How to uninstall op from other providers to the default CPUExecutionProvider. #25695
Description
Describe the issue
I try to run kokorotts on windows+intel。it's success run with CPUExecutionProvider. but it want to run on intelgpu.so i try to use onnxruntime-openvino firstly ,but get error:
Error: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: C:\Users\Administrator\Documents\windows_wheels\onnxruntime\onnxruntime\core\providers\openvino\ov_interface.cc:87 class onnxruntime::openvino_ep::OVExeNetwork __cdecl onnxruntime::openvino_ep::OVCore::CompileModel(class std::shared_ptr<class ov::Model const > &,class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &,class std::map<class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> >,class ov::Any,struct std::less<class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > >,class std::allocator<struct std::pair<class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > const ,class ov::Any> > > &,const class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &) [OpenVINO-EP] Exception while Loading Network for graph: OpenVINOExecutionProvider_OpenVINO-EP-subgraph_1_0Exception from src\inference\src\cpp\core.cpp:112:
Exception from src\inference\src\dev\plugin.cpp:53:
Check 'inputRank == 2 || inputRank == 4 || inputRank == 5' failed at src\plugins\intel_gpu\src\plugin\ops\interpolate.cpp:38:
Mode 'linear_onnx' supports only 2D or 4D, 5D tensors
when use openvinoCPU:
Error: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: C:\Users\Administrator\Documents\windows_wheels\onnxruntime\onnxruntime\core\providers\openvino\ov_interface.cc:87 class onnxruntime::openvino_ep::OVExeNetwork __cdecl onnxruntime::openvino_ep::OVCore::CompileModel(class std::shared_ptr<class ov::Model const > &,class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &,class std::map<class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> >,class ov::Any,struct std::less<class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > >,class std::allocator<struct std::pair<class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > const ,class ov::Any> > > &,const class std::basic_string<char,struct std::char_traits<char>,class std::allocator<char> > &) [OpenVINO-EP] Exception while Loading Network for graph: OpenVINOExecutionProvider_OpenVINO-EP-subgraph_2_1Exception from src\inference\src\cpp\core.cpp:112:
Exception from src\inference\src\dev\plugin.cpp:53:
Exception from src\plugins\intel_cpu\src\node.cpp:90:
Unexpected: CPU plug-in doesn't support Parameter operation with dynamic rank. Operation name: /decoder/decoder/generator/STFT_output_0
then i try DmlExecutionProvider
Non-zero status code returned while running ConvTranspose node. Name:'/encoder/F0.1/pool/ConvTranspose' Status Message: D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\MLOperatorAuthorImpl.cpp(2816)\onnxruntime_pybind11_state.pyd!00007FFAC893C70A: (caller: 00007FFAC8908545) Exception(2) tid(8148) 80070057
it seem like all error is op's error, So like issue'title ,i want to know how to avoid use this error op(because CPUExecutionProvider is ok, so run this error op with CPUExecutionProvider may be a method).
Can you gei me some advice?
To reproduce
pip install onnxruntime-openvino
pip install onnxruntime-directml
self.sess = rt.InferenceSession("D:\TTS\kokoro-tts\kokoro-v1.0.onnx", providers=providers, provider_options=[{'device_type' : "GPU"}])
onnxruntime 1.22.1
onnxruntime-gpu 1.22.0
onnxruntime-openvino 1.22.0
openvino 2025.0.0 17942
openvino-telemetry 2025.2.0
onnxruntime-directml 1.22.0
Urgency
No response
Platform
Windows
OS Version
windows11
ONNX Runtime Installation
Released Package
ONNX Runtime Version or Commit ID
1.22.1
ONNX Runtime API
Python
Architecture
X64
Execution Provider
OpenVINO
Execution Provider Library Version
No response