* added the runcoverage powershell script
* updated the run coverage script. added installation to the windows CI for trying
* exclude other parts of win ci
* fix in the download script
* fix in the download script
* fix in the download script
* fix in the download script
* fix in the download script
* fix in the download script
* fix in the download script
* fix in the download script
* fix in the download script
* added the runtestcoverage script to the pipeline
* some typo fix
* formatting
* re-commenting previously commented block
* cleaned up the powershell script
* fix path in pipeline
* fix path in pipeline
* fixed model path
* some fixes
* excluded long running tests
* add the publish job
* uncomment other tasks
* fixed excluded tests
* some format correction
* stopped running the test debug
* try placing the tes-all at the beginning
* try running the failing test only
* edit run_coverage
* some fix
* skip onnx_model_test
* Added memory size log in powershell script
* try running the onnxruntime_test_all.exe separately from codecov
* enable error reporting, and double memory size in powershell
* corrected the set-item
* remove memory resize, since we are already at max 2 GB
* fixed the tvm.dll issue
* added back the onnx tests in codecov. added back the regular test run
* cleanup
* remove * from the the module path
* add junction target resolution for modules dir
* remove junction-resolution
* reduced tests
* added target extraction for the junction paths in build machine
* added the appropriate change in win ci pipeline to call the updated ps script
* fix typo
* added back all the tests that were disabled
* try fixing the source root
* cleanup and enable all tests
* increase timeout for windows CPU CI due to codecoverage
* templatized the code coverage steps. Conitnue on error with any codecoverage step
* change quote marks
This PR introduces a rewrite rule that replaces a Shape node with an initializer when the shape of the input is statically known through shape inference.
* ConstantOfShape CUDA implementation
* Enhance the fallback logic, so the case that Shape -> ... -> ConstantOfShape won't fallback ConstantOfShape to CPU provider
* move shared code to cpu implementation
* do the fill based on sizeof(data_type)
* update method access level
This fixes#1034: Can't Create Model Sessions on Different GPU
The root cause of the bug is that CUDA execution provider uses thread_local to save per-thread-context and allocator, and when two CUDA execution providers are running on the same thread there's a conflict. The fix is to add a std::unordered_map to differentiate EPs in the same thread.
* Update MaxPool & AveragePool to support opset 10
* fix build issue
* still use cudnn for MaxPool if dilation is not set or are default 1.
* fix build issue
* add version filter to failed tests
* exclude test from backend
* exclude shrink from opset 9
* fix compile err
* exclude certain version of constant shape
* enable flatten test
* fix compile err
* comment mvn test
* disable constantofshape test in x86
* disable x86 test
* get model version from imported opset
* test linux x86 case
* disable nonzero opset 10
* make mutex const
* test filter by commit id
* adjust substr offset
* Limit test platform
* remove change impacting TFModleInfo.h
* refactoring
* refactoring
* test x86 pipeline with filter
* add comment
* restrict version extraction on non-win
* restrict version extraction on non-win
* add tag
* exclude case from backend test
* remove dup
* remove dup
* make script runnable
* hard code adsolute path
* refactor log
* fix x86 compile err
* fix x86 compile err
* fix x86 compile err
* sync with latest tensorrt
* switch to regex
* fix cpu pipeline err
* test filter
* disable nonzero from all versions
Not needed any more. Because we don't build the date library.
And Sheil says: "It’s a little bit intrusive for callers to be forced onto cpp14 just because they are consuming onnxruntime."
* refactoring the ep codes.
* remove unnecessary lock.
* fix the comment to claim KernelRegistryManager is not thread safe.
* clarify that APIs to add custom op in inferencesession is not thread safe.
* CUDA opset9: Update Cast/MatMul version, add Erf
* Address CR
* More fixes on node placement logic
* Fix typo
* Update CUDA ops Gemm and BatchNormalization to be registered in opset10
* Remove Relu if followed by Clip. Update Clip 'min' if necessary.
Add unit test.
* Rename to match behaviour a little better.
* Update to match latest RewriteRule interface
* Add version and latest commit id to ORT Server
* Update cmake
* Change build id to build number
* Use target_compile_definitions instead of add_definitions
