Fix TensorRT RTX provider name matching

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>

Author: nieubank

Samples/WindowsML/Shared/cpp/PerformanceConfigurator.h

@@ -34,7 +34,7 @@ namespace Shared
             {
                 return GetMiGraphXOptions(mode);
             }
-            if (normalized == "TENSORRTRTXEXECUTIONPROVIDER")
+            if (normalized == "NVTENSORRTRTXEXECUTIONPROVIDER")
             {
                 return GetTensorRtRtxOptions(mode);
             }

Samples/WindowsML/Shared/cs/PerformanceConfigurator.cs

@@ -17,7 +17,7 @@ public static Dictionary<string, string> GetEpOptions(string epName, Performance
                 "QNNEXECUTIONPROVIDER" => GetQnnOptions(mode),
                 "VITISAIEXECUTIONPROVIDER" => GetVitisAiOptions(mode),
                 "MIGRAPHXEXECUTIONPROVIDER" => GetMiGraphxOptions(mode),
-                "TENSORRTRTXEXECUTIONPROVIDER" => GetTensorRtRtxOptions(mode),
+                "NVTENSORRTRTXEXECUTIONPROVIDER" or "NVTENSORRTRTX" => GetTensorRtRtxOptions(mode),
                 _ => new Dictionary<string, string>(StringComparer.OrdinalIgnoreCase)
             };
         }

Samples/WindowsML/cpp/CppConsoleDesktop.GenAI/GenAIPerformanceConfigurator.h

@@ -43,7 +43,7 @@ class GenAIPerformanceConfigurator
         {
             return GetMiGraphXOptions(mode);
         }
-        if (normalized == "TENSORRTRTXEXECUTIONPROVIDER")
+        if (normalized == "NVTENSORRTRTX")
         {
             return GetTensorRtRtxOptions(mode);
         }