* [GHA] Set SSL_CERT_FILE for model downloading
* Run Win CC in precommits
* Move setting SSL_CERT_FILE before calling CMake
* Set SSL_CERT_FILE for model downloading in windows.yml
* Wording
* Revert "Run Win CC in precommits"
This reverts commit 94126aab1c.
* Applied common functions to tests in conversion.cpp
* Refactored convert_partially_tests
* Refactored convert_tests.cpp
* Removed usage of ngraph namespace in load_from.cpp
* Replaced definition in model_support_tests.cpp
* Fixed codestyle
* Move infer_convolution_forward to dev API
* Move infer_auto_padding to dev API
* Move evaluate_as_partial_shape to dev API
* Move default_label_evaluator to dev API
* Move generate_transpose_default_order to dev API
* Move is_valid_axes_order to dev API
* Move has_no_labels to dev API
* Remove usage of legacy get_constant_from_source
from core and transformations
* Move normalize_axes to dev API
* Move normalize_axis to dev API
* Deprecate functions to be removed later
* [PyOV] OVDict as input for infer/call methods
* for copied inputs
* improvement
* add test
* apply comments
* add test assert
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* CLean up ov_helpers headers from ngraph/
* Move `ngraph/` includes from ov_helpers to tests
* Remove include of all opsets in builders.hpp
* Remove opsets includes from ov_helpers
* Fix GNA tests
* Delete comments
* ClangFormat
* Fix build
* Fix `-fpermissive`
* Fix build #2
* Fix `<` && `>` in includes
* Fix build #3
* Build fix
* [CPU tests] migrate single layer test cases to be API 2.0 - part 8
* [CPU tests] migrate single layer test cases to be API 2.0 - part 8
* Fix skipped testcase issue
* Remove unused ie header files
* [PT FE] Report unsupported operations with model list
* Continue on error
* Disable more models
* Check if file exists
* continue of error
* Fix on failure
* Fix file path
* Apply suggestions from code review
* the proxy device with id should be also a proxy device.
* 1. using real name in the logic of checking if device is proxy.
2. Disable the added test case.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* enable test case
---------
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* resolve skipped HF models: 2nd batch
* commented out models with no info and less than 10 downloads
* Revert "commented out models with no info and less than 10 downloads"
This reverts commit a55861ed69.
* replace with self.image
* resolve todo
* Update tests/model_hub_tests/torch_tests/test_hf_transformers.py
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>
* Added common functions for onnx tests
* Removed test cases which are non-related to ONNX
Extended convert_model by extension
* Extended test utils by convert_partially
* Added model convertion using istream as input
* Moved common functionality to a ov namespace
* Removed unused function
* update parse_processor_info_macos for wrong macos info
* update default setting
* update default setting
* update for comment
* fix typo
* update test data
* update init order
* Switch Windows Conditional Compilation workflow to AKS runners
* Fix YAML syntax
* Limit number of threads for CC build
* Split build stages to two to avoid step being successful when it's not
* Install python to conditional compilation job
* Combine both build commands into a single step
* Trying to work around sccache port issue
Sometimes build hangs and then ends by timeout. The only error message
in the logs is "sccache: error: An attempt was made to access a socket in a way forbidden by its access permissions. (os error 10013)"
* Temporary disable ctest step
* Revert "Temporary disable ctest step"
This reverts commit 8714200994.
* Disable Windows conditional compilation for PRs
* [PyOV] Expose result op
* update docs with op.Result
* codestyle
* add test and fix flake8 errors
* add result test
* fix transformation tests
* update return type
* [CPU] CPU API 2.0 migration for TensorDesc
* Fixed CustomOpCPUTest issue
* Cleanup unused code
1. normalize_preprocess
2. MemoryDescUtils::convertToBlockedMemoryDesc
3. Fix a typo issue
* Fix zero dim with none zero strides issue
* Fix Expected and actual shape are different: [] VS [1]
* Remove InferenceEngine::Layout
* Solve rebase issues
* Update for code reviewer's comments
* Keep ov::intel_cpu::node::Generic for legacy compatibility
* Solve scalar data issue
* Solve reviewer's comments
* Restore Generic registeration
* fix coredump with numactl
* record original socketid and numaid
* update comment
* update comments
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
* extract cpu func tests into a reusable workflow
* add needs
* check paths
* correct paths
* rm usage of setupvars
* extract samples
* use yaml string
* split mac workflow
* check variables
* try github workspace
* check full dir
* set variables
* try with sub directory
* Revert "try with sub directory"
This reverts commit d891ee3f28.
* extract c++ tests from linux
* change
* use cxx workflow in mac workflows
* add noninteractive
* extract cpu func tests
* rm unused
* enable mac
* fix reusable workflow name
* correct path for sparse-checkout
* extract python UT
* remove unnecessary asterisk
* remove another unnecessary asterisk
* use reusable action for linux cc
* add check for setupvars existence
* check with manually installed opencl
* add components input to samples workflow; rm pr triggers for mac workflows
* add missing needs
* add missing option for deps install script
* use disables in test themselves instead of ifs in workflows
* use reusable workflow for cxx tests in linux arm
* use python reusable workflow in linux arm
* add missing endif
* use self-hosted for samples, add x86_64 constraint for jax
* check paths
* find gompby partial name
* skip failing tests on arm; correct gomp finding for ovc
* check tests
* add debian packages job; use job_ prefix for reusable workflows with jobs
* extract tf hub model tests
* extract tf model hub perf tests
* extract pytorch models tests
* do not use container on GHA runners
* extract onnx runtime
* add missing deps
* skip test for linux arm
* rm always()s
* fix quotes
* correct paths
* correct ifs, check dir for onnxruntime
* correct path for onnxruntime utils folder; install python3
* use self-hosted as input
* check for self-hosted runner via name, pass version
* skip cpu plugin unittest
* check cxx tests
* rm pr trigger
* [TF FE] Switch on ConvLSTM2D layer tests in pre-commit
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove extra blank line
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* use perf_counter_ns to measure performance; meausure within time not count
* fixes
* remove nightly
* set 60 secs by default
* fix output html
* code review fixes
* fix runtime duration
* remove unneeded inference
* cleanup
* Add and implement the logic of property SCHEDULE_POLICY for MULTI plugin.
* Updated.
* Enable test case for schedule policy test.
* enable test case for property ov::intel_auto::schedule_policy.
* Update.
* Updated.
* Updated.
* Update.
* Update the lock logic here by considering the runtime fallback case.
* Update.
* Update.
* Update.
* Update default value of schedule policy to DEVICE_PRIORITY
* Enable the function test case for schedule policy.
* Add description for inference requests schedule policy within AUTO plugin cumulative mode.
* Updated.
* Python bindings for enum SchedulePolicy and property ov::intel_auto::schedule_policy.
* Update.
* Update.
* Update.
* Updated.
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
* [GPU] Add SLM support for FC bf tiled kernel
* Fix unaligned IFM leftovers processing in case of compressed weights and add decompression scale post op support
* added FullyConnected_bf_tiled::GetUpdateDispatchDataFunc
* updated FullyConnected_bf_tiled::GetUpdateDispatchDataFunc for two types of kernels
---------
Co-authored-by: Kim, Eddy <eddy.kim@intel.com>
* [CPU tests] migrate single layer test cases to be API 2.0 - part 3
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* [CPU tests] migrate single layer test cases to be API 2.0 - part 3
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
---------
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* add failToSetUninitializedInputBlob, failToSetUninitializedOutputBlob and canInferWithGetOut
* FailedAsyncInferWithNegativeTimeForWait
* Revert "FailedAsyncInferWithNegativeTimeForWait"
This reverts commit 3b6780102f.
* Update src/tests/functional/plugin/shared/src/behavior/ov_infer_request/io_tensor.cpp
Co-authored-by: River Li <river.li@intel.com>
* Update src/tests/functional/plugin/shared/src/behavior/ov_infer_request/io_tensor.cpp
Co-authored-by: River Li <river.li@intel.com>
---------
Co-authored-by: River Li <river.li@intel.com>
* Migrate Gather operators to new API
* Remove redundant code form reference
* Use IF_TYPE_OF macro
* Remove unused include
* Use common utils in gather base
* Fix normalize after merge issues
* Port properties in time and stress tests to API2.0
* Port CC tests infer_tool.py to API2.0
* Update tests/conditional_compilation/tools/infer_tool.py
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Fixed comments for linux-riscv64 GHA workflow
* Try to enable PDPD tests back
* support paddle 2.5
* fix op test errors
* fix op test errors
* recover openvino/src/core/src/op/swish.cpp
* recover thirdparty open_model_zoo
* update cmakelist
* disable some tests
* fix code style
* enable paddle ci tests
* disable some tests
* fix np.long error
* recover reverse op
* update ci config
* recover set_value test codes
* rm linux_debian.yml
* Compatible with cases where different paddle versions have different output shapes
* remove set_value tests
* recover save_model.py
* Added ctest labels for FE tests only if FW is found
* recover thirdparty
* Update CMakeLists.txt
Fixed creation of paddle_tests target two times
* update paddle v2.5.1 proto file
* recover thirdparty
* fix Paddle_Reader_Tests.LoadModelMemoryToCore error
* fix Paddle_Places test issue in v2.5.1
* support some tests for low version paddle
* fix paddle FrontEndCutModelTest issue
* fix
* support all other tests for low version paddle
* fix codestyle
* fix codestyle
* Update generate_multi_tensor_split.py
* fix build error
* add testUnloadLibBeforeDeletingDependentObject into paddle skip tests config
* remove PROTOBUF_LITE from paddle CmakeList.txt
* fix path error
* add debug info
* add debug codes
* use make_model_path
* recover
* add option optimize_for
* use FrontEndTestUtils in read_paddle_model_test.cpp
* use FrontEndTestUtils in read_paddle_model_test.cpp
* fix grid_sample error when using dynamic shape
* fix error tests for 2.4 version
* add paddle version judge for floor_div
* fix grid_sample and add tests
* fix
* fix
* recover
* recover grid_sampler
* Apply suggestions from code review
* fix
* Apply suggestions from code review
* Apply suggestions from code review
* fix build error
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: meiyang-intel <yang.mei@intel.com>
* Remove usage of util::wrap_tensor
* Remove tensor conversion utils
make it local in model to remove with legacy evaluate
* Make only output tensor dynamic if Shape{0}
* Evaluate fixes on HostTensor
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* add arm as a matrix for build job
* uncomment
* comment
* try inside pipeline
* check location
* another dirs
* try to privide correct action path
* use corrected action
* use newer commit
* use newer commit
* use newer commit
* use newer action commit
* add setting
* rm from pipeline, adapt action iteslf
* add missing deps
* enable samples and debian jobs
* correct yml
* correct image name
* correct syntax, use self-hosted option
* enable onnx runtime and c++, use newer action
* enable Python and CPU Func tests
* add missing deps for arm64
* increase timeout for python tests
* disable some tests, add more time
* skip failing tests
* skip speech sample test on arm
* dummy chang
* skip mxnet mo on arm, run all tests
* rm quotes
* separate linux x86 and arm64 workflows
* rm unused matrix refs, add timeouts
* add skips for c++ tests and some Python tests
* correct cache keys, extend timeout
* skip more python tests
* add more skips: for python and CPU func
* extend cpu func list with skips
* disable cpu func tests and python api 2.0 tests
* rm disable job
* styling, rm pr trigger, rm always(), rm unnecessary changes
* revert
* use ifs instead of comments, provide better wording for skips
* [TF FE] Support different types: u16, u64, u32, boolean
Support constants of different types and dtype attribute values
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Use map instead of unordered_map
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add tests with different types
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* fix didn't udpate last second input issue
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* to match master code
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* fix review comment
use parametrized test case instead of creating new test case
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
---------
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* Improve Constant creation from string values
* Optimize Constant creation from vector<T>
binary size reduction
* Fix code style
* Add tests to check there is no precision los
* Fix conversion for string -> integral numbers
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* only use current thread when -nstreams=0 with TBB
* add comments
* fix building issue
* fix comments
* only use current thread when -nstreams=0 with TBB
* add comments
* fix building issue
* fix comments
* fix scatter update axis name
* Remove _exec_deps control for backedge_from because this is not required after PR-21333
* Previously, we organized execution order based on dependency for input-output buffer sharing from loop-body
* With PR-21333, we are not sharing buffer between input and output when loop input has multiple outputs.
* Therefore, there is no need to adjust exec order.
* 1. Update the logic for filtering out the device that supports the stateful model.
2. Enable the function to create stateful model in the test case.
* 1. Enable unit test cases for stateful model support.
2. disable accelerator device(CPU_HELP) if model is stateful.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
* Updated.
* Updated.
* Updated.
---------
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* [GPU] union 1D and scalar output dim for subgraph is skipped in condition
* Set friendly name using primitive_id for debugging.
* Do not share memory between internal input and external input when internal input has backedge in loop
* Set backedge mode to SINGLE when backedge_from_prim has multiple users
* Add condition unit test to check empty inner body
* Fix functional test failures
* Fix unit test failure on dg2
* Follow up code review - rename function
* [Core] Support String Tensors
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add String Constant implementation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix build issue in tests
* Add cast_vector for Constant of ov::string type
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix build issue
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix build issue: ambiguous type in GNA
* Fix ambiguous build issue in GNA tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix code-style
* Fix code-style
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix ambiguous build issue in GNA tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix ambiguous build issue in TF FE tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update openvino.style for naming convention check
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix compilation error in core unit tests - need typename
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add test for new element_type
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix code-style
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update src/inference/src/dev/make_tensor.cpp
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Add support of string Tensors for Constant
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix copying string tensor value for Constant
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Complete template methods for Constant
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Improve performance for initialization and destruction of string Tensor for set_shape
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add check for string value in test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove unused variable
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update src/inference/src/dev/make_tensor.cpp
* Fix copy_to for ITensor of string type and add tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add tests for Constant of string type and serialization
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Use memset_allocation to switch initialization
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add additional documentation for host_ptr
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update src/core/src/op/constant.cpp
* Use OPENVINO_THROW
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update src/core/include/openvino/op/constant.hpp
* Update src/core/include/openvino/op/constant.hpp
Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
* Apply code-review feedback: use string_size
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply code-review feedback
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Recover evaluate impl for non-string type
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix code for creating of string constant for legacy non HostTensor tensor
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix build issue
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply code-review feedback: simplify copy_to method
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix build issue
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Use StringAlignedBuffer to store string Constant values
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Remove not needed methods in StringAlignedBuffer
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Refactor set_shape method
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
* Use ShapeOf node output type to evaluate bound
- lower bound is not set to 0 when only upper is above inf
- update test where lower bound was set to 0 previously
- re-factor label evaluation
* Remove `max_et_val` from capture list
* Fix constexpr capture for MSVC
* Restore clear lower bound if upper is infinite
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* cldnn::program serialization
* fixed to set a stream in a outputbuffer
* removed unnecessary comments
* replaced emplace_back with push_back
* updated bool vector serializer
* fixed several bugs
* removed m_model from compiled_model
* fixed streams_test for model caching
* updated mutable_data handling logic
* added a new API SetUpdateDispatchDataFunc
* updated to serialize weights_reorder_param
* added functional tests for dynamic model caching
* renamed to GetUpdateDispatchDataFunc
* added dynamic model caching tests
[Snippets] BufferManager is not derived from PassPipeline now
[Snippets] Added MemorySolver support
[Snippets] Made as static class
[Snippets] Added one-level inplace support
[Snippets] Added optimization bits
[Snippets] Small cosmetic fixes
[Snippets] Renamed to BufferSolver
[Snippets] Refactored
[Snippets] Fixed IdendifyBuffers
[Snippets] Add inplace multi + identify buffers
[Snippets] Made common pass
[Snippets] Added PassPipeline::get_pass<>()
[Snippets] Added comments, briefs, refactored smth
[Snippets] Fixed win build
[Snippets] Not allow to have the same Buffer ID for multi level Buffers
[Snippets] Moved CleanupRepeatedPtrShifts to common pioeline
[Snippets] Made IdentifyBuffers::ShiftPtrParams
[Snippets] Fixed window sliding mode
[Snippets] Refactored nested clusters
[Snippets] Adde normalized buffer regs
[Snippets] Not allowed to have the same ID for nested Buffers in IdentifyBuffers
[Snippets] Fixed DefineBufferClusters::are_buffer_neighbours::find
[Snippets] Removed useless method from InitLoops
[Snippets] Fixed CC build
[Snippets] Applied Ivan comments
[Snippets] Applied Ivan comment: refactored pass classes
[Snippets] Applied Vladislav comments
[Snippets] Applied Ivan comments 2
[Runtime] Moved MemorySolver to API2.0
[Snippets] Created common buffer allocation pass AllocateBuffers
[Snippets][Tests] Added InplaceEltwise unit test
[Snippets] fixed NormalizeBufferIDs
[Snippets][CPU] Fixed BrgemmBlocking lowered pass: move wsp for AMX to brgemm
[Snippets][CPU][Tests] Covered AMX MHA buffer allocation by unit tests
* Integrate `IfTypeOf` class with CC
- Add macro to warp class to add support for CC
- Update `ccheader.py` to created PP symbols for template parameter list
- Use new macro in Convert operator
* Correct symbols generation
* Update OV PP macros
* Wrap TestVisitor into namespace{}
* Removed not required macros, update comments
* Update element_visitor.hpp
* Migrate Range operator to new API
- remove legacy function an duplicated shape inference
- Minor change range reference implementation
* Move accessing tensors after validation
* [PT FE] Fix timm model list according to newest version
* Remove xfail for hf model passed in latest nightly
* Fix code for loading vit_h model
* Restore torchvision
* [CPU Plugin][Func Test] Upgrade Fuse related to API 2.0
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* Update src/plugins/intel_cpu/tests/functional/subgraph_tests/src/fuse_non0_output_port.cpp
Co-authored-by: River Li <river.li@intel.com>
---------
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
Co-authored-by: River Li <river.li@intel.com>
* [CPU Tests] migrate ConcatResizeConcatTest to be 2.0
* [CPU Tests] migate matmul test cases to be api 2.0
* Update
* Revert "[CPU Tests] migate matmul test cases to be api 2.0"
This reverts commit b5fe09b3fa.
* Remove Node type
CPU graph always adds Result node for outputs which don't have consumers. If Conversion is inserted between such output and Result this Conversion became consumer and require defined memory.
* FakeConvert spec init
* Add spec files to the opset docs
* Remove apply_scale attribute and update inputs description
* Experimental op notice
* Update short description
* Update detailed description.
* Add BF16 type to supported inputs
* Update note about "Fake"
* Add more details
* Add formula of the operation
* Migrate leftovers in Loop operator to new API
- use new version of `get_constant_from_source`
- migrate `is_rank_compatible_any_of` to dev API
- Improve rank compatibility checks
* Use new version of `is_rank_compatible_any_of`
instead deprecated to reduce bin-size
* Remove deprecated `is_rank_compatible_any_of`
* [GPU] Fix constant dimension in case of node from if-op internal body
* Add a condition to restrict to case where allow_new_shape_infer is false
* Add a condition to restrict to case where allow_new_shape_infer is false
* Add functional test
* Add a condition to retrict to case where the program is inner program
* Add Smart CI for more pipelines. Refactor logic for workflow skip
Since different workflows may have different requirements for skipping them, I suggest to move these requirements to parameters instead of hardcoding them
* Use patterns for skipping pipeline for conformance-only
* Remove path filters for Android
* Return mistakenly deleted param
* Propagate params to Python script
* Add missing outputs mapping
* Return push trigger
* Skip CC CPU func when CPU is not affected
* Fix variable name
* [TF FE] Speed up compilation - part 5
Avoid usage of heavy opsetX header
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Complete constant.hpp template methods for string Tensor
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Revert "Complete constant.hpp template methods for string Tensor"
This reverts commit 8f86ab2e7b.
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-11-27 10:51:18 +04:00
River LiandDurandin, Pavel <pavel.durandin@intel.com>
* [Core] lstm api fix
* Fix LSTMCell failure issues
* Solve GNA failures
* Update for comments
* Minor update
* Use new ov::test::utils::makeEltwise
---------
Co-authored-by: Durandin, Pavel <pavel.durandin@intel.com>
* FakeConvert op init
* Update dest types names
* Update op hpp
* Update opset ops number
* Init type_prop tests
* Add attributes tests
* Add op check test
* Update namespace in fc cpp
* Update getters
* Refactor static member
* Make destination_type lower case
* Update type in test
* Move get_valid_types out of class
* Update ops number in opset
* Evaluate init
* Init poc evaluate
* Update types name
* Style update
* FakeConvert eval tests
* Add support for FP16 input
* Remove unused functions
* Use const auto and constexpr
* Create fake_convert reference file and move ref functions
* FakeConvert eval and reference update
* Remove unused is_normal variable
* Add bf16 tests
* Update construtor in tests
* adjust convert helper name
* Update comments
* Make func params as constexpr
* Update types
* Non scalar scale shape tests
* Use autobrodacast_select
* Use single autobroadcast_select
* Check scale_shape size
* Add var to keep scale_shift lambda
* Use lamda only for autobroadcast
* More checks for per channel scale
* Remove union half_t
* Change template to fp16 type for emulate
* Use f8e4m3_min_val as constexpr
* Update unsigned short to uint16_t
* Minor style refactor
* Minor comments update
* Update fake_convert_details namespace to func
* Update apply_conversion return type
* Add doxygen text
* Update supported type assert
* Remove duplicated tests
* Update namespace move to cpp
* Fill init with zeroes instead of reserve
* Use add div mul sub reference for applying scale
* Use autobroadcast_select for applying scale
* Bring back opt broacast cases
* Reuse scale_shift as func
* Adjust s and o var names
* Update multiplication in loop tu accumulate
* Add sort to test params
* Add more tests, batch, classes, sort
* test_sort_batch
* Fix sorting if sort_result_desc true
* Diable clang for test data
* Reenable type tests
* Fix comment
* Use std tie for values comparison
* Update var names to lhs and rhs
* Apply alignment with nms patch for GPU
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* migrate threading related interface from API 1.0 to 2.0
* fix code style
* fix @ref issue in doc
* change <> to quotation marks
* restore threading related interface API 1.0
* restore the changes of legacy code
* binding pcore for stream calculation
* remove useless branch
* modify the function of query cache size
* fix compilation error
* use MT2.0 interface
* bind core when there is ecore
* initialize Xbyak::util::Cpu object at the begining of compile_model
* restore the file
* initialize Xbyak::util::Cpu object at the beginning of cpu plugin
* remove unused header
* extract task executor creation into a separate function
---------
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
* Switch Windows workflow to self-hosted runners in AKS
* Uncomment 'pull_request' event
* Fix YAML indentation
* Fix YAML indentation again
* trying to pre-create sccache dir
* Fix yaml syntax
* Add sccache blob storage prefix
* sccache directory creation seems unneeded
The issue was in the usage of bsdtar instead of GNU tar - the former
is in C:\Windows\System32, which is the first entry in the PATH
* Fix sccache --zero-stats command for Linux
* [windows] Replace ccache-action with sccache-action sccache install
We don't need to use GitHub Actions cache feature as we have sccache
and Azure Blob Storage
* Switch the rest of the stages to AKS runners
* Hardcode VS Build Tools version
* Revert "Hardcode VS Build Tools version"
This reverts commit ea9ae1fb33.
* Increase timeout for C++ Unit tests
* Increase timeout for particular step
* Further increase of timeout
* Switch Windows Conditional Compilation workflow to AKS runners
* Fix YAML syntax
* Revert "Increase timeout for C++ Unit tests"
This reverts commit e9a00c41ad.
* Revert "Fix YAML syntax"
This reverts commit ecc1b15552.
* Revert "Switch Windows Conditional Compilation workflow to AKS runners"
This reverts commit d5969d58cd.
* Disable PR trigger for Windows workflow
Let's run this in test mode on master branch only for a while
* [GPU] Update space_to_depth to use nGraph shape inference
+ Added calc_output_layouts to use shape_infer
+ Added relevant test-cases for static and dynamic
+ Modified typo of filename
Signed-off-by: Min, Byungil <byungil.min@intel.com>
* Optimize OV assertions to reduce bin-size of libs
* Migrate assertion leftovers in CPU plugin
* Add NotImplemented::create to support use with macro
OPENVINO_ASSERT_HELPER
* Remove CheckLocInfo struct
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* implementation of loop for new tf fe
* fix loop dynamic shape func test case failure
* backedge memory validation for static shape
* update checking user of backedge_to_prim
* avoid opt out of loop body network reorder result
* fix for batch 2 case
* fix batch2 case for loop
* fix build error
* fix missing condition
* Update reverse infer to allow changing shape if it already partially defined
* Update tests
* Remove changes in If
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Drop legacy stuff
* Drop HostTensor
* Remove unused element types support
* Revert "Remove unused element types support"
This reverts commit 2ca8280c56.
* Improve style
* add to DisableShapeOfConstantFolding flag; set it in ts_gather; add unit test
* fix ts_general; use check_shape flag in EnableShapeOfConstantFolding
* set EnableShapeOfConstantFolding constructor explicit
---------
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
It's possible now to have in main.py:
parser = parse_args()
import argparse, openvino
core = openvino.Core()
class print_help(argparse.Action):
def __call__(self, parser, namespace, values, option_string):
parser.print_help()
print("\nAvailable target devices: ", (" ".join(core.available_devices)))
sys.exit()
parser.add_argument('-h', '--help', action=print_help, nargs='?', default=argparse.SUPPRESS, help='Show this help message and exit.')
args = parser.parse_args()
The details are in https://github.com/openvinotoolkit/openvino/pull/20098
* Workaround for some non-repo components in Smart CI
* Add possibility to add all components as dependent
* Remove extra check
* Add test case for "all" key
* [GPU] Fix accuracy issue for blocked format batching on iGPU
+ Bugfix GET_INDEX for batching of b_fs_zyx_fsv16 of target model
+ Updated fetch_data.cl
+ Minor fix of error message
Signed-off-by: Min, Byungil <byungil.min@intel.com>
* [TFLite] Fix for crash in case of zero-length file
* Extended verification using FourCC check in the header
* Fix for Linux build
* Fixes for Linux
* Some platforms may miss SizePrefixed... method
* Fixed path preparation
* [GPU] Fix loop issues
* if loop does not run inner body, return zero dimension layout for dynamic dimension layout
* Support dynamic sliced input in inner body in creaet concate mapping
* Modify update_shape to call reset_shape_changed() when inputs of loop are not changed
* Add unit test
* Follow-up codereview
* Skip empty subgraph of If operator
* Added test
Applied review comment
* Fix for the following case:
1) body network output has only constant input
2) body network output itself is the constant
* introduced ov.save_model(...) to the ptq code examples
* replied to comments
* fixed rendering
---------
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
* 1. Add Op_conformance_utils lib.
2.rename targets.
3. Remove behavior folder from api conformance
4. Remove ov1.0 from opImplCheck
5. move tests and insts to one file
6. small refactoring for op conformance test names
* align namespaces, remove test_utils from subgraphs_dumper
* update target names
* Remove extra
* Fix the tests without shapes in meta
* fix failed test names
* Add attribute reader
* Fix buils
* Check the registered lib
* try
* add comparator
* Revert "try"
This reverts commit 27eaa4ea0f.
* try to fix win build
* types
* tr
* remove pragma once
* Migrate Convert operator to new API
* Unify Convert reference for non-LP types
* Correct evaluate when output tensor not allocated
* Correct input type name
* Restore static_cast for bool as char
* Update random_uniform in multinomial reference implementation to generate values of the same type as the first input
* Add kernel selector for multinomial
* Add multinomial primitive and its instantiation
* Add calc_outut_layout implementation for slice_inst
* Multinomial builder
* Add multinomial kernel
* Add multinomial single layer test class
* Add GPU multinomial tests instantiation
* add get property test case
* add CanCreateTwoExeNetworksAndCheckFunction and pluginDoesNotChangeOriginalNetwork
* tmp
* add canSetInputPrecisionForNetwork and canSetOutputPrecisionForNetwork
* fix code style
* tmp
* Revert "tmp"
This reverts commit ff3f8d56d5.
* tmp
* add CanCompileModelWithEmptyProperties
* remove comment
* add infer request
* add CanLoadNetworkWithCustomLocale
* add CanLoadNetworkWithCustomLocale
* fix error
* remove case in io_tensor.cpp
* fix Unsupported metric key: OPTIMAL_BATCH_SIZE
* Update src/tests/functional/plugin/conformance/test_runner/api_conformance_runner/include/api_conformance_helpers.hpp
Co-authored-by: Chen Peter <peter.chen@intel.com>
* fix batch size
* remove useless code
* remove failed case CanCompileModelWithEmptyProperties, CanLoadNetworkWithCustomLocale and LoadNetworkWithBigDeviceIDThrows to test
* Revert "remove failed case CanCompileModelWithEmptyProperties, CanLoadNetworkWithCustomLocale and LoadNetworkWithBigDeviceIDThrows to test"
This reverts commit 1317d0773c.
* Revert "remove useless code"
This reverts commit b3dd0ffaab.
* Revert "fix batch size"
This reverts commit 2afd673cff.
* Revert "Update src/tests/functional/plugin/conformance/test_runner/api_conformance_runner/include/api_conformance_helpers.hpp"
This reverts commit 9d6030952f.
* Revert "fix Unsupported metric key: OPTIMAL_BATCH_SIZE"
This reverts commit 2de26547ea.
* try to add optimal_batch_size in cpu plugin
* return model when optimal_batch_size not found in apply_auto_batching
* revert cpu plugin
* gna cannot support some model
* update test case name
* skip CanCreateTwoCompiledModelsAndCheckRuntimeModel in gna
* Update src/inference/src/dev/core_impl.cpp
Co-authored-by: Chen Peter <peter.chen@intel.com>
* Update src/inference/src/dev/core_impl.cpp
Co-authored-by: Chen Peter <peter.chen@intel.com>
* replace deviceName.substr(pos + 1) with deviceNameWithoutBatch
* fix bug
* Update src/inference/src/dev/core_impl.cpp
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Update src/tests/functional/plugin/shared/include/behavior/compiled_model/compiled_model_base.hpp
Co-authored-by: River Li <river.li@intel.com>
* Update src/tests/functional/plugin/shared/include/behavior/compiled_model/compiled_model_base.hpp
Co-authored-by: River Li <river.li@intel.com>
* Update src/plugins/intel_gna/tests/functional/shared_tests_instances/skip_tests_config.cpp
Co-authored-by: River Li <river.li@intel.com>
* Update src/plugins/intel_gna/tests/functional/shared_tests_instances/skip_tests_config.cpp
Co-authored-by: River Li <river.li@intel.com>
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Co-authored-by: River Li <river.li@intel.com>
* [GPU] Optimize Condition operation by better integrating its subnetwork primitives with the main network
* Reuse main network's stream in sub-networks
* FakeConvert op init
* Update dest types names
* Update op hpp
* Update opset ops number
* Init type_prop tests
* Add attributes tests
* Add op check test
* Update namespace in fc cpp
* Update getters
* Refactor static member
* Make destination_type lower case
* Update type in test
* Move get_valid_types out of class
* Update ops number in opset
* Remove apply_scale attribute
* Additional constructor to make `shift` input optional
* [GPU] Fix acc issue for LSTMSequence w/ -1 seq_length
* add output port for multiple outputs of node
* add functional test for lstm_sequence
* Fix CI test failures
* Replace IE_THROW with OPENVINO_THROW
1. IE_THROW() is replaced by OPENVINO_THROW
2. IE_THROW(NOTIMPLEMENT) is replaced by OPENVINO_THROW_NOT_IMPLEMENT
3. IE_ASSERT is replaced by OPENVINO_ASSERT
* Minor update
* Use system model cache when running torch hub tests locally
* Update tests/model_hub_tests/torch_tests/test_torchvision_models.py
* Update tests/model_hub_tests/torch_tests/test_torchvision_models.py
* `setupvars.sh`: ignore `cd` output
Having `function cd() { builtin cd "$@" && l; }` defined in bash breaks `setupvars.sh`
* Use `builtin cd` to enable `function cd() { builtin cd "$@" && l; }`, remove wrapping `echo $()` because `pwd` already prints
* Input/output order Keras tests.
* Added precommit mark.
* Added xfail.
* Small correction.
* Check input/outputs by names in FW.
* Moved output order tests to Python API group.
* Corrected comments.
* [GPU] Support LSTMSequence w/ -1 seq_length
Co-authored-by:Taylor Yeonbok Lee <taylor.lee@intel.com>
Co-authored-by:Andrew Park <andrew.park@intel.com>
* Fix GetInputInfo to retrieve input pid from LSTMCell
* LSTMCell use ov::PartialShape instead of cldnn::tensor
* implement lstm_elt_inst::calc_output_layouts
* implement lstm_elt_impl::static_canonicalize_shapes
* Add functional tests
* Fix unit test failure
---------
Co-authored-by: Andrew Park <andrew.park@intel.com>
* [TF FE] Fix TF1 SSD PPN model conversion
It contains a case when one Merge node eliminated different conditional flows.
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add layer test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Migrate Constant operator to new API
- refactor to reduce binary size
* Fix code style
* Fix build issues
* Apply corrections after review:
- Restore mem_size calculation for bit widths >= 8
- Remove element type helpers functions
* Use float cast for floating types except f64
* Try using a custom action directly from repo
* Run smart CI under ubuntu-latest
* Set output + add a sample step
* Update linux.yml
* Add components.yml
* Add some conditions
* Just to check if reference to "needs" work in job context
* Update linux.yml
* More example cases
* Dummy change to CPU
* Fix typo
* Fix SAMPLES_AFFECTED variable
* Use more correct dependents key
* Fighting with messy GHA conditions
* No brackets and no double quotes in conditions
* Revert "Dummy change to CPU"
This reverts commit 4eae09e5b5.
* Use refactored action
* Move action implementation to openvino repo
* Extend components.yml config
* Update labeler.yml
* Dummy change to TF FE
* Fix indentation
* Add missing needs
* Add missing records
* Allow missing records for components in validation
* install_openvino_dependencies as a separate step for Python_Unit_Tests
* Improve config validation
* Revert "Dummy change to TF FE"
This reverts commit 01190864d1.
* Dummy change to model hub tests
* Update CPU component config
* Dummy change to Python API
* Dummy change to Python API
* Revert "Dummy change to Python API"
This reverts commit 3fce0bb3fb.
* Dummy change to Python API
* Simplify conditions. Cover "no components changed" case
* Update components.yml
* Update .gitignore
* Revert "Dummy change to Python API"
This reverts commit e57ea9852c.
* Fix dependencies scopes
* Add simple unit tests for smart ci functionality
* Revert "Dummy change to model hub tests"
This reverts commit c3d6837e22.
* Use ghapi module with permissive license
* Cover install_build_dependencies.sh script by labeler
* More labels
* Use ghapi. Apply review comments
* Enable dot files to be matched by labeler
* Warning instead of error in artifacts upload where smart ci is enabled
* Fix master merge
* Fix condition for TF FE common tests
* Fix condition for Pytorch FE tests
* Remove condition for pytorch model tests
* Allow any label as a component
* Refactor tests log handling
* Allow any defined label as a component
* Rearrange config structure. Fill the config with actual data
* Run full scope on changes to non-matching files
* Add missing conditions
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Added experimental ScaledDotProductAttention operation in opset12. Supported in PT FE for aten::scaled_dot_product_attention translation. Decomposed in the common optimizations as functional reference.
* Better ScaledDotProductAttention
- Moved decomposition to the decomposing transformation
- Implemented more ctors for the op
- Renamed is_causal to causal
- Shape/type inference native code instead of using decomposition
- Moved the op from opset12 to opset13
- Added Python wrapper for ScaledDotProductAttention
* Fix test that counts ops in the opsets
* Update src/core/src/op/scaled_dot_product_attention.cpp
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
* Update src/core/src/op/scaled_dot_product_attention.cpp
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
* Move ScaledDotProductAttentionDecomposition from fusions to decompositions.
* Remove not used legacy shape inference in ScaledDotProductAttention
* Better namespace usage
* Register all nodes in ScaledDotProductDecomposition for correct tracking of nodes and running next mather passes on all new nodes.
* Don't use register_new_node_
* ScaledDotProductAttention specification (with an extra scale argument)
* Code style fix
* Scale input implementation for ScaledDotProductAttention
* Handle attention_mask=0 case in the op spec
* Better description of scale input
* N->M in scale description
* Code style fix, remove debug print.
* Apply suggestions from code review
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Co-authored-by: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
* Fix for case when is_causal is not passed
* Extended description of ScaledDotProduct op
* Better description in py op wrapper
* Basic shape propagation tests for ScaledDotProductAttention
* Added ScaledDotProductAttention to toc.
* Add op impl check
---------
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Co-authored-by: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
- fix cum_sum_partial_sum kernel;
- add unit test and func test for big shapes;
- add test to compare Partial vs Ref performance;
- change kernels' priorities according to performance measurements;
- move common profiling helpers to test_utils.
Ticket: CVS-123590
* Migrate Multiply operator to new API
* Add comment explain use of custom multiply
* Update custom multiply comment
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
---------
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
* [GPU] Support dynamic tensoriterator with -1 num_iteration
- remove redundant codes
* [GPU] Refactoring methods for pre_process / post_process for body_network
* Add unit test for dynamic tensoriterator wo trip_count_id
* Follow-up code review
* Set inner network in loading of model cache
* Fix legacy loop unit tests
* [TF FE] Fix conversion of TF1 OD models out-of-the-box
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add test While with nested If operation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update tests/layer_tests/tensorflow_tests/test_tf_While.py
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* [CPU] CPU plugin migrates to plugin API 2.0
* Fix legacy config/metric issue
* Fix some issue of ov_cpu_func_tests
1. set_tensors_impl segment fault
2. ov::loaded_from_cache unsupported issue
* Resolve some comments
1. ov::loaded_from_cache issue
2. throw_if_cancelled issue
3. import_model issue
4. set_tensor_impl issue
5. batched_inference issue
* Fix dynamic shape inference issue
* Fix build error
* keep original model info in infer_request
* Fix minor error
* cache internal tensors for input/output precision change
* Disable import model test cases with precision changes
* fix precision issue
* Fix issue for import model
* Fix InferRequestCancellationTests exception issue
* Skip InferRequestIOBBlobTest.*secondCallGetInputDoNotReAllocateData due to new plugin api have different behavior
* Fix graph name issue
* Fix ROI issues
* Fix Transpose shape issue
* Skip vie::Version test due to change to ov::Version
* Solve input port name changes issue
* Solve preprocess layout issue
* Fix minor issue
* tidy up code
* Fix conflict after rebase
* Fix Windows build warning
* Add aux tensors for precision change issue
* Fix import/export model issue
* WA single layer name changed by preprocess
* Revert "WA single layer name changed by preprocess"
This reverts commit bc8fcdd43c.
* Skip some legacy tests due to plugin api 2.0 is enabled
1. skip some python legacy tests for plugin api 2.0 some different behaviors
2. skip some smoke tests due to output port name was changed
* Fix 2 build warnings
* Skip some AUTO plugin tests
* Fix property issue caused by AUTO plugin
* Skip PSROIPooling issues
* Follow header files reference policy
* Split out transformation fixing for nop_elimination
* Fix AUTO plugin mismatch issue for get_tensor function
* Fix aux tensor shape issue
* Fix tensor shape issue
* WA python sync inference sample's segmentfault issue
* Fix reshape issue for dynamic inference
* Fixed incorrect tensor name in e2e test
Fixe issue: e2e ONNX_Customized_Cascade_Rcnn_api_2_True_batch_1_device_CPU_precision_FP325den8cnk
* Fix python segmentfault issue of plugin api 2.0
* Fix python segmentfault issue of plugin api 2.0
* Revert "Fix python segmentfault issue of plugin api 2.0"
This reverts commit 6f502e5d86.
* Fix onnx_duplicated_output_name due to empty tensor
Co-authored-by: Bell, Song <bell.song@intel.com>
* Remove redundant code
* Remove python segment fault WA
* Keep rt_info to fix test failure in case of legacy public api
* Fix output port names missing issue
* Adress some reviewers' comments
* Restore OnnxBackendNodeModelTest::test_maxpool_with_argmax_2d_precomputed_pads_cpu after fixing has been merged
* Resolve tensor sharing issue when there are same name output port name
In some case, model has 2 or more same name input/output ports, they aslo have the same
precision and partial_shape. Compiled_model will share the same ov::Descriptor::Tensor pointer
and ov::Tensor between multiple such ports.
Considered solving python segment fault issue to create seperated input/output ports, which also
need handle such tensor shared case, this patch will do it.
* Resolve tensor sharing issue when there are same name output port name
In some case, model has 2 or more same name input/output ports, they aslo have the same
precision and partial_shape. Compiled_model will share the same ov::Descriptor::Tensor pointer
and ov::Tensor between multiple such ports.
Considered solving python segment fault issue to create seperated input/output ports, which also
need handle such tensor shared case, this patch will do it.
* Better method to find shrared tensor desc
* rename with snake_case style
* Remove ngraph header files
* Keep external_ptr naming
* Add OPENVINO_SUPPRESS_DEPRECATED for some legacy code
* Use port's tensor_ptr to replace creating new tensor_ptr
* Resolve some reviewer comments
* Implement ov::IInferRequestInternalWrapper::GetPreProcess to recover python GetPrepProcess tests
* Remove unnecessary header files reference
* Assert the risk of precision change and reorder at the same time
* Modify legacy python test to fit plugin api 2.0 behavior
* Recover smoke_Transpose(2|4|5|6)D/TransposeLayerTest.CompareWithRefs due to fixing is merged
* Fix typo issue
* Address reviewer's comments
* Disable precision coversion
* Fix error when CpuBlockedMemoryDesc
* Remove precision mismatch WA
* WA precision issue for query_model
* Solve precision mismatch between compiled model and graph
* Fixe failure of query_model
* Rebase to new plugin api update
* Recover the test cases of precision mismatch
* Try to fix name changing for graph model
* Remove tets code
* Remove fp64
* Rebase to new plugin api update
* Update for some failure cases
* Fix bert_benchmark failure issue
* Avoid segment fault in arm acl
Legacy public api + cpu plugin api will add convert op by preprocess by default for unsupported precision,
but ACLConvertExecutor cannot support dimension > 6, so this test will be segment fault due to dimension > 6
smoke_TestNumpyBroadcastNgraphEvaluate/BroadcastLayerTest.CompareWithRefs/targetShape=(1.2.3.4.5.6.7.8.9.10)_axesMapping=()_mode=numpy_inShape=(1.2.1.4.1.6.1.8.1.10)_inNPrec=I8_trgDev=CPU
smoke_TestNumpyBroadcastNgraphEvaluate/BroadcastLayerTest.CompareWithRefs/targetShape=(1.2.3.4.5.6.7.8.9.10)_axesMapping=()_mode=numpy_inShape=(1.2.1.4.1.6.1.8.1.10)_inNPrec=U8_trgDev=CPU
* Remove precision change from preprocess to avoid ACL unsupport convert dim > 6
* ACLConvertExecutor cannot support dimension > 6, don't let preprocess to add Convert
* Revert "ACLConvertExecutor cannot support dimension > 6, don't let preprocess to add Convert"
This reverts commit fd7a8b35af.
* Revert "Remove precision change from preprocess to avoid ACL unsupport convert dim > 6"
This reverts commit 3c2d9a5f17.
* Debug
* Debug incorrect precision checking issue
* Debug Eltwise FP64 unsupported issue
* Add logs for precision
* debug log
* Update for new dependent PRs merged
* Fix failure caused by preprocess
Fix below failures due to cannot find ops by name
smoke_LPT/ReduceMaxTransformation.CompareWithRefImpl/f32_[1,3,10,10]_CPU_f32__256*
* Fix build error
* Fix failure caused by missing code during rebase
* Add debug
* Fix precision unsupport issue
* U16/I16/U64 precision support
* Resolve the issue of f64 reorder
Fix below issue:
Cannot create reorder primitive: unsupported reorder case
* Fix convert multiple child edge issue
* Solve ROI tensor failure issues
* Temporarily disable num_nodes comparison
* Only change convert precision for fp64
* Put convert precision change before reorder to avoid confusion
* Add debug log for transformation
* Fix rebase confilict
* Fix clang issue
* Temporarily disable test_infer_mixed_values python test of bf16
* Solve issue of smoke_ConvertCPULayerTest_BOOL_Dynamic_inputPRC=BF16 choose FP32 primType rather than BP16 primType
* Fix issue of pytorch_tests/test_outer.py
There are 2 output ports, but with the same port name, they should share the same tensor.
* Fix arm cannot find Eltwise executor issue
smoke_SetBlobCPU/SetBlobTest.CompareWithRefs/Type=INPUT_Device=CPU_PrecisionInNet=FP16_PrecisionInNgraph=BOOL
will report below error:
[ GENERAL_ERROR ] Supported Eltwise executor is not found
It need change convert precision to avoid such problem.
* Fix memory overwritten issue
* Temporarily skip arm fp16 SetBlobTest
* Fix compile error after rebase
* Restore smoke_IsOp test due to fixing pr merged
* Fix float to bf16 issue in avx2 isa
* solve onnx test xfail issue
* Skip test cases that ARM Eltwise executor FP16 is not supported
smoke_SetBlobCPU/SetBlobTest.CompareWithRefs/Type=INPUT_Device=CPU_PrecisionInNet=FP16_PrecisionInNgraph=BOOL
smoke_SetBlobCPU/SetBlobTest.CompareWithRefs/Type=BOTH_Device=CPU_PrecisionInNet=FP16_PrecisionInNgraph=BOOL
[ GENERAL_ERROR ] Supported Eltwise executor is not found
* [CPU] improve reorder to support any precision
* Implement ReorderExecutor
* Fix builld error
* Not cache executor due to its primitive has been cached
* Keep convert one time at most
At most insert one convert if needed, if still cannot do reorder it will throw exception rather than insert the second convert
For example, below reorder will not be supported:
FP64<->I64/U64/U32
U32<->I64/U64
U32<->I16/U16
FP64<->FP64
BIN<->BIN
* Only do conversion if layout is same
* update for only convert case
* Update for reviewer comments
* update for failure cases
* Address reviewer comments
* Update rebase issue
* minor update
* Solve unsupported precision issue in tranfromation rather than init_edge
* Remove unnecessary convert in init_edge
* Minor changes
* Update Reorder::reorderData
* Solve issue if only coversion without reorder
* Address reviewer comments
* Address reviewer comments
* Keep exception for unsuported precision
* update
* Revert reorder executor implement
* Solve float->bool issue on transformation pipeline
* Solve I64 is not supported issues
* Solve reviewer's comments
* Fixed dynamic top_k node issue
* Skip nhwc and nChw16c test cases for ConvertLayer
* Update for reviewers' comments
* Fix some failures
* Update for several failure cases
* Update for apiConformanceTests failures
* Fix incorrect node name after import model
* update
* update comments
* Solve issue of smoke_MatMul_NoTranspose and smoke_MatMul_BothTranspose
* Fixed AlignMatMulInputRanks scalar issue
* Address reviewers' comments, remove redundant path in graph.cpp
* Remove test_div_uint8_cpu from xfail_issue_58676
* Solve invalid number of nodes for smoke_Snippets_BroadcastSelect
* ConstantResultSubgraphTest of u16/i16/u32/i64/u64
* restore smoke_SetBlobCPU BOOL tests for arm
* [CPU] Fix ARM precision issue
ARM64 ACL prefers fp16 than fp32, API 2.0 requires input/output precision not changes,
then fp32 input will trigger convert node is added to convert fp32 to fp16.
* Solve some ARM64 failures
* Fix arm64 InferRequestVariableStateTest tests out of memory issue
ARM64 will force fp16 precision, which cause states memory can be fp16, so memcpy to state_memory
cannot use float * element_size, else it will be out of memory bound.
* Skip 2 arm64 tests caused by forcing fp16 precision
* Revert "Fix arm64 InferRequestVariableStateTest tests out of memory issue"
This reverts commit 3e12bd48c2.
* Fix python test_get_profiling_info failure issue
---------
Co-authored-by: Bell, Song <bell.song@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* Remove `ngraph` from PT FE and FE tests utils
* Remove `ngraph` from Paddle FE
* Remove `InferenceEngine` from some ONNX FE test
* Port `generate_embedding.py` to API2.0
* CLangFormat
* Fix comments
* Migrate Mish operator to new API
* Remove `visit_attributes` is same as base class
* Refactor Mish reference implementation
* Add cast as function is generic
-mish calculation is floating-point but return type can be integral.
* Fix constant folding in MulMulMulFusion
by add f64 precision in Multiply to perform evaluate for const folding
* Do not transform if input has not supported type
* [TF FE] Support complex tensors
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Align output type for Real and Imag operations
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update decoding complex types
* Add support for ComplexAbs, FFT and IFFT operations
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Correct axes based on a number of inner-most dimensions
* Add layer tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update supported ops documentation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add a comment for ComplexTypeMark
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* MIgrate GridSample to new API
* Refactor GridSample to reduce binary size
- use function pointer instead std::function (simpler less code size)
- use RoundingGuard instead manual set/restore rounding mode
- move interpolate selection outside main data processing loop
* Migrate FloorMod operator to new API
* Remove `visit_attributes` is same as base class
* Restore FloorMod calculation for signed values
floating-point and integral
* Use ov:: namespace
* Drop HostTensor
* Use ov::util::make_tensor_of_max_value
instead of ngraph::get_constant_max_of_type
* Use ov::util::make_tensor_of_min_value instead of
ngraph::get_constant_min_of_type
* Refactor get_constant_min_of_type
* Extend throughput benchmark CLI parameters
* Added device name as the second CLI parameter with default CPU value
* Update samples/cpp/benchmark/throughput_benchmark/main.cpp
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
* Fix comments to review
* Modified python version
* Modified documentation
* Fix comments to review
* Fixed the comment
* Modified python doc
* Fixed device name handling in python version
* Update main.cpp
* Update throughput_benchmark.py
---------
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
* Remove functions`get_tensor_data_as for HostTensor
* Remove HostTensor support in TA
* Update doxy comments
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
---------
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
* Update list of TF formats.
* Minor correction.
* Added comment.
* Update docs/articles_en/openvino_workflow/model_preparation/Convert_Model_From_TensorFlow.md
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Model changed.
* Update docs/articles_en/openvino_workflow/model_preparation/Convert_Model_From_TensorFlow.md
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
---------
Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
* Handle Reshape's special zero in SimplifySecondInputOfReshape
SimplifySecondInputOfReshape detects ShapeOf->Gather->Concat
subgraphs on Reshape's second input and replaces ShapeOf->Gather
with a Constant with zero(s). Currently it works only with Reshapes
that have special_zero set to true, but it can work for Reshapes
with special_zero == false if non-Gather inputs to Concat are Constants
and don't contain any zero.
Ticket: CVS-123434
* fix no default output
* add platform-agnostic setup python action
* use specific version
* rm debug message, checkout action
* correct path
* add checkout of the action, correct paths
* correct path; enclose into brackets
* transfer linux pipelines to local setup-python action
* transfer pipelines
* use newer version
* account for fedora, add missing cache path
* correct name
* use 3.9 for fedora
* rm python install from fedora
* mv fetch and setup together, set pip_cache_dir
* correct order
* rm triggers
* add missing pythonpaths
* correct path
* add one more pythonpath
* add paths to ov package libs
* Revert "add paths to ov package libs"
This reverts commit a775881f3e.
* Handle Reshape in SplitSqueezeConcatFusion
Ticket: CVS-122455
* move check for squeeze/reshape
* add some comments
* review comments
* add use_shapes flag to SplitSqueezeConcatFusion
* Corrected memory consumption log, removed unused log_level info.
* Minor correction.
* Trace memory only if verbose is set.
* Use get_traced_memory().
* [TF FE] Switch off TF1 While support totally
This is a total switch off due to GPU limitation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Need additional fallback in Enter to avoid shapes problem
* Disable tests with While op
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Disable layer test for TF1 While
* Remove extra spaces
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* fix paddle load model from memory
* fix coding style
* ignore the deprecated api
* fix a istream bug; add test case
* simplify func variant_to_stream_ptr
* restore the previous impl for less memory affect
* fix memory leak
* Migrate NotEqual operator to new API
* Remove `visit_attributes` is same as base
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* Set sort_result_descending attr false for nms
* Add onnx test
* Tmp exclude for CPU
* Update test values
* Update test vals to avoid cast warning
* Fix typo
* [TF FE] Fix body graph injection, CumSum and SparseFillEmptyRows
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Do not handle non-parameters in body
* Update layer test to cover default parameter and attribute values
* Fix layer tests
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Improved warning message for BA + OpenCL case
* Update samples/cpp/benchmark_app/CMakeLists.txt
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
---------
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
* Drop HostTensor and move to ov namespace
* Style
* Optimize vector assignment
* Optimize vector assignment
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* Migrate Concat op to new API
* Move shape validation to shape_infer
* Fix getting concat axis in shape inference
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* choose Pcore to compile model for GPU plugin
* provide function to update executor config
* set callback executor to nullptr for GPU plugin
* fix code style
* fix warning
* optimize duplicate code
* set callback executor to nullptr for another gpu compile_model
* add description for new function
* add smoke test
* fix code style
* modify function definition
---------
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
* Migrate Transpose to new API
* Move shape validation to shape_infer
* Remove visit_attributes is same as base
* Correct transpose order shape check
for static shapes
- correct creation of order shape for static shape tests
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* Add static shape adapter
- Adapters holds CPU dimension which can be reference to it or vector
- Add ov::optional for holding optional result from shape inference
- Add new `infer` function in `IStaticShapeInfer`
* Temporary support of StaticShape
* Minor corrections in ShapeInferenceTA
* Migrate shape_infer to new interface version
* Replace StaticShape by adapter implementation
* Replace IShapeInferCommon by IStaticShapeInfer
* Correct code formatting
* Fix build issues
* NodeValidationFailure::create for StaticShapeRef
* Review shape inference for reshape operator
- review shape_infer implementation
- add more unit test for static and dynamic shapes
* Fix build issues
* Correct minus one dim calculation
* Fix build issues on windows
* Improve resolving special minus one
* Use NODE_SHAPE_INFER_CHECK
* Update product in/out calculations
* Temporary add ngraph header to solve build issue
* Correct minus one dim calc when static part same
* Add check for scalar input
* Remove debug message
* Fix `minus one` dynamic dimension calculation
* Fix `minus one` dynamic dimension calculation
* Fix merge issues in reshape
Minor refactor reshape evaluate
* Don't pass input label on minus one pattern
when input dimension will be modified.
Deconvolution::createDescriptor will call createDescriptorInternalDefault() to create fwd_conv_pd,
sometimes ref_convolution_fwd_t will be chosen to return its primitive_desc, but ref_convolution_fwd_t
primitive will not be created finally, then CC will not put this primitive into convolution_impl_list
in selective build stage, the final CC package will fail due to cannot create fwd_conv_pd of ref_convolution_fwd_t.
* [GPU] Fix outputs are not allocated in loop_inst
* Fill empty padding when the number of output paddings is less than num_outputs
* Fill empty data types when the number of output data types is less than num_outputs
* Modify postprocess_output_memory to set output memory without set_output_memory function
* In postprocess_output_memory, get concatenated_output_mem using input_info including output idx
* Modify gpu functional tests for dynamic loop to check multiple outputs of dynamic loop
* update postprocessing for condition
* Fix empty dimension issue for scalar value
* change code to get output paddings and output data type in primitive
* allocate memory for scalar data type with zero dimension
* Fix mismatch issue of input layout with shape and data types in body_network
* Fix output setting in post-processing
* pass bytes_count to gpu_usm params
* Fix condition gpu functional test issue
* Revert "allocate memory for scalar data type with zero dimension"
This reverts commit 2f10f3687c78406b20d52b6e37b1be2a30b4b73f.
* reinterpret one dimension memory buffer to zer dimension memor buffer to avoid zero byte memory allocation issue
* Add support for ONNX GroupNormalization
* Enable onnx compliance tests
* Add f to the test values to avoid cast warning
* Use tolerance as fp instead of bits
* Migrate Equal to new API
* Remove `visit_attributes` is same as base
* Remove i4, u4 from evaluate in Equal
reference implementation not handle binary precisions correctly
* Sync precisions in `has_evaluate` with `evaluate`
* Fix all equal check for lower bound
- make broadcast test assertion more strict
- remove deprecated functions from broadcast test
* [CPU]fix mergeTransposeAndReorder when Transpose and Reorder do opposite permutation to each other as expected, but isOptimized is false due to some reason like inPlace memory. The permuation is asked because the dnnl reorder primitive requires the source and destination tensors to have the same shape.
* add unit test
* Update src/plugins/intel_cpu/src/graph_optimizer.cpp
Co-authored-by: Maksim Kutakov <maxim.kutakov@gmail.com>
* simplify unit test
* update comments
---------
Co-authored-by: Maksim Kutakov <maxim.kutakov@gmail.com>
* build dynamic in win main; transfer win main to MSVC 2019; use toolchain for win cc
* Update windows_conditional_compilation.yml
use cmake toolchain globally in build stage
* Update windows_conditional_compilation.yml
* Update windows_conditional_compilation.yml
* use quotes
* try w/o protobuf
* do not restore cache
* return
* revert
* add missing shell
* skip Template OpImpl tests
* skip OV C API tests
* rm pr trigger
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Migrate Negative operator to new API
* Remove `visit_attributes` is same as base
* Use std::negate instead of lambda
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* Migrate slice to new API
* Remove visit_attributes, is same as base class
* Move shape checks to shape_infer
- minor refactor Slice op
* Move `get_tensors_partial_shapes` to dev API
* Correct comment
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
---------
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
* skip excessive mem alloc request in build
* update mem check function
* fix os behavior
* update mem size check location
* only dynamic shape case takes check_allocatable
* update check condition
* `RNNSequenceTest` to API2.0
* `Result` to API2.0
* `Reshape` to API2.0
* `ReorgYolo` to API2.0
* `RegionYolo` to API2.0
* Alignment fixes
* Skip more `RNNSequenceTest` cases
* Migrate Less operator to new API
* Migrate Greater operator to new API
- use less implementation in greater to reduce bin size
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* [workflows/linux] Switch to sccache and Azure Blob Storage
* Install curl
* Remove --show-config
* Add sccache to other Linux workflows
* sccache to Android, curl to riscv and CC
* Use sccache action instead of manual install
* Oops, missed sccache manual installation in two places
* Use env vars instead of hardcoded CMAKE_C(XX)_COMPILER_LAUNCHER
* Forgot one more stage in Linux CC pipeline
* Temporarily disable Blob Storage for RISC-V
For some reason sccache has no effect on build time and show 0 hits
and 0 compilation requests despite being in CMake calls
* forgot to add sccache installation to Linux CC
* Revert "Temporarily disable Blob Storage for RISC-V"
This reverts commit b528f41dad583a38b9ef93121e38044b9dccb71b.
* Missing container option for CC build
* Remove curl installation
* Remove CCACHE* variables which have no effect on sccache
* Revert sccache changes for Linux RISC-V workflow
* Add Rotation support to primitive and kernel
* Add unit tests
* Add transformation for NMSRotated
* add single-layer tests
* Fix: angle value for the same box may have its sign changed several times passing through iterations of batch and class loops.
* fix review comments
* Migrate Minimum op to new API
* Refactor evaluates to reduce binary size
- add infer_broadcast_shape, get shapes from tensors reduce OV_ASSERT
- refactor Evaluate structures to reduce binary size
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Transformation fuses Transpose on first or second MatMul's input
and sets MatMul's transpose_a/transpose_b accordingly.
TransposeMatMul is already part of SmartReshape, but it can be added
to MOCTransformations as well so native models that are don't use reshape
can benefit from that.
Ticket: CVS-118908
* Preserve partial values on mod inputs
- static values full range of integers
- intervals only if not negatives
* Fix bounds evaluate when inputs are scalars
Current implementation tries to leverage branchless approach, but it's not correct
if scale is 0. In that case - zero point can can become inf or nan and multiplication
by 0 doesn't change its value. That causes another issue - infinite or NaN zero point
cannot be optimized out later.
Ticket: CVS-122931
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
* try to fix memory leak issue
cpustreamer is released, but there are still thread id in t_stream_count_map
* fix threadlocal affect all threads
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* add comment for local() function to avoid mistaken modification
in the future
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* use custom stread id
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* fix review comments
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* fix format issue
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* create shared_ptr before assert
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
---------
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* Initial implementation of primitive, kernel selector, dummy kernel for RMS Norm
Signed-off-by: Andrew Park <andrew.park@intel.com>
* RMS ref kernel implementation with single WI
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add TC and reference func for ov_gpu_unit_tests
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add internal RMS norm op
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add transformation which fuse RMS decompsition pattern to RMS internal op
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix pattern for RMS fusion transformation
* Update rms ref kernel for optimization and additional planar format suuport
* Initial impl for optimized rms kernel excluding leftovers handling and case smaller than vector size
* Update the initial version to handle leftovers and case smaller than vector size
* Fuse pre decom and post comp reorders additionally
* Enable dynamic impl for rms again
* Revert fuse pre decomp and post comp reorders additionally
* Add subgraph TC for ov_gpu_func_tests
* decrease error margin for f32 data type
* update description
Signed-off-by: Andrew Park <andrew.park@intel.com>
* update test param for input shapes
* Apply comments
* Fix failed TC for invalid gamma element type
* Apply comments
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Update pattern that fuse post reorder together
* Apply comments
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
* [TF FE] Provide full support of TF1 Control flow and TensorArray ops
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add missed header for TensorArrayV3 op
* Temporarily disable GRU cell fusion
* Update src/common/transformations/src/transformations/common_optimizations/moc_transformations.cpp
* Fix a case when element_shape for TensorArrayV3
* Fix translator for TensorArrayCloseV3
* Update summarize graph with TensorArrayCloseV3
* Add layer tests for TensorArrayScatterV3, Close, Size, Array
* Fix output shape for Merge node
* Remove unused variable
* Fix translator for TensorArrayConcatV3
* Fix translator for TensorArrayConcatV3
* Add layer tests for TensorArrayWriteV3, Gather, and Concat
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add translator for GatherTree
* Fix TF FE unit-test for GatherTree
* Fix GatherTree translator
* Fix GatherTree translator to handle 1d end_token
* Fix undeclared parameter issue
* Fix GatherTree unit-test
* Add TensorArrayV3Replacer transformation
* Temporarily disable dangling transformation
* Recover RemoveMultiSubGraphOpDanglingParamsResults transformation
* Recover GRUCellFusion transformation
* Simplify check for GRUCellFusion transformation
* Use proper name for unit-tests
* Simplify translator for TensorArrayWriteV3
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Fix RemoveMultiSubgraphOpDanglingParamsResults transformation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Additional fix for remove_multi_subgraph_op_dangling_params
* Make static TI run a dynamic subgraph
* Dedicated SL test
* Change condition to respect stat shapes
* Adjust test to cover the code path properly
* Recover fallback for still failing case GNMT
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Maksim Kutakov <maksim.kutakov@intel.com>
* add m1 mac pipelines as a matrix parameter
* Update mac.yml
disable java_api because of macos arm64 - Java is not available on macOS arm64 runners
* Update mac.yml
added always condition for all tests
* Update mac.yml
* Update mac.yml
* Update mac.yml
* Update setup.py
temp commit
* Update tools/openvino_dev/setup.py
* use matrix for var
* add mxnet to extras only for x86_64
* skip failing tests
* use xfail for Python tests; add missing filter for transformations tests
* skip CPU func tests on x86_64 mac; skip some tests from CPU func tests on arm mac
* Update mac.yml
* skip tests on mac arm
* skip tests on darwin; apply review
* add more skips for python and c++ tests
* skip tf tests
* skip more tf tests; skip more Python UT stages
* rm alwayses, rm triggers, add nightly trigger
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Introduce WA to improve performance of find_port() method
* Add mutex
* Remove redindant lock
* Reduce the number of get_tensor_ptr calls
* Fixed typo
* Removed WAs from Hetero plugin
* Update model list and install cpu torch
* Move to hub tests
* Update tests/model_hub_tests/torch_tests/requirements.txt
* Make pytorch mainteiners owners of torch tests
* 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>
* 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>
* 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.
* Update src/frontends/pytorch/src/op/cat.cpp
* Check mask and shift values in u4 pattern. deque -> OutputVector for u4_compression_stack
* Convert to a given floating type instead of half in gptq patching. Better structured code.
* Code style fix
* Removed deque include
* Code style fixes
* Trailing space removed
* Fixed patched_forward and ts_decoder after unvalidated commits.
* Swap nibbles in u4/i4
* Better exception handling around jit.trace and gptq.patch_model
* Update src/bindings/python/src/openvino/frontend/pytorch/gptq.py
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
* Update src/bindings/python/src/openvino/frontend/pytorch/gptq.py
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
* Code style
* Revers int4 byte order
* Fixed core tests
* Fixed unguarded dynamic_cast result
Co-authored-by: Evgenya Nugmanova <eva.my.link@gmail.com>
* Fixed transformation tests
* Update src/bindings/python/src/openvino/frontend/pytorch/gptq.py
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* Prevent patching of non-gptq models
* Removed extra calling of quantized weights decompression patterns
* Better detection of supported AutoGPTQ models + more diagnostics
* Accurate diagnostics in case when aten::stack has multiple axes
---------
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
Co-authored-by: Evgenya Nugmanova <eva.my.link@gmail.com>
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* 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
* 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.
* 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
* Check for ReduceProd + SoftMax fix
* Check for ReduceProd + SoftMax fix
* Fix after moving on get_constant_max_of_type
* Extended tests and added coverage for other types
* Code optimization
* [GPU] Fixed data generation for f16 fusion tests
* [GPU] Temporary tolerance increase for failed tests on iGPU
* [GPU] Temporary skip or tolerance increase for failed tests on dGPU
* Enable device properties setting via AUTO plugin.
* Update.
* Update.
* Update.
* Update.
* Update.
* Update.
* Update docs/OV_Runtime_UG/auto_device_selection.md
Co-authored-by: yanlan song <bell.song@intel.com>
* Add for stateful model
* Fix the link
---------
Co-authored-by: yanlan song <bell.song@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* Add group_normalization_kernel_selector
* Define group_normalization GPU primitive and its instantiation
* Add GroupNormalization operation builder
* Add test class for GroupNormalization operator
* Add instantiation of GroupNormalization test for GPU Plugin
* Disable GroupNormalizationDecomposition transformation in GPU Plugin
* Add GroupNormalizationKernelRef implementation
* Add GroupNormalization unit tests which cover blocked layout support
* [GPU] enable dynamic loop
- support multiple outputs
- support dynamic loop memory allocation
- support negative num_iterations
- implement calc_output_layouts
- add dynamic loop functional / unit tests
* Fix fail to check memory to set when original 1d data
- follow up code reviews
* Fix unit test failures
* Follow up code review
* Modify concat memory map creation process
* Check whether or not first input of loop is num_iteration_id
* Follow up code review
- refactoring preprocess_backedge_memory
* * Fix ci failures
* Clear custom_outputs_vec for condition
* Add num_outputs for condition and loop
* *Fix constant and param of body network have mismatched layouts
* Set consts.needsBatchInterpretation for const
* * refactoring is_dynamic in loop_inst::execute
* * remove wait_for_events in body_network execution loop
* * Remove redundant events
* * follow-up code review - modify OPENVNO_ASSERT
* * Remove redundant codes in loop_inst::execute
* * add current iteration update nodes into the ov::Model
* * rollback some codes for the performance degradation
* Migrate TopK to new API
* Refactor compare_max for TopK
* Unify check of k for const and non-const input
* Update src/core/include/openvino/op/util/evaluate_helpers.hpp
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
* Move `get_tensors_partial_shapes` to dev API
---------
Co-authored-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
* Refactor shape_size util to reduce bin size
* Make `check_new_args_count` non-template function
* Use as not template check_new_args_count
in multi-nominal
* Migrated all subgraph tests after quantization graphs
* Fixed skip tests config
* Add alias for NPU
* Try to fix NPU
* Remove unsupported precisions
* Remove GNA test
* Remove more tests
* Use precise op version - Parameter
* Use precise op version - Constant
* Use precise op version - Result
* Use precise op version - Add, Concat, Subtract
* Use precise op version - NMS
* Use precise op version - TopK, Broadcast
* Use precise op version
* Include openvino headers in quotes
* Use precise op version - LSTMCell
* Fix code style
* [TF FE] Support TF 2.14 and add OnesLike translator
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Update tests constraints
* Update open_model_zoo
* Adopt TF Lite test to 2.14 TF
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Support TF Lite layer tests for diffrent TF versions
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* only skip test if mac
* unskip
* unskip trigger
* skip for onnx fe as well
* do not skip
* return skips and unskip test_backend in Python API 1.0
* rm pr trigger
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* skip gna-related tests on mac; rm unused in pipelines
* rm unused env var
* use if instead of commenting out
* add name
* return pr trigger
* rm pr trigger
* enable eltwise skip test
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* enable skipped test of onehot
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* remove shapeof OD test. cpu node shape_of don't support it
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* enable skipped test case of strideslice
remove default stride test
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* enable skipped test case of matmul
remove some test cases, custom matmul only support some rank
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* fix eltwise autob issue
powerstatic don't get the autob attibute from origin op
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* Revert "fix eltwise autob issue"
This reverts commit 1139296411.
* Revert "enable eltwise skip test"
This reverts commit c9f0a6f225.
* disable eltwise none autob test
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* add error message for OPENVINO_ASSERT
go NgraphShapeInfer branch in matmul node
when input0 rank is not equal to input1 rank
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* create ticket for EltwiseShapeInfer and skip the test case
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* revert test case order in matmul
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
---------
Signed-off-by: HU Yuan2 <yuan2.hu@intel.com>
* add new operations as unary
* get unary as input(0) instead of iterating pattern map
* add CumSum + unit tests
* add Tile + unit tests
* add tile
* fix ts_tile
* code review fix: use ADD_MATCHER
* fix bug CI tests
* Optimize CompressQuantizeWeights transformation
- remove CoordinateTransform usage from FakeQuantize reference implementation
- move ZeroPointOptimizer functionality inside CompressQuantizeWeights
- compute scale and zero point in the same loop
Ticket: CVS-119273
* review comments
* clang format
* fix comments
* Do not normalize negative indices for Gather v8
* code style fix
* added transformation test with accuracy check for Gather-v8
* removed GatherNegativeConstIndicesNormalize transformation at all
* ConvertGather8ToGather7 conversion: added more checks
* Introduced shared Gather8withIndicesDataLayerTest: added CPU, GPU instances
* code style fix
* small fix
* review fixes
* do negative indices normalization if possible
* code style fix
* refactor cpu test instances
* code style fix
* add test data for SRF on Linux
* update cpu map detection for Ecore only platform
* update test data for smoke test of streams generation
* update test data
* [GPU] oneDNN3.3 integration.
* Supports new formats from oneDNN3.3 requires.
* Fix Perf regression because of the wrong mvn kernel selection issue.
modnet_webcam_portrait_matting.int8
person-reidentification-retail-0248.int8
* support undefined onednn tag for using any tag instead.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Merge opt_kernel into reference
* Remove get_default_order
* Use ov:: in jit generators
* Remove unused template function
* Add reshape parameter for consistency with Op spec
* Add brief description and such
* Remove unused param from reshape ref
* Use C++ casting
* Remove ngraph namespace from operations without namespace
* Try to fix build
* Additional fixes
* More fixes
* More fixs
* Fix reverse op
* Fixed tests
* Throw an exception if somebody tries to reallocate tensor
* Revert "Throw an exception if somebody tries to reallocate tensor"
This reverts commit 8e06d6d576.
* Remove python test
* Revert "Remove python test"
This reverts commit 37b12148d3.
* Changed evaluate model behavior
* check dirs
* cmake, build, instlll
* use make
* use build dir
* use target
* add missing
* execute conformance tests
* correct path for requirements
* setupvars
* add API conformance
* conformance as a separate job; install all necessary files
* uncomment
* merge
* install deps
* use matrix, upload expected failures to gh cache
* use 8-core
* use the same paths
* uncomment
* comment
* change
* use csv
* add exit if there are failed tests
* always upload logs
* check dir
* use another dir for expected_failures
* upload always
* rm
* new key
* rm unused
* change
* update
* update
* rm unused
* do not exit if update is set
* copy file
* do not fail in failures check
* use specific branch
* run clean
* add expected failures
* uncomment
* comment out
* correctly add failed tests to fix_priority; check for unexpected failures in case of an update
* use azure runners for conformance
* use 4-core
* uncomment
* comment out
* split deps installation
* add missing deps for setup-python
* print error
* install certs
* do not verify ssl
* add ca-certificates install
* uncomment
* comment
* pack artifacts, rm unused deps
* rm unused dep
* always pack artifacts
* rm for func tests
* use less cores
* use var
* store int
* do not exit if non-zero code
* only 4 core
* use gh runner
* use sudo
* add missing sudo
* use expected failures
* uncomment
* comment
* create fresh expected failures
* use expected failures
* use specific ref and repo
* use expected failures
* uncomment
* comment out
* check caches
* fix str
* rm unused
* restore by restore key
* create dir
* use array
* use diff path
* mv after each download
* add sleeping and more logs
* add saving of hash table
* change
* uncomment
* comment
* download cache entries
* check dir
* use better dir
* uncomment
* rm unused
* add skip configs
* update lists
* rm unused dir; add docs
* rm unused
* rm hardcoded repo ref
* rm unused options; use better name for job
* rm unnecessary dir creation
* GPU primitive and kernel changes to support ScatterElementsUpdate-12
* Add single-layer test for ScatterElementsUpdate-12
* Unit tests:
- fix formats test - add separate data type for indices;
- add tests for Reduction.
* add pipeline
* rm triggers
* address comments
* use uninteractive as env
* rm triggers
* rm unused testdata
* use better concurrency group
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
* use aks runner
* correct path
* provide path
* add missing cmake options; rm unnecessary dir creation
* use image from private docker
* split OV and plugin cmake & build; do not fail on warning for plugin build
* use different build_dir for nvidia plugin
* add missing options
* rm unnecessary options; add target for build
* Apply suggestions from code review
try fix for NVIDIA plugin
* Apply suggestions from code review
revert to default contrib repo, used ccache for CUDA files
---------
Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* [GPU] Added more debug print for prepare input/output
Skip enqueuemempcy for zero count tensor
* Fix mem alloc limitation
* Simplify memory check condition
* Fix not to wait for null event
* Additional fixes
- apply review comments (disable 0 size memcpy for other mem types) && return user event instead of nullptr
- fixd get_max_memory to return cpu memory instead of global memorysize (Because in windows, max_global_memory returns shared gpu memory instead of physical memory size)
* Fixed functest failure
* [C API] support string size for char pointer
* rename function name
* Add deprecated flag
* Add macro to ignore deprecated
* Fix build error in windows
---------
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
* [TF FE] Support TF1 While Control flow
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply code-style fix
* Update API for OpPlace to store back edge
* Fix build: no rvalue by reference passing
* Fix build issue: correct type
* Fix TF FE unit-tests
* Apply code-review feedback: remove unused vars
* Fix fusing complicated case of TF1 While
* Remove unused variable
* Update MO unit test
* Fix layer tests for While
* Handle Switch and NextIteration nodes connected directly
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Migrate ReduceL1, ReduceL2 to new API
- add some new utils which are deprecated
* Hide helper functions from public API
* Migrate reductions ops to new API
* Migrate get_constant_from_source to dev API
* Rename ref max to reduce_max
* Rename ref min to reduce_min
* Rename ref mean to reduce_mean
* Rename ref sum to reduce_sum
* Rename ref product to reduce_prod
- minor optimization in ReduceProd operator
* Restore custom isfinite for ov float types
* Fix type name in reduce_max.hpp
* Add missing include in shape_util.hpp
* Make count same type as data type in reduce mean
* Correct reduce sum doxy comment
* [Hub Tests] Move Hub tests to self-host runners
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Not all directories possible to clean up
* Move Hub models tests to AKS nodes
* Add install actions python setup
* Add ca-certificate deps to install
* Fix bug for PT models
* Update .github/workflows/linux.yml
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Update .github/workflows/linux.yml
* Revert changes for PT models tests
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Install correct version of OV
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* fix compilation issue on Windows arm64
* fix build issue
* fix build issue
* disable clang compiler for Windows on ARM
* disable clang compiler for cpu plugin
* Update CMakeLists.txt
removed fatal_error from cpu cmake
* Update features.cmake
disable Intel CPU plugin by default on Windows ARM64 with clangl-cl compiler
* update comments
* fix build issue
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* [transformations] WeightsDequantizeToFakeQuantize: Extend pattern matching with the case when both Subtract inputs are Convert
* [transformations] WeightsDequantizeToFakeQuantize: Added new tests to cover the extention added to pattern match
* Fix review comments
* Use FindPython3.cmake
* Fixed compilation on macOS 14 with new core development tools
* Try to use Python3_SOABI instead of PYTHON_MODULE_EXTENSION
* Use Development.Module
* Keep specifying only Python3_EXECUTABLE
* Print PYTHON_MODULE_EXTENSION
* Added check for minimal cmake version for python API
* Returned Python3_INCLUDE_DIR for cross-compilation case
* Try to allow cmake older than 3.18
* Use build python interpreter to check cython dependency
* revert changes in .ci/openvino-onnx/Dockerfile
* removed unused code
* Fixed issue with variables scope
* Experiment: remove include dirs
* Corrected docs
* Use pybind11 function to set extension
* Revert "Experiment: remove include dirs"
This reverts commit 6f7f90211c.
* Refactor ConvolutionBackpropDataLayerTest, ConvolutionLayerTest, DeformableConvolutionLayerTest (#19810)
* Refactor ConvolutionBackpropDataLayerTest
* Refactor ConvolutionLayerTest
* Refactor DeformableConvolutionLayerTest
* Apply comments
* Apply comments
* Fix
* Updated minimum cmake version for Windows
* Simplified check
* Removed useless message status
* Use puiblic option
---------
Co-authored-by: Oleg Pipikin <oleg.pipikin@intel.com>
* Add EnableShapeOfConstantFolding transformation
Transpose sinking (that is used in TF frontend) disables ShapeOf constant folding
which prevents some optimizations further in the pipeline.
This patch introduces EnableShapeOfConstantFolding that removes DisableConstantFolding
from ShapeOf nodes.
Ticket: CVS-118890
* add description
* review comments
* headers
* Added support of shapes and types from paddle, torch and tf.
* Removed changes from requirements.
* Corrected test.
* Moved helper methods to utils.
* Separated tests by frameworks.
* Removed changes from complex_params test.
* Refactored Linix GHA pipeline
* Move ONNX tests to Unit
* Install tests together with openvino
* Added checks for GNA usage in docs python snippets
* Install openssl for working pip
* Disabled onnx_dyn_shapes_expand_1_dyn_shape ONNX test
* exclude dyn shapes from onnx
* Migrated samples tests
* Fixed ONNX tests
* caches for PT tests dependencies
* Build Contrib separately from main OpenVINO
* More fixes
* Added python install for samples stage
* Installed manifests for ONNX FE tests
* Try to avoid libgl1 dependency in tests
* Clean-up
* Fixed issue with manifests in ONNX tests
* Try to build debian packages in GHA
* Fixed debian packages build for multi-config generators
* changed unit tests
* add unit tests; fixed
* code review fixes
* remove debugging
* remove debug code
* add tests to ov_cpu_func_tests
* add negative padding tests to ov_gpu_func_tests
* code review fixes: change point to check positive indexes; check Pad mode in the list of currently supported
* code review fix: move check in canBeTransformed
* [TEMPLATE] Disable ReferenceTopKTest topk_min/max_sort_none on MacOs
* Apply suggestions from code review
disabled tests only for macOS x86_64, because they pass on Apple M1 / M2
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Refactored Linix GHA pipeline
* Move ONNX tests to Unit
* Install tests together with openvino
* Added checks for GNA usage in docs python snippets
* Install openssl for working pip
* Disabled onnx_dyn_shapes_expand_1_dyn_shape ONNX test
* exclude dyn shapes from onnx
* Migrated samples tests
* Fixed ONNX tests
* caches for PT tests dependencies
* Build Contrib separately from main OpenVINO
* More fixes
* Added python install for samples stage
* Installed manifests for ONNX FE tests
* Try to avoid libgl1 dependency in tests
* Clean-up
* Fixed issue with manifests in ONNX tests
* Migrate ops evaluate
* Remove using ngraph and std from ops
* Use OPENVINO_ASSERT instead of NGRAPH_CHECK
* Move `shape_util.hpp` to `dev_api/openvino/core/`
* Remove visit_attributes, same as base impl
* Fix build issues
* Fix build issues
* [workflows/liux] Trying AKS runners
* Remove sudo usages
* Fix repositories path
* Well, adding debug output
* execution bit?
* more debug output
* using bash...
* We should use shell syntax for env variables in 'run' sections
* again, may be we should use bash...
* fix cloning path for openvino repo
* more debug output
* Trying to populate WORKSPACE var in other way
* Trying different WORKSPACE
* export ALL variables for samples tests
* Trying to put openvino build into correct directory
* Replace more occurences of BUILD_DIR...
* Use shell expansion instead of Actions syntax in run steps
* Skip unit test failures
* Oops, there's no pytest for MO unit tests
* Oops, typo
* Fix LAYER_TESTS_INSTALL_DIR variable expansion
* Fix LAYER_TESTS_INSTALL_DIR for new stages
* Replace all the varibles
* Comment out CCACHE_DIR
I want to test worst-case scenario
* Comment setup ccache step
* Revert "Comment out CCACHE_DIR"
This reverts commit 046663a9f1.
* Just checking something
* Update with new stages from master
* One more stage to fix
* Fix INSTALL_DIR again (new stages were merged to master?)
* Remove concurrency limit (for test purposes)
* Trigger one more pipeline
* Disable concurrency settings
* Trigger another build
* Disable ccache (for testing purposes)
* trigger another build to measure duration without ccache
* And one more test commit
* Return back ccache
* Testing new image
* Enable concurrency back
* Using new image
* And another image
* Trying build on the clean image
* Install git
Upstream ubuntu image doesn't have git
* Oops, forgot apt-get update
* Upstream Ubuntu image, but using ACR cache
* Remove debug output
* Use Ubuntu image from ACR cache for the rest of the stages
* Display version of ccache
* Swith to ubuntu 20 temporarily (I hope)
* Set CCACHE_TEMP_DIR outside of shared space
* Revert "Swith to ubuntu 20 temporarily (I hope)"
This reverts commit 2e53109d83.
* trying ccche nohardlink option
* Trying to disable ccache file cloning
* fix CCACHE_TEMPDIR
* Install git to Python unit tests stage
* Install libsnappy-dev as tests require it
* Install python to test stage
* Fix env vars syntax in few places
* Update docker image name
* Increase timeout for CPU tests
* Debug output - trying to find out what's wrong with test reports
* Change file name in debug-output 'find' command
* let's try shell syntax for upload artifact action...
It most likely won't work but I see strange output in the logs:
Error: No files were found with the provided path: /__w/openvino/openvino/install/tests/TEST*.xml
/runner/_work/openvino/openvino/install/tests/logs/failed/*.log
/runner/_work/openvino/openvino/install/tests/logs/crashed/*.log
/runner/_work/openvino/openvino/install/tests/logs/hanged/*.log
/runner/_work/openvino/openvino/install/tests/logs/interapted/*.log
/runner/_work/openvino/openvino/install/tests/logs/disabled_tests.log. No
artifacts will be uploaded.
So the first path is translated to the path inside the container
correctly and the rest are not O_o
* Revert "let's try shell syntax for upload artifact action..."
This reverts commit eb19b4f319.
* Leave just disabled_tests.log (as it is the only one present)
* Use my own directory instead of github.workspace
Inside-container path translation doesn't work for upload-artifact
actions (it works only for the first path, but not for the rest)
* Revert "Leave just disabled_tests.log (as it is the only one present)"
This reverts commit 4321827880.
* Okay, let's try hardcoded workspace path...
* Okay, path should be inside "official" workspace. Hardcode it
* Missed some variables, replace github.workspace to hard-coded value
* Remove debug output 'find' command
* Remove old-style cache setup
* Clean ccache stats after cmake
* Change docker image to the one with non-root user
* Oops, switch to Ubuntu 20
* Playing with concurrency group name
* Oops, forgot sudo for ninja installation
* Revert "Oops, forgot sudo for ninja installation"
This reverts commit a7e1730279.
* Revert "Oops, switch to Ubuntu 20"
This reverts commit 19fe75f4af.
* Revert "Change docker image to the one with non-root user"
This reverts commit 553116492d.
* Use Ubuntu 20 DockerHub image
* Trying to force apt-get packages not to wait for user input
* Make DEBIAN_FRONTED for all stages
* Update reason of skipped MO unit test
* Add DEBIAN_FRONTED to all jobs
* Fix environment variables expansion in newly-added stages
* Update .github/workflows/linux.yml
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Update .github/workflows/linux.yml
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Fix review comments
* More review comment fixes
* Remove DEBIAN_FRONTEND from Python Models job
* "Get tools versions" step is absent on master
---------
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* add cpu pinning on windows
* remove pinning limitation on windows
* only support the machine with one numa node
* fix code style
* fix build error on macos
* set mask initial value
* fix test failure on window
* fix build failure on macos, add limitation on windows machine with two sockets
* fix test failure on windows
* fix test failure
* fix comments
* [OVC] do not parse inputs
* fix unit-tests
* remove redundant lines, add test case
* add one more unit-test
* skip None values
* replace str with List in test_mo_import_from_memory
* corrected type hints, added a safety assert
OV_PYTHON_VERSION:3.11.2# Full version of Python its required for LD_LIBRARY_PATH. More details https://github.com/microsoft/azure-pipelines-tool-lib/blob/master/docs/overview.md#tool-cache
steps:
- task:UsePythonVersion@0
inputs:
versionSpec:'$(OV_PYTHON_VERSION)'# Setting only major & minor version will download latest release from GH repo example 3.10 will be 3.10.10.
OV_PYTHON_VERSION:3.11.2# Full version of Python its required for LD_LIBRARY_PATH. More details https://github.com/microsoft/azure-pipelines-tool-lib/blob/master/docs/overview.md#tool-cache
steps:
- task:UsePythonVersion@0
inputs:
versionSpec:'$(OV_PYTHON_VERSION)'# Setting only major & minor version will download latest release from GH repo example 3.10 will be 3.10.10.
OV_PYTHON_VERSION:$(OV_PYTHON_VERSION_MAJOR_MINOR).2# Full version of Python its required for LD_LIBRARY_PATH. More details https://github.com/microsoft/azure-pipelines-tool-lib/blob/master/docs/overview.md#tool-cache
steps:
- task:UsePythonVersion@0
inputs:
versionSpec:'$(OV_PYTHON_VERSION)'# Setting only major & minor version will download latest release from GH repo example 3.10 will be 3.10.10.
OV_PYTHON_VERSION:3.11.2# Full version of Python its required for LD_LIBRARY_PATH. More details https://github.com/microsoft/azure-pipelines-tool-lib/blob/master/docs/overview.md#tool-cache
steps:
- task:UsePythonVersion@0
inputs:
versionSpec:'$(OV_PYTHON_VERSION)'# Setting only major & minor version will download latest release from GH repo example 3.10 will be 3.10.10.
OV_PYTHON_VERSION:3.11.2# Full version of Python its required for LD_LIBRARY_PATH. More details https://github.com/microsoft/azure-pipelines-tool-lib/blob/master/docs/overview.md#tool-cache
steps:
- task:UsePythonVersion@0
inputs:
versionSpec:'$(OV_PYTHON_VERSION)'# Setting only major & minor version will download latest release from GH repo example 3.10 will be 3.10.10.
message:Thank you for looking into this issue! Please let us know if you have any questions or require any help.
issueCurrentlyAssignedMessage:Thanks for being interested in this issue. It looks like this ticket is already assigned to a contributor. Please communicate with the assigned contributor to confirm the status of the issue.
OpenVINO™ is always looking for opportunities to improve and your contributions
play a big role in this process. There are several ways you can make the
product better:
product better.
# Table of Contents
1. [Forms of contribution](#Forms-of-contribution)
2. [Technical guide](#Technical-guide)
## Forms of contribution
### Provide Feedback
@@ -32,7 +38,7 @@ product better:
If you want to help improving OpenVINO, choose one of the issues reported in
[GitHub Issue Tracker](https://github.com/openvinotoolkit/openvino/issues) and
[create a Pull Request](./CONTRIBUTING_PR.md) addressing it. Consider one of the
tasks listed as [first-time contributions](https://github.com/openvinotoolkit/openvino/issues/17502).
tasks listed as [first-time contributions](https://github.com/orgs/openvinotoolkit/projects/3).
If the feature you want to develop is more complex or not well defined by the reporter,
it is always a good idea to [discuss it](https://github.com/openvinotoolkit/openvino/discussions)
with OpenVINO developers first. Before creating a new PR, check if nobody is already
@@ -81,6 +87,66 @@ product better:
share your expertise with the community. Check GitHub Discussions and
Issues to see if you can help someone.
## Technical guide
This section lists all the necessary steps required to set up your environment, build OpenVINO locally, and run tests for specific components. It's a perfect place to start when you have just picked a Good First Issue and are wondering how to start working on it.
Keep in mind that we are here to help - **do not hesitate to ask the development team if something is not clear**. Such questions allow us to keep improving our documentation.
### 1. Prerequisites
You can start with the following links:
- [What is OpenVINO?](https://github.com/openvinotoolkit/openvino#what-is-openvino-toolkit)
- [Blog post on contributing to OpenVINO](https://medium.com/openvino-toolkit/how-to-contribute-to-an-ai-open-source-project-c741f48e009e)
- [Pick up a Good First Issue](https://github.com/orgs/openvinotoolkit/projects/3)
### 2. Building the project
In order to build the project, follow the [build instructions for your specific OS](https://github.com/openvinotoolkit/openvino/blob/master/docs/dev/build.md).
### 3. Familiarize yourself with the component you'll be working with
Choose the component your Good First Issue is related to. You can run tests to make sure it works correctly.
Use the issue description and locally built OpenVINO to complete the task. Remember that you can always ask users tagged in the "Contact points" section for help!
We'll make sure to review your Pull Request as soon as possible and provide you with our feedback. You can expect a merge once your changes are validated with automatic tests and approved by maintainers.
@@ -33,7 +33,7 @@ OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference.
- Reduce resource demands and efficiently deploy on a range of Intel® platforms from edge to cloud
This open-source version includes several components: namely [Model Optimizer], [OpenVINO™ Runtime], [Post-Training Optimization Tool], as well as CPU, GPU, GNA, multi device and heterogeneous plugins to accelerate deep learning inference on Intel® CPUs and Intel® Processor Graphics.
This open-source version includes several components: namely [OpenVINO Model Converter (OVC)], [OpenVINO™ Runtime], as well as CPU, GPU, GNA, multi device and heterogeneous plugins to accelerate deep learning inference on Intel® CPUs and Intel® Processor Graphics.
It supports pre-trained models from [Open Model Zoo], along with 100+ open
source and public models in popular formats such as TensorFlow, ONNX, PaddlePaddle, MXNet, Caffe, Kaldi.
@@ -48,8 +48,7 @@ source and public models in popular formats such as TensorFlow, ONNX, PaddlePadd
* [python](./src/bindings/python) - Python API for OpenVINO™ Runtime
* [Plugins](./src/plugins) - contains OpenVINO plugins which are maintained in open-source by the OpenVINO team. For more information, take a look at the [list of supported devices](#supported-hardware-matrix).
* [Frontends](./src/frontends) - contains available OpenVINO frontends that allow reading models from the native framework format.
* [Model Optimizer] - is a cross-platform command-line tool that facilitates the transition between training and deployment environments, performs static model analysis, and adjusts deep learning models for optimal execution on end-point target devices.
* [Post-Training Optimization Tool] - is designed to accelerate the inference of deep learning models by applying special methods without model retraining or fine-tuning, for example, post-training 8-bit quantization.
* [OpenVINO Model Converter (OVC)] - is a cross-platform command-line tool that facilitates the transition between training and deployment environments, and adjusts deep learning models for optimal execution on end-point target devices.
* [Samples] - applications in C, C++ and Python languages that show basic OpenVINO use cases.
## Supported Hardware matrix
@@ -62,30 +61,30 @@ The OpenVINO™ Runtime can infer models on different hardware devices. This sec
<td>Auto batch plugin performs on-the-fly automatic batching (i.e. grouping inference requests together) to improve device utilization, with no programming effort from the user</td>
<td>Multi plugin enables simultaneous inference of the same model on several devices in parallel</td>
</tr>
@@ -129,6 +128,16 @@ OpenVINO™ Toolkit also contains several plugins which simplify loading models
OpenVINO™ Toolkit is licensed under [Apache License Version 2.0](LICENSE).
By contributing to the project, you agree to the license and copyright terms therein and release your contribution under these terms.
## Telemetry
OpenVINO™ collects software performance and usage data for the purpose of improving OpenVINO™ tools. This data is collected directly by OpenVINO™ or through the use of Google Analytics 4.
You can opt-out at any time by running the command:
``` bash
opt_in_out --opt_out
```
More Information is available at https://docs.openvino.ai/latest/openvino_docs_telemetry_information.html.
## Documentation
### User documentation
@@ -155,9 +164,9 @@ The list of OpenVINO tutorials:
## System requirements
The system requirements vary depending on platform and are available on dedicated pages:
- Broader model and hardware support - Optimize & deploy with ease across an expanded range of deep learning models including NLP, and access AI acceleration across an expanded range of hardware.
- NEW: Support for Intel 13th Gen Core Processor for desktop (code named Raptor Lake).
- NEW: Preview support for Intel’s discrete graphics cards, Intel® Data Center GPU Flex Series and Intel® Arc™ GPU for DL inferencing workloads in intelligent cloud, edge and media analytics workloads. Hundreds of models enabled.
@@ -18,6 +18,6 @@
- NEW: Introducing new performance hint (”Cumulative throughput”) in AUTO device, enabling multiple accelerators (e.g. multiple GPUs) to be used at once to maximize inferencing performance.
- NEW: Introducing Intel® FPGA AI Suite support which enables real-time, low-latency, and low-power deep learning inference in this easy-to-use package
ie_dependent_option(ENABLE_SYSTEM_TBB"Enables use of system TBB"${ENABLE_SYSTEM_TBB_DEFAULT}
ov_dependent_option(ENABLE_SYSTEM_TBB"Enables use of system TBB"${ENABLE_SYSTEM_TBB_DEFAULT}
"THREADING MATCHES TBB"OFF)
# TODO: turn it off by default during the work on cross-os distribution, because pugixml is not
# available out of box on all systems (like RHEL, UBI)
ie_option(ENABLE_SYSTEM_PUGIXML"Enables use of system PugiXML"${ENABLE_SYSTEM_PUGIXML_DEFAULT})
ov_option(ENABLE_SYSTEM_PUGIXML"Enables use of system PugiXML"OFF)
# the option is on by default, because we use only flatc compiler and don't use any libraries
ie_dependent_option(ENABLE_SYSTEM_FLATBUFFERS"Enables use of system flatbuffers"${ENABLE_SYSTEM_FLATBUFFERS_DEFAULT}
ov_dependent_option(ENABLE_SYSTEM_FLATBUFFERS"Enables use of system flatbuffers"${ENABLE_SYSTEM_FLATBUFFERS_DEFAULT}
"ENABLE_OV_TF_LITE_FRONTEND"OFF)
ie_dependent_option(ENABLE_SYSTEM_OPENCL"Enables use of system OpenCL"${ENABLE_SYSTEM_LIBS_DEFAULT}
ov_dependent_option(ENABLE_SYSTEM_OPENCL"Enables use of system OpenCL"${ENABLE_SYSTEM_LIBS_DEFAULT}
"ENABLE_INTEL_GPU"OFF)
# the option is turned off by default, because we compile our own static version of protobuf
# with LTO and -fPIC options, while system one does not have such flags
ie_dependent_option(ENABLE_SYSTEM_PROTOBUF"Enables use of system Protobuf"OFF
ov_dependent_option(ENABLE_SYSTEM_PROTOBUF"Enables use of system Protobuf"OFF
"ENABLE_OV_ONNX_FRONTEND OR ENABLE_OV_PADDLE_FRONTEND OR ENABLE_OV_TF_FRONTEND"OFF)
# the option is turned off by default, because we don't want to have a dependency on libsnappy.so
ie_dependent_option(ENABLE_SYSTEM_SNAPPY"Enables use of system version of Snappy"OFF
ov_dependent_option(ENABLE_SYSTEM_SNAPPY"Enables use of system version of Snappy"OFF
"ENABLE_SNAPPY_COMPRESSION"OFF)
ie_dependent_option(ENABLE_PYTHON_PACKAGING"Enables packaging of Python API in APT / YUM"OFF
ov_dependent_option(ENABLE_PYTHON_PACKAGING"Enables packaging of Python API in APT / YUM"OFF
"ENABLE_PYTHON;UNIX"OFF)
ie_option(ENABLE_OPENVINO_DEBUG"Enable output for OPENVINO_DEBUG statements"OFF)
ov_option(ENABLE_OPENVINO_DEBUG"Enable output for OPENVINO_DEBUG statements"OFF)
if(NOTBUILD_SHARED_LIBSANDENABLE_OV_TF_FRONTEND)
set(FORCE_FRONTENDS_USE_PROTOBUFON)
@@ -196,4 +207,4 @@ if (ENABLE_PROFILING_RAW)
add_definitions(-DENABLE_PROFILING_RAW=1)
endif()
print_enabled_features()
ov_print_enabled_features()
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.