Repository navigation
Fix TensorRT RTX provider name matching - #642
Merged
Merged
Conversation
Use the real Windows TensorRT RTX execution provider name in shared helpers and the canonical ONNX Runtime GenAI provider name in GenAI helpers. ADO: 61791041 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Darshak Bhatti (dabhattimsft)
approved these changes
May 27, 2026
shisan (qiutongMS)
pushed a commit
that referenced
this pull request
Aug 25, 2026
Align the WindowsML central package set with stable Windows App SDK 2.1.3 and port the main-only EP performance chain from PRs #588, #634, #635, #629, #642, and #643. Preserve release Central Package Management, defer the PR #643 legacy sample removals to final integration review, and record the x64 Release validation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
TensorRTRTXExecutionProvidermatch with the real Windows TensorRT RTX EP nameNvTensorRTRTXExecutionProviderin shared helpers.NvTensorRtRtxfor HelloPhi/shared C# and C++ GenAI performance options.Rationale
ADO 61791041 is not only a C# catalog mismatch. ONNX Runtime GenAI uses
NvTensorRtRtxas the provider name, while Windows EP registration/catalog data usesNvTensorRTRTXExecutionProvider. The previousTensorRTRTXExecutionProviderstring is not a real provider name.Validation
git diff --checkdotnet restore Samples/WindowsML/cs/HelloPhi/HelloPhi.csproj -p:Platform=x64dotnet build Samples/WindowsML/cs/HelloPhi/HelloPhi.csproj -c Release -p:Platform=x64 --no-restoreMSBuild Samples/WindowsML/cpp/CppConsoleDesktop.GenAI/CppConsoleDesktop.GenAI.vcxproj /p:Configuration=Release /p:Platform=x64 /p:BuildProjectReferences=falseNotes: HelloPhi restore/build reports existing NU1603 package-resolution warning. C++ GenAI build reports existing WindowsAppRuntimeAutoInitializer duplicate-object warnings, but succeeds.
Fixes ADO 61791041.