fix windows arm64 cuda 13 build

Author: tianleiwu

cmake/external/cuda_configuration.cmake

@@ -164,6 +164,7 @@ macro(setup_cuda_architectures)
   unset(ORT_HAS_SM80_OR_LATER)
   unset(ORT_HAS_SM90_OR_LATER)
   unset(ORT_HAS_SM100_OR_LATER)
+  unset(ORT_HAS_SM120_OR_LATER)
   foreach(CUDA_ARCH IN LISTS CMAKE_CUDA_ARCHITECTURES_ORIG)
     if(CUDA_ARCH MATCHES "^([0-9]+)")
       if(CMAKE_MATCH_1 GREATER_EQUAL 80)
@@ -175,6 +176,9 @@ macro(setup_cuda_architectures)
       if(CMAKE_MATCH_1 GREATER_EQUAL 100)
         set(ORT_HAS_SM100_OR_LATER ON)
       endif()
+      if(CMAKE_MATCH_1 GREATER_EQUAL 120)
+        set(ORT_HAS_SM120_OR_LATER ON)
+      endif()
     endif()
   endforeach()
   if(ORT_HAS_SM80_OR_LATER)
@@ -186,6 +190,9 @@ macro(setup_cuda_architectures)
   if(ORT_HAS_SM100_OR_LATER)
     add_definitions("-DHAS_SM100_OR_LATER")
   endif()
+  if(ORT_HAS_SM120_OR_LATER)
+    add_definitions("-DHAS_SM120_OR_LATER")
+  endif()
 
   set(ARCHITECTURES_WITH_KERNELS "80" "86" "89" "90" "100" "110" "120")
   foreach(CUDA_ARCH IN LISTS ARCHITECTURES_WITH_KERNELS)

cmake/onnxruntime_providers_cuda_plugin.cmake

@@ -357,6 +357,12 @@ if(NOT onnxruntime_DISABLE_CONTRIB_OPS)
   if(_cuda_plugin_llm_srcs)
     if(MSVC AND NOT onnxruntime_USE_FP4_QMOE)
       onnxruntime_filter_cuda_archs(_plugin_llm_cuda_architectures MIN_SM 75 EXCLUDE_SM120_REAL)
+      # A native-only Windows ARM64 build has no lower architecture left after the
+      # MSVC SM120 exclusion. Emit PTX privately for this object library so its host
+      # launchers and device kernels are still linked into the plugin.
+      if(NOT _plugin_llm_cuda_architectures AND ORT_HAS_SM120_OR_LATER)
+        set(_plugin_llm_cuda_architectures "120-virtual")
+      endif()
     else()
       onnxruntime_filter_cuda_archs(_plugin_llm_cuda_architectures MIN_SM 75)
     endif()