Jade Cho
e2b553302b
[GPU] Use preferred output format if node impl type is onednn ( #19601 )
...
+ Changes to use preferred format in both cldnn and onednn for gemm and
FC when shape inferencing.
2023-09-08 15:56:40 +09:00
Artyom Anokhov
f9560518e3
[DOC] Add hints for debug build ( #19675 )
...
* Added HINTS for generating PDB files and debugging
* Fixed upper case
* Keep hint only for Windows OS
* build_raspbian.md: Added empty line
2023-09-07 16:39:02 +02:00
Sergey Shlyapnikov
4eb9c57424
[GPU] Add input feature leftovers processing for fully_connected_gpu_bs_f_bsv16_af8_vload kernel ( #19650 )
2023-09-07 13:20:11 +04:00
Taylor Yeonbok Lee
4124851d2b
Revert "[GPU] Fixed reordered memory cache not to contain original weight memory ( #19465 )" ( #19659 )
...
This reverts commit e8f1df495c
2023-09-06 22:35:00 -07:00
River Li
252afa3b6c
[CPU] Fix incorrect output for float to bf16 in avx2 isa ( #19358 )
2023-09-07 09:09:16 +04:00
yanlan song
14e0b1fd2c
Do not clean batch setting if proxy plugin ( #19508 )
...
* do not clean batch setting if proxy plugin
Signed-off-by: fishbell <bell.song@intel.com>
* add tests
Signed-off-by: fishbell <bell.song@intel.com>
---------
Signed-off-by: fishbell <bell.song@intel.com>
2023-09-07 07:47:45 +04:00
Roman Kazantsev
63a6d4c41e
[TF Hub][GA] Set correct scheduler and model scope for regular validation ( #19658 )
...
* [TF Hub][GA] Set correct scheduler and model scope for regular validation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove empty line
* Update .github/workflows/linux.yml
Co-authored-by: Andrey Kashchikhin <andrey.kashchikhin@intel.com>
* Correct a path to output html report
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Andrey Kashchikhin <andrey.kashchikhin@intel.com>
2023-09-06 22:51:31 +02:00
David Nam
cb479f4a5d
[GPU] No need to add reorder after strided_slice ( #19411 )
2023-09-06 11:43:51 -07:00
Maxim Vafin
bacb83f8a2
Support aten::tile op ( #19645 )
2023-09-06 17:28:22 +00:00
Karol Blaszczak
c123843d0d
[DOCS] installation guide restructuring 23.1 master ( #19241 )
2023-09-06 17:46:55 +02:00
Andrey Kashchikhin
5644ca40f6
[GA] ccache: specify key ( #19519 )
...
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
2023-09-06 15:45:00 +00:00
Roman Kazantsev
4f7ac430fc
[TF Hub][TF FE][GA] Establish regular validation for all TF Hub models ( #19649 )
...
* [TF Hub][TF FE] Establish regular validation for all TF Hub models
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Correct names of reports
* Simplify configuration
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-09-06 17:02:59 +02:00
Roman Kazantsev
023a2f462a
[TF Hub][Notebook] Secure future notebook models in the precommit ( #19652 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-09-06 18:43:30 +04:00
Ilya Churaev
d9952b2455
Enabled clang format for unit test utils ( #19653 )
2023-09-06 14:37:12 +00:00
Vladislav Golubev
94bdaea965
[Snippets] ov::Node replaced with lowered::Expression in emitter constructors ( #19481 )
2023-09-06 16:45:50 +04:00
Maksim Kutakov
45cc4fdb33
[CPU] Fix input output tensor binding ( #19589 )
...
* Fix input output tensor binding plus test
* Clean up code
2023-09-06 17:04:38 +08:00
Ilya Churaev
7a4e765600
Removed legacy API from common frontend and shared tests ( #19583 )
...
* Removed legacy API from common frontend and shared tests
* Fixed build
2023-09-06 12:24:18 +04:00
Katarzyna Mitrus
bd66971dd6
[ShapeInfer] FFTBase shape infer improvement - preserve input sizes bounds and labels ( #19463 )
...
* Reduce number of rank checks
* Preserve data shape if signal_size input is not provided
* Add bounds propagation on fft input
* Improved preserving bounds on fft input
* Remove size_t rank cast and have_axes variable
* Check refactor
* Use ge helper for rank comparison
* Make bounds constexpr
* Pass raw pointer instead of unique_ptr ref
* Use normalize_axes helper
* Ensure to call set label if it's not zero
2023-09-06 12:20:58 +04:00
Anastasia Kuporosova
8723b5dd6d
resolve gil ( #19631 )
2023-09-06 10:04:52 +02:00
Ilya Lavrenov
46d05cc820
Fixed CPU plugin compilation ( #19629 )
2023-09-06 10:48:26 +04:00
Ilya Lavrenov
a322b8256d
Unlock custom creation of PLATFORM_TAG ( #19609 )
2023-09-06 10:46:37 +04:00
Maciej Smyk
4598da7a55
[DOCS][PT FE] Update pytorch conversion docs for master
2023-09-06 08:15:35 +02:00
Yury Gaydaychuk
8d6083e08e
[Commit slider] Skipping for commits ( #18966 )
2023-09-06 09:12:17 +04:00
Sungeun Kim
b7758b0504
[GPU] update the data-type of primitive from ops ( #19302 )
...
* set the data-type of transpose by dt of ops.
* set output_data in calc_output_layouts
2023-09-06 13:30:53 +09:00
dependabot[bot]
be23ac7c26
Bump actions/checkout from 3 to 4 ( #19602 )
...
Bumps [actions/checkout](https://github.com/actions/checkout ) from 3 to 4.
- [Release notes](https://github.com/actions/checkout/releases )
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md )
- [Commits](https://github.com/actions/checkout/compare/v3...v4 )
---
updated-dependencies:
- dependency-name: actions/checkout
dependency-type: direct:production
update-type: version-update:semver-major
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-09-06 07:29:13 +04:00
HARI CHAND BALASUBRAMANIAM
954536d2d6
Create documentation.yml ( #18926 )
...
This is for customer to report any issue regarding documentation.
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2023-09-06 05:27:12 +02:00
Ilya Churaev
dc1339d8e3
Remove legacy API from samples ( #19608 )
2023-09-05 22:16:18 +04:00
Ilya Churaev
1d62f0141d
Rename cmake ie_ macros and ie_parallel script ( #19606 )
...
* Rename cmake ie_ macros and ie_parallel script
* Add warning messages
2023-09-05 19:31:52 +02:00
Maciej Smyk
8f6b30a8f9
link fix ( #19624 )
2023-09-05 14:59:06 +00:00
Mikhail Ryzhov
bf5690fa7d
[GA] Parallel tests ( #18773 )
...
* test job
* added script to the test package
* test call fix
* switched test to large runner
* Added option to split tests by suites
* extended logs
* enabled test cache
* fixed workload
* optimized splitting mode
* excluded disabled suites
* temroary removed parallel logs
* added failed logs
* fixed empty name in suites
* test on 4 cores
* make step optional
* fixed param
* test
* grouping suites
* set suite arg
* increase test timeout
* test commit
* test pip deps
* include requirements.txt to the test package
* fixed deps step order
* fixed test counter
* fixed smart filter for suites
* clean up
* disabled repeat failed tests
* review comments
* use runtime execution time for skipped tests
* removed disabled suites
* reduced command lines
* enabled tests results
* fixed typo
* removed unused argument pp
* Log improvements
* merge cached and runtime filters
* fixed order
* fixed init list error
* fixed cache writing
* enable windows pipeline
* changed runner for windows
* optimized balancing using heap
* Fixed test counter
* fixed windows pipeline
* extended logging
* changed pipelines
* added logs on Windows
* fixed pipelines
* debug
* removed os specific code
* fixed "#"
* fixed test results
* fixed win pipeline
* cleanup debug
* rebase fixes
* windows pip requirements
* aligned run_conformance.py
* Apply suggestions from code review
Co-authored-by: Andrey Kashchikhin <andrey.kashchikhin@intel.com>
* reverted windows changes
* reverted build runner
* fixed review comments
* minor review fixes
* make help func static
* renamed test runner
* fixed merge issue
* removed unused log
* reduced command line
* fixed issue fith conformance run
* fixed typo
* set testa as default split unit
* fixed tasks queue with time -1
* fixed test result caculation
* reverted wrong fix
* reverted changes
* set time limitation
* reverted unused change
* fix win command lines
* reuse env variables in pipeline
* fixed install files permissions
* fixed pipeline syntax
* reset validation schema
* fixed env names
* reverted initial setting of env
* increased test runner
* fixed pathes
* reuse env path
* reset validation schema
* Revert "reuse env path"
This reverts commit 97422ac595010aa31641
2023-09-05 14:23:17 +00:00
Roman Kazantsev
188d53d813
[TF Hub][TF FE] Clean-up all downloaded files for TF Hub models validation ( #19612 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-09-05 13:07:13 +00:00
Vladimir Paramuzov
77600c7701
[GPU] Add FullyConnected custom op ( #19539 )
2023-09-05 16:47:05 +04:00
Mingyu Kim
3d679edf18
[GPU] Remove propagate_constants pass at pre_optimize_graph stage ( #19323 )
...
Co-authored-by: Lyamin-Roman <roman.lyamin@intel.com>
2023-09-05 16:37:31 +04:00
Ilya Churaev
5fd327ae30
Remove legacy API from IR frontend ( #19582 )
...
* Remove legacy API from IR frontend
* Remove dependency from inference dev API
2023-09-05 15:41:57 +04:00
Sofya Balandina
198da893d4
[analyzeConfFails] Fix arm device and exclude analyzing some files ( #19591 )
2023-09-05 12:28:45 +04:00
Alexander Suvorov
53414832eb
add 2023.0.2 selector tool ( #19598 )
2023-09-05 09:51:04 +02:00
Xiuchuan Zhai
1b5f428752
eliminate broadcast node in masked_fill ( #19595 )
2023-09-05 10:36:30 +04:00
Roman Kazantsev
4eadef9e61
[TF Hub][TF FE] Make TF Hub validation more robust and add convenient xfail test marking ( #19596 )
...
* [TF Hub][TF FE] Use multiprocessing based tests for TF Hub validation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix import and initialization
* [TF Hub][TF FE] Make TF Hub validation more robust and add convenient marking for failing cases
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-09-05 09:41:01 +04:00
Ilya Lavrenov
c3b0c531f7
Added tflite to 'predefined_frontends' list ( #19599 )
2023-09-05 09:33:35 +04:00
Ilya Churaev
75b6a24787
Remove ICore legacy mock object ( #19573 )
2023-09-05 00:42:42 +04:00
Ilya Churaev
509e00da60
Move Inference Functional Caching Tests to new API ( #19513 )
...
* Moved inference unit tests to new API
* Added infer request and variable state
* Try to fix LTO
* Try to avoid warning from gmock
* Try to fix azure build
* Try to fix Windows build
* Comment all variable_state_test file for future investigation
* Start migration of caching tests to new API
* Removed legacy API from mock_plugin
* Fixed more tests
* Remove redundant code
* Enable more tests
* Move all tests, need to reenable tests
* Revert incorrect change
* Cosmetic changes
* Fixed AUTO BATCH tests and disabled hetero tests
* Fixed crash in HETERO tests
2023-09-05 00:42:11 +04:00
Evgenya Stepyreva
fef4d4d641
Auto batch lost label fix ( #19535 )
...
* Restored opset1::Reshape label peropagation for -1 special value
* Lets opset1::Reshape keep same shape infer. Makes FindBatch transformation keep labels in output shapes of Result node
* uses Parameter from correct namespace
2023-09-04 17:11:09 +02:00
Ilya Churaev
15685e0141
Remove legacy API from snippets tests ( #19577 )
...
* Remove legacy API from snippets tests
* Fixed comment
2023-09-04 14:09:26 +00:00
Maciej Smyk
3677dda457
[DOCS] 23.0 to 23.1 link update for master ( #19584 )
...
* 2023.1 link fix
* 2023.1 link fix
* 2023.1 link fix
* 2023.1 link fix
* 2023.1 link fix
2023-09-04 15:40:02 +02:00
Vladimir Paramuzov
2f782b2131
[GPU] Add permute primitive instead of manual copy for deconv weights ( #19516 )
2023-09-04 17:03:49 +04:00
Sebastian Golebiewski
2d760ba1bf
Adding Quantizing with Accuracy Control using NNCF notebook ( #19585 )
2023-09-04 14:57:35 +02:00
Sofya Balandina
8f4d72826a
[apiConformance] Fix double numbers in results after merge xml ( #19564 )
2023-09-04 16:52:23 +04:00
Mateusz Tabaka
bd0c156a70
PullReshapeThroughReduce - skip transformation if Reshape doesn't unsqueeze input ( #19477 )
...
Ticket: CVS-118905
2023-09-04 13:58:53 +02:00
Mateusz Mikolajczyk
c46f6bf115
[PT FE] Add aten::swapaxes ( #19483 )
...
* Add aten::swapaxes
* Add comment
* Improve swapaxes tests
2023-09-04 13:04:28 +02:00
Maciej Smyk
511f06f9ba
[DOCS] Fix for Install from Docker Image for master ( #19505 )
...
* Update installing-openvino-docker-linux.md
* Update installing-openvino-docker-linux.md
* Update installing-openvino-docker-linux.md
2023-09-04 11:35:07 +02:00
