[NvTensorRTRTX EP] Enable automatic selection of NvTensorRTRTX EP for PREFER_GPU policy

[nieubank]

Description

Enables automatic selection of NvTensorRTRTX EP for PREFER_GPU policy similar to #24629

Sample code from unit test:

  auto env = Ort::Env();

  env.RegisterExecutionProviderLibrary(kNvTensorRTRTXExecutionProvider, ORT_TSTR("onnxruntime_providers_nv_tensorrt_rtx.dll"));

  Ort::SessionOptions so;
  so.SetEpSelectionPolicy(OrtExecutionProviderDevicePolicy_PREFER_GPU);
  Ort::Session session_object(env, model_name_ctx.c_str(), so);
  EXPECT_TRUE(SessionHasEp(session_object, kNvTensorRTRTXExecutionProvider));

  env.UnregisterExecutionProviderLibrary(kNvTensorRTRTXExecutionProvider);

Note: Google Test filter = *NvExecutionProviderTest*AutoEp_PreferGpu*
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from NvExecutionProviderTest
[ RUN      ] NvExecutionProviderTest.AutoEp_PreferGpu
[       OK ] NvExecutionProviderTest.AutoEp_PreferGpu (1136 ms)
[----------] 1 test from NvExecutionProviderTest (1137 ms total)

[----------] Global test environment tear-down
[==========] 1 test from 1 test suite ran. (1138 ms total)
[  PASSED  ] 1 test.

Motivation and Context

A recent feature allows ORT to automatically select an EP according to policies set by the user (e.g., prefer npu or prefer gpu). This PR allows NvTensorRTRTX EP to be potentially selected when the user sets the PREFER_GPU policy.

[nieubank]

@adrianlizarraga - I've updated the PR on the latest main with the change we took for Windows ML to fix multi-device path. When you get a chance, please review and let me know if there is anything else that needs to be done to unblock merging. Thanks!