023-04-22 01:45:14 +04:00
Ilya Lavrenov
46f8ebfaec
Revert "Fix C API unite test case error ( #17012 )" ( #17128 )
...
This reverts commit 63c0089128
2023-04-22 01:44:34 +04:00
Ilya Lavrenov
fbc28297ec
Enabled C-API tests on ARM platform ( #17119 )
...
* Enabled C-API tests on ARM platform
* Fixed ARM CPU plugin test on streams
2023-04-21 22:55:18 +04:00
Ilya Lavrenov
d7b775f583
Updated onednn submodule ( #17126 )
2023-04-21 20:47:37 +04:00
Aleksandr Voron
e31b00c299
[CPU] Enable Python test test_infer_request.test_infer_mixed_values with bool for ARM ( #17111 )
...
* Update test_infer_request.py
* enable all py tests
2023-04-21 19:52:32 +04:00
Anastasiia Pnevskaia
50a6c88ea3
Fix of crashes of convert_model() when executed for different frameworks ( #16968 )
...
* Fix of class conflicts in different frameworks.
* Remove commented code.
* Moved FakeQuantWithMinMaxVars to common part.
* Fixed BOM package test.
* Removed not needed code.
* Removed not needed code.
2023-04-21 19:29:38 +04:00
Maksim Kutakov
793bbb6ee2
Remove dyn batch support from onednn i8 ref conv ( #17106 )
2023-04-21 17:44:00 +04:00
Jan Iwaszkiewicz
88cb428763
[PyOV][DOCS] Added Python advanced inference documentation ( #17090 )
...
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2023-04-21 15:22:33 +02:00
Maciej Smyk
c4b155edc2
DOCS shift to rst - Opsets C ( #17112 )
2023-04-21 13:30:07 +02:00
yanlan song
304991f88b
Revert "Clean up unused code ( #17006 )" ( #17110 )
...
This reverts commit 359b444558
2023-04-21 15:26:01 +04:00
Tomasz Dołbniak
6ea9cc7149
ONNX FE - model loading fix ( #17091 )
...
* Path retrieval fix
* More detailed messages in the failing test
* Exe path with model name
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2023-04-21 15:25:26 +04:00
Jade Cho
8fbd78fb07
[GPU] Fix a bug of fusing eltwise sum post-op. ( #17078 )
...
+ When input of eltwise is full-tensor constant layer, use binary add
instead of sum as post-op on oneDNN.
2023-04-21 20:17:35 +09:00
