onnxruntime/tools/ci_build/github/azure-pipelines
Changming Sun 61fae9bb91
Remove "--enable_pybind" from webgpu pipeline (#23550)
There is a crash in the WebGPU CI pipeline. It crashed at process
shutdown when unloading onnxruntime_pybind11_state.pyd.
Here is the callstack:

```
 	dxil.dll!DxcSwapThreadMalloc()	Unknown
 	dxil.dll!DxcThreadMalloc::DxcThreadMalloc(struct IMalloc *)	Unknown
 	dxil.dll!DxcValidator::Release(void)	Unknown
 	[Inline Frame] webgpu_dawn.dll!Microsoft::WRL::ComPtr<IDxcValidator>::InternalRelease() Line 235	C++
 	[Inline Frame] webgpu_dawn.dll!Microsoft::WRL::ComPtr<IDxcValidator>::{dtor}() Line 290	C++
 	webgpu_dawn.dll!dawn::native::d3d12::Backend::`scalar deleting destructor'(unsigned int)	C++
 	webgpu_dawn.dll!`eh vector destructor iterator'(void * ptr, unsigned __int64 size, unsigned __int64 count, void(*)(void *) destructor)	C++
 	webgpu_dawn.dll!dawn::native::InstanceBase::~InstanceBase() Line 197	C++
 	webgpu_dawn.dll!dawn::native::InstanceBase::`scalar deleting destructor'(unsigned int)	C++
 	webgpu_dawn.dll!dawn::native::InstanceBase::DeleteThis() Line 218	C++
 	ucrtbase.dll!<lambda>(void)()	Unknown
 	ucrtbase.dll!__crt_seh_guarded_call<int>::operator()<<lambda_7777bce6b2f8c936911f934f8298dc43>,<lambda>(void) &,<lambda_3883c3dff614d5e0c5f61bb1ac94921c>>()	Unknown
 	ucrtbase.dll!_execute_onexit_table()	Unknown
 	onnxruntime_pybind11_state.pyd!dllmain_crt_process_detach(const bool is_terminating) Line 182	C++
>	onnxruntime_pybind11_state.pyd!dllmain_dispatch(HINSTANCE__ * const instance, const unsigned long reason, void * const reserved) Line 293	C++
 	ntdll.dll!LdrpCallInitRoutine()	Unknown
 	ntdll.dll!LdrShutdownProcess()	Unknown
 	ntdll.dll!RtlExitUserProcess()	Unknown
 	kernel32.dll!ExitProcessImplementation()	Unknown
 	ucrtbase.dll!exit_or_terminate_process()	Unknown
 	ucrtbase.dll!common_exit()	Unknown
 	python312.dll!00007ff9cab3ec8d()	Unknown
 	python312.dll!00007ff9cab3efbf()	Unknown
 	python312.dll!00007ff9cab3edee()	Unknown
 	python312.dll!00007ff9cab57f4c()	Unknown
 	python312.dll!00007ff9cab57579()	Unknown
 	python312.dll!00007ff9cab573be()	Unknown
 	python312.dll!00007ff9cab5729b()	Unknown
 	python312.dll!00007ff9cabacfcb()	Unknown
 	python312.dll!00007ff9cabacd7d()	Unknown
 	python312.dll!00007ff9cab99e2d()	Unknown
 	python.exe!00007ff78a641230()	Unknown
 	kernel32.dll!BaseThreadInitThunk()	Unknown
 	ntdll.dll!RtlUserThreadStart()	Unknown
```
It might be because the destruct order of some global variables was
wrong. I saw DX DLLs were getting destroyed earlier than the WebGPU
instance in our code in onnxruntime_pybind11_state.pyd.
2025-01-31 08:43:58 -08:00
..
nodejs/templates Update pool to MacOS-13 (#17361) 2024-09-17 10:07:30 -07:00
nuget Remove PostBuildCleanup (#23233) 2024-12-31 13:12:33 -08:00
stages Enable coremltools for Linux build (#23481) 2025-01-24 18:18:37 -08:00
templates [webgpu] Bump version of Dawn to b9b4a370 (#23494) 2025-01-27 14:02:06 -08:00
triggers
android-arm64-v8a-QNN-crosscompile-ci-pipeline.yml [QNN EP] Make QNN EP a shared library (#23120) 2025-01-22 12:11:00 -08:00
android-x86_64-crosscompile-ci-pipeline.yml Update pool to MacOS-13 (#17361) 2024-09-17 10:07:30 -07:00
bigmodels-ci-pipeline.yml Enable coremltools for Linux build (#23481) 2025-01-24 18:18:37 -08:00
binary-size-checks-pipeline.yml Update onnxruntime binary size checks ci pipeline's docker image (#23405) 2025-01-17 15:29:17 -08:00
build-perf-test-binaries-pipeline.yml Update onnxruntime binary size checks ci pipeline's docker image (#23405) 2025-01-17 15:29:17 -08:00
c-api-noopenmp-packaging-pipelines.yml Update Qnn SDK default version to 2.30 (#23411) 2025-01-17 22:36:35 -08:00
c-api-training-packaging-pipelines.yml Move on-device training packages publish step (#21539) 2024-07-29 09:59:46 -07:00
cuda-packaging-pipeline.yml Update onnxruntime binary size checks ci pipeline's docker image (#23405) 2025-01-17 15:29:17 -08:00
linux-ci-pipeline.yml Update onnxruntime binary size checks ci pipeline's docker image (#23405) 2025-01-17 15:29:17 -08:00
linux-cpu-minimal-build-ci-pipeline.yml Update onnxruntime binary size checks ci pipeline's docker image (#23405) 2025-01-17 15:29:17 -08:00
linux-dnnl-ci-pipeline.yml Remove PostBuildCleanup (#23233) 2024-12-31 13:12:33 -08:00
linux-gpu-ci-pipeline.yml Enable coremltools for Linux build (#23481) 2025-01-24 18:18:37 -08:00
linux-gpu-tensorrt-ci-pipeline.yml Enable coremltools for Linux build (#23481) 2025-01-24 18:18:37 -08:00
linux-gpu-tensorrt-cuda-minimal-ci-pipeline.yml Enable coremltools for Linux build (#23481) 2025-01-24 18:18:37 -08:00
linux-gpu-tensorrt-daily-perf-pipeline.yml [TensorRT EP] support TensorRT 10.7-GA (#23011) 2024-12-19 10:39:15 -08:00
linux-migraphx-ci-pipeline.yml Remove PostBuildCleanup (#23233) 2024-12-31 13:12:33 -08:00
linux-openvino-ci-pipeline.yml OVEP 1.21.0 Development Updates (#23080) 2024-12-11 22:26:32 -08:00
linux-qnn-ci-pipeline.yml [QNN EP] Make QNN EP a shared library (#23120) 2025-01-22 12:11:00 -08:00
linux-rocm-ci-pipeline.yml Remove PostBuildCleanup (#23233) 2024-12-31 13:12:33 -08:00
mac-ci-pipeline.yml Add a reminder in set-trigger-rules script (#21929) 2024-08-30 12:18:10 -07:00
mac-coreml-ci-pipeline.yml Update pool to MacOS-13 (#17361) 2024-09-17 10:07:30 -07:00
mac-ios-ci-pipeline.yml Update min iOS version to 15.1 to align with React Native 0.76 (#23292) 2025-01-08 16:02:45 -08:00
mac-ios-packaging-pipeline.yml Update pool to MacOS-13 (#17361) 2024-09-17 10:07:30 -07:00
mac-react-native-ci-pipeline.yml Update onnxruntime binary size checks ci pipeline's docker image (#23405) 2025-01-17 15:29:17 -08:00
npm-packaging-pipeline.yml Seperate RN andriod and IOS into 2 separated Stages. (#23400) 2025-01-20 18:08:01 -08:00
nuget-cuda-publishing-pipeline.yml
nuget-windows-ai.yml Nuget Windows AI Pipeline, Disable SDL Submodules. (#22711) 2024-11-04 08:39:28 -08:00
post-merge-jobs.yml Merge web machine pools (#23243) 2025-01-03 13:53:17 -08:00
publish-nuget.yml Move on-device training packages publish step (#21539) 2024-07-29 09:59:46 -07:00
py-cuda-alt-package-test-pipeline.yml Enable coremltools for Linux build (#23481) 2025-01-24 18:18:37 -08:00
py-cuda-alt-packaging-pipeline.yml Update Python-Cuda-Publishing-Pipeline (#23253) 2025-01-06 11:50:58 -08:00
py-cuda-package-test-pipeline.yml Enable coremltools for Linux build (#23481) 2025-01-24 18:18:37 -08:00
py-cuda-packaging-pipeline.yml Update Python-Cuda-Publishing-Pipeline (#23253) 2025-01-06 11:50:58 -08:00
py-cuda-publishing-pipeline.yml Update Python-Cuda-Publishing-Pipeline (#23253) 2025-01-06 11:50:58 -08:00
py-dml-packaging-pipeline.yml Add pipauth to more ADO pipelines and enable CSV (#22612) 2024-10-28 16:39:22 -07:00
py-package-test-pipeline.yml Adding new Python package testing pipeline for Cuda Alt (#22584) 2024-10-24 19:24:53 -07:00
py-packaging-pipeline.yml Update Qnn SDK default version to 2.30 (#23411) 2025-01-17 22:36:35 -08:00
qnn-ep-nuget-packaging-pipeline.yml Update Qnn SDK default version to 2.30 (#23411) 2025-01-17 22:36:35 -08:00
rocm-nuget-packaging-pipeline.yml Remove PostBuildCleanup (#23233) 2024-12-31 13:12:33 -08:00
rocm-publish-nuget-pipeline.yml New rocm nuget publish pipeline (#22418) 2024-10-13 08:30:06 +08:00
web-ci-pipeline.yml Merge web machine pools (#23243) 2025-01-03 13:53:17 -08:00
win-ci-fuzz-testing.yml Remove PostBuildCleanup (#23233) 2024-12-31 13:12:33 -08:00
win-ci-pipeline.yml [onnxruntime/build] Add new flag enable_generic_interface to build primary EPs by default (#23342) 2025-01-28 15:24:09 -08:00
win-gpu-cuda-ci-pipeline.yml Revert DML pipeline changes (#23135) 2024-12-18 10:42:10 -08:00
win-gpu-dml-ci-pipeline.yml Revert DML pipeline changes (#23135) 2024-12-18 10:42:10 -08:00
win-gpu-doc-gen-ci-pipeline.yml Add a reminder in set-trigger-rules script (#21929) 2024-08-30 12:18:10 -07:00
win-gpu-reduce-op-ci-pipeline.yml
win-gpu-tensorrt-ci-pipeline.yml [TensorRT EP] Refactor TRT version update logic & apply TRT 10.5 (#22483) 2024-10-29 09:23:41 -07:00
win-gpu-tensorrt-cuda-minimal-ci-pipeline.yml [TensorRT EP] New CIs to test TRT+minimal CUDA build (#23028) 2024-12-19 10:30:39 -08:00
win-gpu-training-ci-pipeline.yml Add a reminder in set-trigger-rules script (#21929) 2024-08-30 12:18:10 -07:00
win-gpu-webgpu-ci-pipeline.yml Remove "--enable_pybind" from webgpu pipeline (#23550) 2025-01-31 08:43:58 -08:00
win-qnn-arm64-ci-pipeline.yml [QNN EP] Make QNN EP a shared library (#23120) 2025-01-22 12:11:00 -08:00
win-qnn-ci-pipeline.yml [QNN EP] Make QNN EP a shared library (#23120) 2025-01-22 12:11:00 -08:00