* Disable set_property() to support ov::device::properties setting.
* Update benchmark APP to set device properties through compile_model() instead of through set_property().
* Update.
* Update.
* Update some test case including ov::device::properties setting via core.ser_property().
* Since core.set_property() didn't support ov::device::properties setting, just remove the test case to check compile_model() works well if setting ov::device::properties via core.set_property() first.
* Update CompileModel in test name to CompiledModel
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* Add corresponding test case.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
* Update.
* Remove the changes of this commit as this modification has nothing to do
with this PR.
This reverts commit 4f04b9f085.
---------
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* add test case for device_bind_buffer
* Correct path to header file properties.hpp
* rename remote blob testcase with multi
* add test case for remote blob and device bind buffer
* add logs for debug
* disable test case RemoteBlobInitializedWithoutGPU
* add property for remote blob test case
* remove debug logs for bind_multi_schedule.cpp
* fix MultiDeviceMultipleGPU_Test fail
* add test case for oversubsciption of infer requests
* get optimal number to create inferRequests
* using macro ENABLE_INTEL_CPU to make sure tests need CPU
* fix the issue that canCreateRemoteTensorThenInferWithAffinity test case fails to run
* remove ov::hint::PerformanceMode::UNDEFINED from MultiDeviceMultipleGPU_Test
* add test case for get perf_hint from GetMetric
* Increase Mock GetMetric test sleep time
* add mock test case for getMetric
* add new test case OVAutoExecutableNetworkTest
* convert ov::Any to ov::hint::Priority
* resolve conflict of get_metric.hpp
* add macro ENABLE_INTEL_CPU for gpu test case and fix cases not getting instantiated for cpu test
* fix the issue of running Mock GetMetric test cases fail
* add perf_hint test cases to properties_tests.cpp
* Modify the logic of judging whether it is a single device in ctput mode
* Enable AUTO compiledModel::get_property supporting its properties only.
* Update.
* Update.
* Update some releated test cases.
* Update.
* Update related test case.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
---------
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* Provide ENABLE_STARTUP_FALLBACK property to enable/disable CPU as acceleration
* Add more test cases to ENABLE_STARTUP_FALLBACK property
* Remove unnecessary config
* Remove plugin.hpp
* Update test case by PR#14754
* Update copyright
Co-authored-by: River Li <river.li@intel.com>
* Simplify using namespace
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
Co-authored-by: River Li <river.li@intel.com>
* [TF FE] Optimize DynamicPartition translator
It avoid squared complexity to compute split lengths for each partition
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* WA a bug in Unique operation: not use axis
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Review interval shape and labels propagation
* Review shape infer template implementation
- add test for default ctor
* Add evaluate upper, lower and label
- add new default label evaluator which propagates labels
from inputs list
* default_label_evaluator for 0 input only is wrapper for
generic evaluator implementation
* Use default_label_evaluator in ScatterUpdate
* Fix build issues
* [GPU] Fix a bug of permute optimization
For int8 models, if there is FakeQuantize between permute and convolution, an operation like data type casting could be fused to permute. In this case, do not optimize permute.
* [TF FE] Add Const to Result removing transformation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add test model
* Optimize ConstToResultRemover
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* remove ... in /src/bindings/c and resolve format
* remove ... in auto and resolve format
* remove ... in auto batch and resolve format
* remove ... in hetero and resolve format
* IE exception
* IE exception
* const
* const
* resolve format and ov::Exception
* ov::Exception
* reset IE::Exception
* remove ov::Exception
* InferenceEngine->IE in auto_schedule.cpp
* fix coredump while runing test case smoke_AutoMultiMock_NumStreamsAndDefaultPerfHintToHWTest
* fix coredump issue of running LoadNetworkWithSecondaryConfigsMockTest
* fix commpile fail in CI
* resolve core dump of running exec_network_get_metrics.cpp and disable some test cases for KEEMBAY and MYRIAD in exec_network_get_metrics.cpp
* remove test cases of MYRIAD and resolve core dump of running KEEMBAYin exec_network_get_metrics.cpp
* resolve conflic of common.h
* resolve conflic of common.h
* resolve common.h complie fail
---------
Co-authored-by: guozhong <guozhong.wang@intel.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
* [GPU] Added shape agnostic optimized MVN kernel
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Apply code review
Signed-off-by: Andrew Park <andrew.park@intel.com>
* replace built-in log2 with function macro to calculate power from integer
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Move compile-time JIT constants to cl code
Signed-off-by: Andrew Park <andrew.park@intel.com>
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
* [TF FE] Refactor LogSoftmax translator and layer test
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Work around for the legacy frontend
* Update src/frontends/tensorflow_common/src/op/log_softmax.cpp
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Add env to nGraph step
* Update windows_conditional_compilation.yml
* Add PYTHONPATH to nGraph step
* Revert all changes related with setupPython 3.10 for Linux_debian
Temporary disable on time investigate
* [WIP]: poc: integrate pt fe to mo.convert_model
* temporaly resolve names using signature inspection
* fix logic
* move to moc frontend
* add rank and data type setting
* add input signature
* apply comments
* move after convert processing
* support work without example_input, provide parameters description
* ignore extensions on fe side
* upd tests
* more tests
* add notes about extensions support and removing onnx path
* remove debug prints
* refactoring
* update BOM
* optimize shape infer of matmul
* remove some redundant check
* fix some comments
* fix some comments
* Update src/plugins/intel_cpu/src/nodes/matmul.cpp
fix an implicit bug
Co-authored-by: Maksim Kutakov <maxim.kutakov@gmail.com>
* Update src/plugins/intel_cpu/src/nodes/matmul.cpp
optimize by using OV RTTI instead of dynamic_pointer_cast
Co-authored-by: Maksim Kutakov <maxim.kutakov@gmail.com>
---------
Co-authored-by: Maksim Kutakov <maxim.kutakov@gmail.com>
* Az pipeline
* Debug comment
* Update linux.yml
* Update linux.yml
* Add $Library
* Other version
* Update linux.yml
* Remove ld_library
* Update linux.yml
* Add neccesary variables and export LD_LIBRARY in sub task
* Fix problem windows_cc
Allow to download Python from GH Python registry
* Update linux.yml
Remove needless env and add export variable before scripts
* Correct syntax
* Debug: Use Ubuntu22.04 public image for MS hosted agent
Removed variables LD_LIBRARY_PATH and OV_PYTHON_VERSION
* Debug: Use Ubuntu22.04 public image for MS hosted agent
Removed variables LD_LIBRARY_PATH and OV_PYTHON_VERSION
* Update VM image
* Update linux.yml
Fast check if changing VM will help
* Correct wrong syntax in pool section
* update pool for lin_arm64 and linux_cc
* Revert changes with public VM
* Revert VM public in onnxruntime.yml
* Update windows_conditional_compilation.yml
* Update Python setup steps on Windows_CC
* Revert all changes related to win_cc
