Support load TensorRT V3 plugin

[toothache]

Description

TensorRT V3 plugin is not able to load in TensorRT EP. The change deprecates getPluginCreatorList with getAllCreators to load V1 and V3 plugin creators.

Motivation and Context

Support load TensorRT plugin.

Reference: https://github.com/NVIDIA/TensorRT/blob/8c6d69ddec0b2feff12f55472dc5d55cb6861d53/python/src/infer/pyPlugin.cpp#L2971C1-L2995C6

[toothache]

After the change, V3 plugins can be loaded.

2025-03-27 22:39:40.3063320 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] CustomEmbLayerNormPluginDynamic, version : 4
2025-03-27 22:39:40.3124991 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] CustomEmbLayerNormPluginDynamic, version : 5
2025-03-27 22:39:40.3163747 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] CustomSkipLayerNormPluginDynamic, version : 7
2025-03-27 22:39:40.3199090 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] CustomSkipLayerNormPluginDynamic, version : 8
2025-03-27 22:39:40.3239330 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] CustomSkipLayerNormPluginDynamic, version : 5
2025-03-27 22:39:40.3275216 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] CustomSkipLayerNormPluginDynamic, version : 6
2025-03-27 22:39:40.3346971 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] InstanceNormalization_TRT, version : 3
2025-03-27 22:39:40.3379989 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] ROIAlign_TRT, version : 2
2025-03-27 22:39:40.3419829 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:83 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP][V3ONE] ScatterElements, version : 2
2025-03-27 22:39:40.3453966 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:79 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP] CaskDeconvV2RunnerWeightsTransformerPlugin, version : 1
2025-03-27 22:39:40.3489028 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:79 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP] CaskDeconvV1RunnerWeightsTransformerPlugin, version : 1
2025-03-27 22:39:40.3525361 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:79 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP] CaskConvolutionRunnerWeightsTransformerPlugin, version : 1
2025-03-27 22:39:40.3567290 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:79 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP] CaskFlattenConvolutionRunnerWeightsTransformerPlugin, version : 1
2025-03-27 22:39:40.3617080 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:79 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP] CaskConvActPoolWeightsTransformerPlugin, version : 1
2025-03-27 22:39:40.3652211 [W:onnxruntime:Default, tensorrt_execution_provider_custom_ops.cc:79 onnxruntime::CreateTensorRTCustomOpDomainList] [TensorRT EP] CaskDepSepConvWeightsTransformerPlugin, version : 1

[toothache]

@jywu-msft , @tianleiwu , may I get a review of this change as well? Thanks!

[chilo-ms]

/azp run Big Models, Linux CPU Minimal Build E2E CI Pipeline, Linux QNN CI Pipeline, ONNX Runtime Web CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows x64 QNN CI Pipeline

[azure-pipelines]

Azure Pipelines successfully started running 9 pipeline(s).

[chilo-ms]

/azp run Big Models, Linux CPU Minimal Build E2E CI Pipeline, Linux QNN CI Pipeline, ONNX Runtime Web CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows x64 QNN CI Pipeline

[azure-pipelines]

Azure Pipelines successfully started running 8 pipeline(s).