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
Nesterov Alexander
6ad80576b7
[ARM CPU] Fix smoke_if tests ( #17095 )
...
* fix smoke if
* fix smoke if - arm32
* review fix
2023-04-21 14:45:22 +04:00
HARI CHAND BALASUBRAMANIAM
6b44902bf2
Update bug.md ( #16880 )
...
Update the OpenVINO GitHub issue submission template. To allow the submitter to provide more information when submitting an issue.
2023-04-21 02:27:39 -07:00
Sun Xiaoxia
b22d0641cb
fix streams is not correct by latency mode ( #17101 )
2023-04-21 09:21:14 +01:00
Yury Gaydaychuk
4ae7e1ff61
[CPU] Commit slider: safe file opening ( #16755 )
2023-04-21 11:42:42 +04:00
Vladislav Golubev
31efdfd00d
[Transformations] BroadcastTransition transformation ( #16861 )
2023-04-21 11:35:04 +04:00
Chen Xu
70d80a750f
[CPU] Reduce node asymmetrical precision optimization ( #16829 )
2023-04-21 11:00:16 +04:00
Mingyu Kim
ba23e2290e
[GPU] Choose onednn impl for reorder ( #17077 )
...
* [GPU] Choose onednn impl for reorder
* [GPU] Add unit test
2023-04-21 13:56:58 +09:00
yanlan song
359b444558
Clean up unused code ( #17006 )
...
* 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>
---------
Signed-off-by: fishbell <bell.song@intel.com>
2023-04-21 04:23:55 +00:00
Sun Xiaoxia
c186ffdf0d
Xiaoxia/stream process refactor ( #16692 )
...
* add _streams_info_table in Executor config
* change useHyperThreading init value
* restore cmake
* fix comments
* add calling enableCpuPinning property
* fix judgment about number of sockets in init_stream
* fix test case compile issue
* fix ci test case fail issue
* modify GetPerformanceStreams calling position
* add affinity in get_cpu_pinning
* modify ecore judgement
* add no binding core on ADL
* fix ci issue, add get_num_numa_nodes()
* fix code style
* fix StreamsHasHigherPriority issue
* fix according to comments
* merge master
* fix build issue
* fix template plugin test case failed issue
* fix build issue
* fix cpu test failed
* Update plugin.cpp
---------
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
2023-04-21 01:38:32 +00:00
hyunback kim
344db564fc
[GPU] Fix dump graph failure issue in levit-128s model. ( #17055 )
...
* [GPU] Fix dump_graph failure issue in levit-128s model.
1. to_string() in strided_slice always access begin/end/stride param id from dependencies
regardless of max dependencies.
2. Add an exception in dump_full_node(). It helps below.
- Avoid a dump failure. Usually, graph dump are used during debugging,
which reduces unnecessary debugging time due to graph dump failure.
- You can immediately see which node has failed, making it easy to find it.
Signed-off-by: hyunback <hyunback.kim@intel.com>
2023-04-21 09:14:47 +09:00
Wanglei Shen
14d4fcf827
enable smoke_SetConfigAffinity for ARM ( #17092 )
2023-04-20 20:25:35 +01:00
Anastasia Kuporosova
a8b5ccc03f
[PyOV] Check for glibc version in python test ( #17081 )
...
* [PyOV] Check for glibc version in python test
* fix for no glibc
2023-04-20 19:28:55 +04:00
Karol Blaszczak
0c12ee6015
[DOCS] fix for copyright and trademark glyphs ( #17021 )
2023-04-20 14:11:16 +02:00
Karol Blaszczak
dcfa1f6881
[DOCS] bring back conda guide 23.0 ( #17031 )
2023-04-20 14:09:07 +02:00
Wanglei Shen
70e0eed075
update default affinity for macOS ( #17080 )
2023-04-20 11:50:04 +00:00
Mateusz Bencer
77a5d1aa03
[ONNX FE] Fixed handling duplicates during graph extraction ( #17071 )
2023-04-20 11:10:09 +00:00
Vladislav Golubev
f100c36ac9
[LPT] Revert changes in fold_reshape ( #17068 )
2023-04-20 11:43:59 +01:00
Yuan Hu
e53fc86988
[CPU] [Coverity] fix Uninitialized issue in node mvn ( #16980 )
...
* fix uninit issue in node mvn
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
* Revert "fix uninit issue in node mvn"
This reverts commit 45e68725f3
2023-04-20 12:34:49 +02:00
Yuan Hu
bef25ddf43
[CPU] resubmit pr for optimize shape infer of Reshape ( #16942 )
...
* Revert "Revert "[CPU] optimize shape infer of Reshape (#16537 )" (#16703 )"
This reverts commit 06cacfe2a7c305464c8c
2023-04-20 12:34:21 +02:00
Maksim Kutakov
70c3979602
[CPU] Execute constants in order with the create primitives calls ( #16795 )
2023-04-20 14:22:57 +04:00
Mikhail Ryzhov
0f7e6de346
[GNA] WA to fix config parsing of scale factor map ( #17060 )
...
* WA to fix config parsing
* clang fix
* excluded json
2023-04-20 10:51:23 +01:00
Maciej Smyk
7d574e3114
DOCS shift to rst - Opsets ( #17059 )
2023-04-20 10:59:35 +02:00
Maxim Vafin
552143c9cd
[MO] Fix Interpolate-11 in MO ( #17002 )
...
* Fix Interpolate-11 in MO
* Add forgotten file
* Fix output type of TopK-11
* Do not force precision on port 1 for mode scales
* Update tools/mo/openvino/tools/mo/ops/interpolate.py
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
2023-04-20 09:51:38 +02:00
Anastasiia Pnevskaia
5026aa044a
Removed naming of inputs in MO Python API PyTorch tests. ( #17070 )
...
* Removed naming of inputs in MO Python API PyTorch tests.
* Fixed coping of data.
* Small correction.
* Small correction.
* Small fix.
2023-04-20 11:49:45 +04:00
Marcin Kusmierski
4e6a129672
[GNA] Fix tests configuration to ensure that 3_5 target is tested too ( #17046 )
2023-04-20 09:18:36 +02:00
Nesterov Alexander
d00731c0ab
[ARM CPU] Fix tests for eltwise layer ( #16917 )
2023-04-20 09:57:29 +04:00
Taylor Yeonbok Lee
5bded05ae6
[GPU] Improve shape infer performance ( #17039 )
...
* [Dynamic shape] Improve shape infer performance for igpu by preventing copy from usm_device to usm host from lock()
* Fixed is_shape_infer_dep to use pointer instead of unique_id becuase unique_id may not be set
2023-04-20 03:23:52 +00:00
Tomasz Dołbniak
1bd9a1e01c
Passing tests re-enabled ( #17067 )
2023-04-20 01:55:42 +01:00
Ekaterina Aidova
f9fbcbe419
update omz submodule ( #16986 )
2023-04-20 03:53:39 +04:00
Ilya Churaev
71880aadd3
Deprecate set batch method ( #17057 )
...
* Deprecate set batch method
* Fixed some errors
* Suppress warning in tests
* Fixed warning in GPU
* Deprecate python
2023-04-19 20:21:18 +00:00
Ilya Lavrenov
1ec22a3180
32 bits support in Intel CPU plugin ( #16900 )
2023-04-19 22:10:20 +04:00
Eddy Kim
fab8236af3
[GPU] Fixed OneDNN fc+sum fusion serialization ( #16988 )
...
* fixed onednn fc+sum fusion serialization
* removed the white list for sum post op fusion
* added deconv fusing caching tests
2023-04-19 09:43:27 -07:00
Pawel Raasz
4c3a4a8992
Correct inf bound check for 32-bit in shape infer ( #17047 )
2023-04-19 19:33:01 +04:00
Nesterov Alexander
3d33cb2b43
[ARM CPU] Fix eltwise op tests (Divide) ( #17029 )
...
* update skip list
* skip change
* fix divide
* review fixes
* review fixes #2
2023-04-19 18:52:09 +04:00
Egor Duplenskii
39f843fb78
[CPU] Move to oneDNN 3.1 release version ( #16721 )
2023-04-19 18:26:30 +04:00
Tomasz Dołbniak
d230ad9313
Interpolate op cleanup ( #17026 )
2023-04-19 15:47:29 +02:00
Evgenya Stepyreva
497a19edf6
CVS-102308 Read tflite model to vector ( #17048 )
2023-04-19 13:27:41 +00:00
Pawel Raasz
d7083fb4db
Improve slice and strided slice shape inference ( #16940 )
...
when start, stop are interval values
2023-04-19 16:20:29 +04:00
Vitaliy Urusovskij
a611104b12
FQ tests leftovers ( #17009 )
...
* Try to return skipped test after FQ fix
* Copy FQ broadcast case from CPU to TEMPL tests
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-04-19 12:32:44 +01:00
Tatiana Savina
921bebc1ec
change ov version ( #17056 )
2023-04-19 11:28:41 +00:00
Mateusz Tabaka
7338257e00
Fix transformations tests on 32 bit build ( #17043 )
...
Ticket: 104593
2023-04-19 11:28:00 +00:00
Artyom Anokhov
bb6a3251a8
README.md: Added Conda Budge ( #17025 )
...
* README.md: Added Conda Budge
* README: Moved Conda badge after PyPI status
2023-04-19 12:35:31 +02:00
Egor Duplenskii
4ce5548c9a
[GNA] fix compilation warning ( #17027 )
...
Which becomes error with '-Werror'
2023-04-19 10:00:24 +00:00
Marcin Kusmierski
90b485715a
[GNA] Fix tests failing due to dependency to CI environment state ( #17007 )
2023-04-19 11:42:15 +02:00
