[NvTensorRTRTX EP] Fix build breaks with TRT-RTX 1.5+ and 1.6+#28263
Merged
chilo-ms merged 2 commits intomicrosoft:mainfrom Apr 30, 2026
Merged
[NvTensorRTRTX EP] Fix build breaks with TRT-RTX 1.5+ and 1.6+#28263chilo-ms merged 2 commits intomicrosoft:mainfrom
chilo-ms merged 2 commits intomicrosoft:mainfrom
Conversation
Four fixes for build breaks when compiling against TRT-RTX >= 1.5.0.95: 1. nv_execution_provider_custom_ops.cc: Migrate from removed getPluginCreatorList() to getAllCreators(), returning IPluginCreatorInterface* which requires dynamic_cast<IPluginCreator*> with a null check to skip V3 entries. 2. test_nv_trt_rtx_ep_util.cc: Replace onnxruntime::utils::SetRawDataInTensorProto (removed in ORT 1.25) with proto.set_raw_data() at 5 call sites. 3. nv_execution_provider.cc: Guard kSTRONGLY_TYPED enum usage behind #if (TRT_MINOR_RTX == 5 && TRT_BUILD_RTX >= 97) || TRT_MINOR_RTX >= 6 since the enum is marked TRT_DEPRECATED_ENUM starting 1.5.0.97. Use the equivalent literal value (1U) instead. 4. nv_execution_provider.h: Define SubGraph_t / SubGraphCollection_t behind #if TRT_MINOR_RTX >= 6 since these types were removed from NvOnnxParser.h in TRT-RTX 1.6.x. Also add #include <utility> and #include <vector> needed for the type definitions. All guards preserve backward compatibility with TRT-RTX 1.4.x and earlier. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Extend the version guard at both createNetworkV2 call sites to include TRT_MAJOR_RTX >= 2, ensuring future major releases also take the safe literal path instead of falling through to the deprecated enum.
Contributor
|
/azp run Linux QNN CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline |
|
No pipelines are associated with this pull request. |
chilo-ms
approved these changes
Apr 30, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Four fixes for build breaks when compiling against TRT-RTX >= 1.5.0.95:
nv_execution_provider_custom_ops.cc: Migrate from removed getPluginCreatorList() to getAllCreators(), returning IPluginCreatorInterface* which requires dynamic_cast<IPluginCreator*> with a null check to skip V3 entries.
test_nv_trt_rtx_ep_util.cc: Replace onnxruntime::utils::SetRawDataInTensorProto (removed in ORT 1.25) with proto.set_raw_data() at 5 call sites.
nv_execution_provider.cc: Guard kSTRONGLY_TYPED enum usage behind #if (TRT_MINOR_RTX == 5 && TRT_BUILD_RTX >= 97) || TRT_MINOR_RTX >= 6 since the enum is marked TRT_DEPRECATED_ENUM starting 1.5.0.97. Use the equivalent literal value (1U) instead.
nv_execution_provider.h: Define SubGraph_t / SubGraphCollection_t behind #if TRT_MINOR_RTX >= 6 since these types were removed from NvOnnxParser.h in TRT-RTX 1.6.x. Also add #include and #include needed for the type definitions.
All guards preserve backward compatibility with TRT-RTX 1.4.x and earlier.