* [LPT][CPU] Added callback for AddTransformation
* [WIP] Convolution scales fusion
* Force to use weight sclae to test performance.
* Update on interface.
* Use weight scale to adapt to ONEDNN 3.x API changes.
* Update the code.
* Update ONEDNN fix for gemm_x8s8s32x_conv kernel
* Fix the bug in ONEDNN and deconvFusingScale.
* Fuse FC Bias when having DQscale.
* WR to perf regression on
* Update onednn version.
* Fix bug and clean code.
* FC fusing dq scale bug fix.
* Add more comments and debug information.
* Fix CI issues.
* Merge ONEDNN changes.
* Fix CI issues and bugs.
* Apply review comments.
* Update comments.
* Apply reveiw comments.
* Avoid using LPT BiasAttribute RTInfo.
* Applied review comments.
---------
Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
* Used singleton class for version check.
* Moved VersionChecker to utitl/version.py, added tests.
* Minor corrections.
* Sort imports.
* Small correction.
* Small correction.
* Remove exclusive_asyc_requests property from AUTO plugin
* Update test case
* Add test case to test incorrect config
* Remove the test case related to exclusive_asyc_requests property of AUTO plugin
* Allow stable sort in TopK when sorting by indices
* Clarification of stable sorting by index and unblocked test
* XFAIL the test again
* Clarification of sorting by indices
* Revert of changes in previous versions op TopK (spec)
* [CPU] ARM architecture support
This patch extends existing CPU plugin capabilities with ARM CPUs optimized support
* Fixed undefined reference in unit tests
* refactoring
* Fixed Eltwise node behavior for ARM
* init commit
* tests passed
* fix skip failures
* Apply suggestions from code review
---------
Co-authored-by: dmitrygo <dmitry.gorokhov@intel.com>
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
* 1. refine the logic to ov::device::properties setting.
2. the config overrides will be performed if same config setting is came from CMD line.-a
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update configuration sample file within README.md.
* Update.
* Update.
* 1. Update configuration example file within REAMDME.md for Python version.
2. implement the config DEVICE_PROPERTIES value convertation between the string type and dictionary of Python type.
3. Update the configuration file loading and dumping logic.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
* Update.
* Update.
* Update.
* Update.
* 1. Enable configs to be interchangeable between C++ and Python.
2. Update perf_count showing logic.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Revert the logic of showing show performance counters.
* Update help msg for loading config option.
---------
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Benchmark_app set ov::hint::allow_auto_batching through compile_model
* Remove the process about allow_auto_batching in set_property of core
* Remove allow_auto_batching and auto_batch_timeout property from AUTO plugin
* Reserve the info logs and add API to check auto_batching
* Update test case, rm AB property test from core config tests
* Update some API in AUTO plugin config
