natas_hw
/
openvino
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
13,784 Commits 48 Branches 60 Tags 1.3 GiB
Commit Graph

13784 Commits

Author SHA1 Message Date
Luo Cheng ceeafaf64f
[CPU] Support group beam search (#21983) 
* support group beam search

* support dyn batch without set_state

* apply review comments

* strides may be incorrect when batch changed

---------

Co-authored-by: Yu Xu <yu.xu@intel.com>
 2024-01-08 16:42:05 +04:00
River Li 49231c0196
[CAPI] fixed ov_infer_request_wait_for return value issue (#22014) 2024-01-08 16:41:21 +04:00
Ilya Lavrenov 38ee887911
Ported changes from master to 2023.3 (#22012) 
* [JS OV] Specify JS API GitHub config (#21785)

* Extend CODEOWNERS by js api responsibles

* Extend smart ci by js component

* Fix codeowners

* Fix component definition

* Update components.yml

* Update components.yml

---------

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

* [GHA] Fix smart ci for docs changes in linux arm64 (#21798)

Update linux_arm64.yml

---------

Co-authored-by: Vishniakov Nikolai <nikolai.vishniakov@intel.com>
Co-authored-by: Alina Kladieva <alina.kladieva@intel.com>
 2024-01-08 16:33:58 +04:00
Maciej Smyk 429b89f0e4
Debian9 update to Ubuntu 18.04 (#21935) 2024-01-08 15:39:37 +04:00
Vitaliy Urusovskij 1df3008870
Fix `INFER_NOT_STARTED` infer status code (#21939) 
* Fix `INFER_NOT_STARTED` infer status code

* Update `returnDeviceBusyOnSetBlobAfterAsyncInfer` test
to check `INFER_NOT_STARTED` status only

* Update `wait` tests with `INFER_NOT_STARTED` check
 2024-01-08 15:35:20 +04:00
Maxim Vafin 7835368489
[DOCS] Update supported ops by PT FE (#21961) 2024-01-08 11:11:16 +01:00
Maxim Vafin cc8fadf187
[DOCS] Describe dict support (#21923) 
* [DOCS] Describe dict support

* Apply suggestions from code review

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

---------

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
 2024-01-08 11:11:05 +01:00
Pavel Durandin a741d5a8ba
Fix minus axis case for kv cache primitive buffer fusing (#21958) 
Co-authored-by: Taylor Lee <taylor.lee@intel.com>
 2024-01-05 09:22:42 +09:00
Alina Kladieva ca31765d1a
Bump OMZ submodule (#21943) 
unlimit pyparsing to fix CVS-128637
 2024-01-04 09:51:29 +01:00
Roman Lyamin 112a16a056
[GPU] Small fix for dynamic_shape_gather_opts pass (#21807) (#21882) 2023-12-28 14:48:38 +04:00
Roman Lyamin 7d948bf596
[GPU] Add set_arguments() call in case of dynamic dependencies of static inst (#21664) (#21884) 
Co-authored-by: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
 2023-12-28 14:48:13 +04:00
Maciej Smyk 4e15cc0b7f
Port from 21815 (#21839) 2023-12-27 16:01:33 +01:00
Wilson Seok e1bd2a7b55
Revert "[GPU] Fix accuracy problems brought by permute_f_y kernel (#20241)" (#21830) (#21876) 
This reverts commit 6719133af2.

Co-authored-by: Pavel Durandin <pavel.durandin@intel.com>
 2023-12-27 18:31:41 +04:00
Surya Siddharth Pemmaraju 8a5e6b6738
Fixed a bug in input validation for torch.compile options (#21835) 
* Fixed bug in input validation for torch.compile options

* Added default device if device is None

* Addressed PR comments
 2023-12-22 14:26:08 +04:00
Sebastian Golebiewski 81b5895d24
Move Troubleshooting Reshape article to legacy section (#21837) 2023-12-22 11:15:01 +01:00
Maciej Smyk e37569ffd5
[DOCS] Removal of unused images + fixing image directives for 23.3 (#21818) 
* removal of unused images

* removal of duplicate image files

* removal of unused files + fix for image directive

* removal of unused images

* removal of unused images + fix for protecting_model.rst

* overview document graph update
 2023-12-21 13:14:37 +01:00
Karol Blaszczak 07fc4d0813
[DOCS] NPU update 23.3 (#21812) 2023-12-21 09:24:52 +00:00
Tatiana Savina 7ef8faecf0
fix note and img (#21797) 2023-12-21 08:47:51 +01:00
Ilya Lavrenov 53960d6018
Switched GHA branches to 2023.3 (#21793) 2023-12-20 19:22:51 +04:00
Vitaliy Urusovskij 8384279b2e
Preprocessing tests to new utils (#21752) 2023-12-20 15:28:06 +04:00
Sebastian Golebiewski c95a34ea15
Updating thumbnails for notebooks (#21781) 2023-12-20 11:16:42 +01:00
Ilya Lavrenov 139242d47d
Delete old Azure pipelines (#21771) 2023-12-20 12:28:08 +04:00
Ilya Lavrenov 119dc95de6
Revert "[op conformance] Made fixes to allign with accuracy validation (#21347)" (#21778) 
This reverts commit 8f13219728.
 2023-12-20 11:41:27 +04:00
Ilya Lavrenov f6cd2150c2
Disable JS for on all Linux platforms with gcc < 7 (#21777) 2023-12-20 11:39:46 +04:00
Ilya Lavrenov 3a6a62558a
Disable system TBB on Linux arm64 (#21769) 
* Disable system TBB on Linux arm64

* Update cmake/features.cmake
 2023-12-20 10:53:49 +04:00
Sergey Shlyapnikov 51eab3c931
[GPU] Revert transformation changes (#21749) 
* Revert "[GPU] Apply is_non_decompression_multiply() callback only for compressed models (#21719)"

This reverts commit 032ac898e2.

* [GPU] Apply MarkDequantizationSubgraph callback function only to compressed models
 2023-12-20 03:46:09 +00:00
Vishniakov Nikolai 8d704f6400
[JS OV] Node.js API (#19848) 
Co-authored-by: almilosz <alicja.miloszewska@intel.com>
Co-authored-by: Andrei Kashchikhin <andrey.kashchikhin@intel.com>
Co-authored-by: yatarkan <yaroslav.tarkan@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
 2023-12-20 00:19:34 +00:00
Georgy Krivoruchko 2779df5800
[ONNX] Refactoring tests on API 2.0 (#21748) 
* Test in onnx_import_dyn_shapes.in.cpp moved to API 2.0

* Test in onnx_import_exception.cpp moved to API 2.0

* Tests in onnx_import_org_openvino.in.cpp moved to API 2.0

* Tests in onnx_import_org_pytorch.in.cpp moved to API 2.0

* Fixed code style
 2023-12-19 22:49:44 +01:00
Vitaliy Urusovskij e6ab01c681
Shared `onnx` tests to API2.0 (#21726) 2023-12-20 01:03:33 +04:00
Sofya Balandina 5b776e9f1f
[apiConformance] Fix checks for finding logs in analyze_confomance_fails (#21767) 2023-12-20 00:52:08 +04:00
Ilya Lavrenov 662aa57a92
Downgrade GHA for upload / download back to @v3 (#21770) 2023-12-20 00:48:31 +04:00
Ilya Lavrenov dc79c41fb8
Updated xbyak_aarch64 in onednn (#21762) 2023-12-20 00:13:17 +04:00
Jan Iwaszkiewicz 712e374519
[PyOV] Allow replacing of invalid bytes in string-based data (#21761) 
* [PyOV] Allow replacing of invalid bytes in string-based data

* Fix linter
 2023-12-19 23:25:52 +04:00
Georgy Krivoruchko 27c9ca749d
[ONNX] Switched to ONNX 1.15.0 (#20929) 
* [ONNX] Switched to ONNX 1.15.0

* Updated usage of ONNX serialization API

* Updated xfailed lists

* Updated xfailed lists

* Added xfailed ML-operators

* Added xfailed float8 cases

* Fixing mo tests

* Reverted legacy tests

* Sets default opset version in layer tests

* Skipped test which breaks moving on 1.15

* Updated xfailed list

* Fixed typo and added more tests to skipped

* Added xfailed tests

* Reduced opset due to need to work on onnx 1.13

* Removed unnecessary xfails

* Skipped misaligned tests

* WA for old compiler build
 2023-12-19 18:55:32 +00:00
Alina Kladieva 224eb79ab6
[GHA] Prepare new required stages for precommit (#21766) 
* Add Smart CI support to webassembly workflow

* Add ONNX_Models to required checks list
 2023-12-19 22:52:12 +04:00
River Li 7b1074b275
Generalize model cache reusing (#21492) 
* Generalize model cache reusing

* Use .as<std::AnyMap>() to convert std::string to std::AnyMap

* Store driver version for different devices

* Use driver version as gpu compiled model runtime properties
 2023-12-19 16:50:05 +01:00
Vladimir Paramuzov 294cc6668c
[GPU] KVCache custom op and fusion pass (#21689) 2023-12-19 17:56:25 +04:00
Yaroslav Torziuk 6719133af2
[GPU] Fix accuracy problems brought by permute_f_y kernel (#20241) 
* Add test cases from Levit model

* Enable PermuteKernel_f_y_axes kernel

* Fix permute of y and b for planar layout where x is not 1

* Enable fusing in permute_kernel_f_y_axes

* Add tests for fusing in permute_kernel_f_y_axes

---------

Co-authored-by: Wilson Seok <wilson.seok@intel.com>
 2023-12-19 13:50:32 +01:00
Nikolay Shchegolev 6246fb0c23
[CPU] StringMemory for the output tensor in the InferRequest (#21746) 2023-12-19 15:20:15 +04:00
Roman Lyamin 6060683f4c
[GPU] Fix for is_user_cpu() function (#21744) 2023-12-19 10:48:13 +01:00
Sofya Balandina 8f13219728
[op conformance] Made fixes to allign with accuracy validation (#21347) 2023-12-19 13:43:40 +04:00
Xiping Yan a3a3f0b55c
[CPU] Fix chatglmv2 accuracy issue and crash with input 1024 token in SPR (#21360) 2023-12-19 13:13:35 +04:00
Pawel Raasz 63cb89fe1b
Use move instead copy (#21732) 2023-12-19 12:43:28 +04:00
Maciej Smyk e94feea5c7
[DOCS] Update of graphs in repo (#21737) 
* csv files

* Update GNA.rst

* csv files

* csv files

* csv

* csv

* removal of duplicates

* duplicates removal

* Delete small_IR_graph_demonstration.png

* moving graph files to static folder

* Update LowPrecisionModelRepresentation.rst

* update
 2023-12-19 09:20:24 +01:00
Anastasiia Pnevskaia 3c157b2a1b
[TF FE] [Telemetry] Added error_info event to TF FE. (#21736) 
* Added error_info event to TF FE.
 2023-12-19 12:14:36 +04:00
Pawel Raasz 499a9694e5
Fix Coverity CID 1529136, 1529124 (#21733) 
* CID 1529136, fix auto makes a copy of PartialShape
- minor updates to reduce redundant Rank object creation

* CID 1529124 fix copy caused by auto
 2023-12-19 07:06:33 +00:00
rghvsh a4e8f9d98c
[ONNX] Extend ONNX Frontend with BitwiseAnd-18 operator (#21585) 2023-12-19 09:54:55 +04:00
Vladimir Paramuzov 63b23a1ebb
[GPU] Enable state precision conversion to infer precision (#21729) 2023-12-19 09:36:03 +04:00
Min, Byungil 0e92469330
[GPU] bugfix slice mem calculation for batch iteration (#21716) 
Signed-off-by: Min, Byungil <byungil.min@intel.com>
 2023-12-19 14:20:38 +09:00
Taylor Yeonbok Lee b770780b89
[GPU] Skip redundant gather in stateful model (#21681) 
* Skip redundant gather in stateful model

* Fix memory reuse issue for node skipped at runtime.
If the node is not marked as can_be_optimized at build time, memory dep is not properly applied
=> So it can cause the wrong memory reuse
 2023-12-19 00:00:39 +00:00