Merge branch 'main' of github.com:microsoft/onnxruntime into sajandhy…

…/webgpu_upgrade_emsdk_from_3.1.59_to_3.1.62
microsoft · Aug 14, 2024 · 227e7b5 · 227e7b5
2 parents fa53e38 + a0708a0
commit 227e7b5
Show file tree

Hide file tree

Showing 282 changed files with 17,800 additions and 3,685 deletions.
diff --git a/.github/workflows/publish-python-apidocs.yml b/.github/workflows/publish-python-apidocs.yml
@@ -22,7 +22,7 @@ permissions:
 jobs:
   build:
     name: Generate Python API docs
-    runs-on: ubuntu-latest
+    runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-ubuntu-CPU"]
     steps:
       - uses: actions/checkout@v4
       - name: Install tools

diff --git a/.pipelines/nuget_config/x64/packages.config b/.pipelines/nuget_config/x64/packages.config
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="utf-8"?>
 <packages>
   <package id="python" version="3.9.7" targetFramework="native" />
-  <package id="Microsoft.AI.DirectML" version="1.15.0" targetFramework="native" />
+  <package id="Microsoft.AI.DirectML" version="1.15.1" targetFramework="native" />
   <package id="Microsoft.Windows.CppWinRT" version="2.0.201201.7" targetFramework="native" />
 </packages>
diff --git a/.pipelines/nuget_config/x86/packages.config b/.pipelines/nuget_config/x86/packages.config
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="utf-8"?>
 <packages>
   <package id="pythonx86" version="3.9.7" targetFramework="native" />
-  <package id="Microsoft.AI.DirectML" version="1.15.0" targetFramework="native" />
+  <package id="Microsoft.AI.DirectML" version="1.15.1" targetFramework="native" />
   <package id="Microsoft.Windows.CppWinRT" version="2.0.201201.7" targetFramework="native" />
 </packages>
diff --git a/VERSION_NUMBER b/VERSION_NUMBER
@@ -1 +1 @@
-1.19.0
+1.20.0
diff --git a/cgmanifests/generated/cgmanifest.json b/cgmanifests/generated/cgmanifest.json
@@ -351,6 +351,16 @@
         },
         "comments": "directx_headers"
       }
+    },
+    {
+      "component": {
+        "type": "git",
+        "git": {
+          "commitHash": "98ca4e1941fe3263f128f74f10063a3ea35c7019",
+          "repositoryUrl": "https://github.com/NVIDIA/cudnn-frontend.git"
+        },
+        "comments": "cudnn_frontend"
+      }
     }
   ]
 }
diff --git a/cmake/CMakeLists.txt b/cmake/CMakeLists.txt
@@ -729,9 +729,6 @@ set(ORT_PROVIDER_FLAGS)
 set(ORT_PROVIDER_CMAKE_FLAGS)
 
 if (onnxruntime_USE_CUDA)
-  if (onnxruntime_USE_CUDA_NHWC_OPS)
-    add_compile_definitions(ENABLE_CUDA_NHWC_OPS)
-  endif()
   enable_language(CUDA)
   message( STATUS "CMAKE_CUDA_COMPILER_VERSION: ${CMAKE_CUDA_COMPILER_VERSION}")
 
@@ -1445,9 +1442,6 @@ if (onnxruntime_USE_CUDA)
     file(TO_CMAKE_PATH CUDAToolkit_ROOT ${onnxruntime_CUDA_HOME})
   endif()
   find_package(CUDAToolkit REQUIRED)
-  if(onnxruntime_CUDNN_HOME)
-    file(TO_CMAKE_PATH ${onnxruntime_CUDNN_HOME} onnxruntime_CUDNN_HOME)
-  endif()
   if (NOT CMAKE_CUDA_ARCHITECTURES)
     if (CMAKE_LIBRARY_ARCHITECTURE STREQUAL "aarch64-linux-gnu")
       # Support for Jetson/Tegra ARM devices

diff --git a/cmake/deps.txt b/cmake/deps.txt
@@ -58,3 +58,4 @@ utf8_range;https://github.com/protocolbuffers/utf8_range/archive/72c943dea2b9240
 extensions;https://github.com/microsoft/onnxruntime-extensions/archive/94142d8391c9791ec71c38336436319a2d4ac7a0.zip;4365ac5140338b4cb75a39944a4be276e3829b3c
 composable_kernel;https://github.com/ROCmSoftwarePlatform/composable_kernel/archive/204da9c522cebec5220bba52cd3542ebcaf99e7a.zip;1827348efd47831c13074245274d41b7cae8a557
 directx_headers;https://github.com/microsoft/DirectX-Headers/archive/refs/tags/v1.613.1.zip;47653509a3371eabb156360f42faf582f314bf2e
+cudnn_frontend;https://github.com/NVIDIA/cudnn-frontend/archive/refs/tags/v1.5.2.zip;11071a47594b20f00af09aad83e0d5203ccf6029
diff --git a/cmake/external/cuDNN.cmake b/cmake/external/cuDNN.cmake
@@ -0,0 +1,111 @@
+add_library(CUDNN::cudnn_all INTERFACE IMPORTED)
+
+find_path(
+    CUDNN_INCLUDE_DIR cudnn.h
+    HINTS $ENV{CUDNN_PATH} ${CUDNN_PATH} ${Python_SITEARCH}/nvidia/cudnn ${CUDAToolkit_INCLUDE_DIRS}
+    PATH_SUFFIXES include
+    REQUIRED
+)
+
+file(READ "${CUDNN_INCLUDE_DIR}/cudnn_version.h" cudnn_version_header)
+string(REGEX MATCH "#define CUDNN_MAJOR [1-9]+" macrodef "${cudnn_version_header}")
+string(REGEX MATCH "[1-9]+" CUDNN_MAJOR_VERSION "${macrodef}")
+
+function(find_cudnn_library NAME)
+    find_library(
+        ${NAME}_LIBRARY ${NAME} "lib${NAME}.so.${CUDNN_MAJOR_VERSION}"
+        HINTS $ENV{CUDNN_PATH} ${CUDNN_PATH} ${Python_SITEARCH}/nvidia/cudnn ${CUDAToolkit_LIBRARY_DIR}
+        PATH_SUFFIXES lib64 lib/x64 lib
+        REQUIRED
+    )
+
+    if(${NAME}_LIBRARY)
+        add_library(CUDNN::${NAME} UNKNOWN IMPORTED)
+        set_target_properties(
+            CUDNN::${NAME} PROPERTIES
+            INTERFACE_INCLUDE_DIRECTORIES ${CUDNN_INCLUDE_DIR}
+            IMPORTED_LOCATION ${${NAME}_LIBRARY}
+        )
+        message(STATUS "${NAME} found at ${${NAME}_LIBRARY}.")
+    else()
+        message(STATUS "${NAME} not found.")
+    endif()
+
+
+endfunction()
+
+find_cudnn_library(cudnn)
+
+include (FindPackageHandleStandardArgs)
+find_package_handle_standard_args(
+    LIBRARY REQUIRED_VARS
+    CUDNN_INCLUDE_DIR cudnn_LIBRARY
+)
+
+if(CUDNN_INCLUDE_DIR AND cudnn_LIBRARY)
+
+    message(STATUS "cuDNN: ${cudnn_LIBRARY}")
+    message(STATUS "cuDNN: ${CUDNN_INCLUDE_DIR}")
+
+    set(CUDNN_FOUND ON CACHE INTERNAL "cuDNN Library Found")
+
+else()
+
+    set(CUDNN_FOUND OFF CACHE INTERNAL "cuDNN Library Not Found")
+
+endif()
+
+target_include_directories(
+    CUDNN::cudnn_all
+    INTERFACE
+    $<INSTALL_INTERFACE:include>
+    $<BUILD_INTERFACE:${CUDNN_INCLUDE_DIR}>
+)
+
+target_link_libraries(
+    CUDNN::cudnn_all
+    INTERFACE
+    CUDNN::cudnn
+)
+
+if(CUDNN_MAJOR_VERSION EQUAL 8)
+    find_cudnn_library(cudnn_adv_infer)
+    find_cudnn_library(cudnn_adv_train)
+    find_cudnn_library(cudnn_cnn_infer)
+    find_cudnn_library(cudnn_cnn_train)
+    find_cudnn_library(cudnn_ops_infer)
+    find_cudnn_library(cudnn_ops_train)
+
+    target_link_libraries(
+        CUDNN::cudnn_all
+        INTERFACE
+        CUDNN::cudnn_adv_train
+        CUDNN::cudnn_ops_train
+        CUDNN::cudnn_cnn_train
+        CUDNN::cudnn_adv_infer
+        CUDNN::cudnn_cnn_infer
+        CUDNN::cudnn_ops_infer
+    )
+elseif(CUDNN_MAJOR_VERSION EQUAL 9)
+    find_cudnn_library(cudnn_cnn)
+    find_cudnn_library(cudnn_adv)
+    find_cudnn_library(cudnn_graph)
+    find_cudnn_library(cudnn_ops)
+    find_cudnn_library(cudnn_engines_runtime_compiled)
+    find_cudnn_library(cudnn_engines_precompiled)
+    find_cudnn_library(cudnn_heuristic)
+
+    target_link_libraries(
+        CUDNN::cudnn_all
+        INTERFACE
+        CUDNN::cudnn_adv
+        CUDNN::cudnn_ops
+        CUDNN::cudnn_cnn
+        CUDNN::cudnn_graph
+        CUDNN::cudnn_engines_runtime_compiled
+        CUDNN::cudnn_engines_precompiled
+        CUDNN::cudnn_heuristic
+    )
+endif()
+
+mark_as_advanced(CUDNN_INCLUDE_DIR)
diff --git a/cmake/external/cudnn_frontend.cmake b/cmake/external/cudnn_frontend.cmake
@@ -0,0 +1,12 @@
+include(FetchContent)
+FetchContent_Declare(
+  cudnn_frontend
+  URL ${DEP_URL_cudnn_frontend}
+  URL_HASH SHA1=${DEP_SHA1_cudnn_frontend}
+)
+
+set(CUDNN_FRONTEND_BUILD_SAMPLES OFF)
+set(CUDNN_FRONTEND_BUILD_UNIT_TESTS OFF)
+set(CUDNN_FRONTEND_BUILD_PYTHON_BINDINGS OFF)
+set(CUDNN_PATH ${onnxruntime_CUDNN_HOME})
+FetchContent_MakeAvailable(cudnn_frontend)
diff --git a/cmake/external/dml.cmake b/cmake/external/dml.cmake
@@ -41,7 +41,7 @@ if (NOT onnxruntime_USE_CUSTOM_DIRECTML)
   set(NUGET_CONFIG ${PROJECT_SOURCE_DIR}/../NuGet.config)
   set(PACKAGES_CONFIG ${PROJECT_SOURCE_DIR}/../packages.config)
   get_filename_component(PACKAGES_DIR ${CMAKE_CURRENT_BINARY_DIR}/../packages ABSOLUTE)
-  set(DML_PACKAGE_DIR ${PACKAGES_DIR}/Microsoft.AI.DirectML.1.15.0)
+  set(DML_PACKAGE_DIR ${PACKAGES_DIR}/Microsoft.AI.DirectML.1.15.1)
 
   # Restore nuget packages, which will pull down the DirectML redist package.
   add_custom_command(

diff --git a/cmake/external/onnxruntime_external_deps.cmake b/cmake/external/onnxruntime_external_deps.cmake
@@ -587,20 +587,16 @@ endif()
 
 message("Finished fetching external dependencies")
 
-
 set(onnxruntime_LINK_DIRS )
+
 if (onnxruntime_USE_CUDA)
-      #TODO: combine onnxruntime_CUDNN_HOME and onnxruntime_CUDA_HOME, assume they are the same
       find_package(CUDAToolkit REQUIRED)
-      if (WIN32)
-        if(onnxruntime_CUDNN_HOME)
-          list(APPEND onnxruntime_LINK_DIRS ${onnxruntime_CUDNN_HOME}/lib ${onnxruntime_CUDNN_HOME}/lib/x64)
-        endif()
-      else()
-        if(onnxruntime_CUDNN_HOME)
-          list(APPEND onnxruntime_LINK_DIRS  ${onnxruntime_CUDNN_HOME}/lib ${onnxruntime_CUDNN_HOME}/lib64)
-        endif()
+
+      if(onnxruntime_CUDNN_HOME)
+        file(TO_CMAKE_PATH ${onnxruntime_CUDNN_HOME} onnxruntime_CUDNN_HOME)
+        set(CUDNN_PATH ${onnxruntime_CUDNN_HOME})
       endif()
+      include(cuDNN)
 endif()
 
 if(onnxruntime_USE_SNPE)

diff --git a/cmake/onnxruntime.cmake b/cmake/onnxruntime.cmake
@@ -38,10 +38,14 @@ function(get_c_cxx_api_headers HEADERS_VAR)
 
   # need to add header files for enabled EPs
   foreach(f ${ONNXRUNTIME_PROVIDER_NAMES})
-    file(GLOB _provider_headers CONFIGURE_DEPENDS
-      "${REPO_ROOT}/include/onnxruntime/core/providers/${f}/*.h"
-    )
-    list(APPEND _headers ${_provider_headers})
+    # The header files in include/onnxruntime/core/providers/cuda directory cannot be flattened to the same directory 
+    # with onnxruntime_c_api.h . Most other EPs probably also do not work in this way.
+    if((NOT f STREQUAL cuda) AND (NOT f STREQUAL rocm))
+      file(GLOB _provider_headers CONFIGURE_DEPENDS
+        "${REPO_ROOT}/include/onnxruntime/core/providers/${f}/*.h"
+      )
+      list(APPEND _headers ${_provider_headers})
+    endif()
   endforeach()
 
   set(${HEADERS_VAR} ${_headers} PARENT_SCOPE)

diff --git a/cmake/onnxruntime_framework.cmake b/cmake/onnxruntime_framework.cmake
@@ -69,7 +69,7 @@ endif()
 if(onnxruntime_USE_TENSORRT OR onnxruntime_USE_NCCL)
 # TODO: for now, core framework depends on CUDA. It should be moved to TensorRT EP
 # TODO: provider_bridge_ort.cc should not include nccl.h
-target_include_directories(onnxruntime_framework PRIVATE ${ONNXRUNTIME_ROOT} ${eigen_INCLUDE_DIRS} ${onnxruntime_CUDNN_HOME}/include PUBLIC ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES})
+target_include_directories(onnxruntime_framework PRIVATE ${ONNXRUNTIME_ROOT} ${eigen_INCLUDE_DIRS} PUBLIC ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES})
 else()
 target_include_directories(onnxruntime_framework PRIVATE ${ONNXRUNTIME_ROOT} ${eigen_INCLUDE_DIRS} PUBLIC ${CMAKE_CURRENT_BINARY_DIR})
 endif()

diff --git a/cmake/onnxruntime_mlas.cmake b/cmake/onnxruntime_mlas.cmake
@@ -555,8 +555,17 @@ else()
           ${MLAS_SRC_DIR}/intrinsics/avx2/qdwconv_avx2.cpp
           ${MLAS_SRC_DIR}/sqnbitgemm_kernel_avx2.cpp
         )
-        set_source_files_properties(${mlas_platform_srcs_avx2} PROPERTIES COMPILE_FLAGS "-mavx2 -mfma")
 
+message(STATUS "CMAKE_CXX_COMPILER_ID: ${CMAKE_CXX_COMPILER_ID}")
+message(STATUS "CMAKE_CXX_COMPILER_VERSION: ${CMAKE_CXX_COMPILER_VERSION}")
+
+if(NOT "${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU" OR CMAKE_CXX_COMPILER_VERSION VERSION_GREATER "10")
+          message(STATUS "Using -mavx2 -mfma -mavxvnni flags")
+          set_source_files_properties(${mlas_platform_srcs_avx2} PROPERTIES COMPILE_FLAGS "-mavx2 -mfma -mavxvnni")
+else()
+          message(STATUS "Using -mavx2 -mfma flags")
+          set_source_files_properties(${mlas_platform_srcs_avx2} PROPERTIES COMPILE_FLAGS "-mavx2 -mfma")
+endif()
         set(mlas_platform_srcs_avx512f
           ${MLAS_SRC_DIR}/x86_64/DgemmKernelAvx512F.S
           ${MLAS_SRC_DIR}/x86_64/SgemmKernelAvx512F.S
@@ -575,7 +584,7 @@ else()
           ${MLAS_SRC_DIR}/x86_64/ConvSymKernelAvx512Core.S
           ${MLAS_SRC_DIR}/sqnbitgemm_kernel_avx512.cpp
         )
-        set_source_files_properties(${mlas_platform_srcs_avx512core} PROPERTIES COMPILE_FLAGS "-mavx512bw -mavx512dq -mavx512vl")
+        set_source_files_properties(${mlas_platform_srcs_avx512core} PROPERTIES COMPILE_FLAGS "-mfma -mavx512vnni -mavx512bw -mavx512dq -mavx512vl")
 
         set(mlas_platform_srcs_avx512vnni
           ${MLAS_SRC_DIR}/sqnbitgemm_kernel_avx512vnni.cpp

diff --git a/cmake/onnxruntime_providers_cpu.cmake b/cmake/onnxruntime_providers_cpu.cmake
@@ -219,6 +219,7 @@ if (onnxruntime_ENABLE_TRAINING)
 endif()
 
 install(FILES ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/providers/cpu/cpu_provider_factory.h  DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/)
+install(FILES ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/providers/resource.h ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/providers/custom_op_context.h DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/core/providers)
 set_target_properties(onnxruntime_providers PROPERTIES LINKER_LANGUAGE CXX)
 set_target_properties(onnxruntime_providers PROPERTIES FOLDER "ONNXRuntime")
 

diff --git a/cmake/onnxruntime_providers_cuda.cmake b/cmake/onnxruntime_providers_cuda.cmake
@@ -197,12 +197,16 @@
       target_compile_definitions(${target} PRIVATE USE_CUDA_MINIMAL)
       target_link_libraries(${target} PRIVATE ${ABSEIL_LIBS} ${ONNXRUNTIME_PROVIDERS_SHARED} Boost::mp11 safeint_interface CUDA::cudart)
     else()
-      target_link_libraries(${target} PRIVATE CUDA::cublasLt CUDA::cublas cudnn CUDA::curand CUDA::cufft CUDA::cudart
-              ${ABSEIL_LIBS} ${ONNXRUNTIME_PROVIDERS_SHARED} Boost::mp11 safeint_interface)
-      if(onnxruntime_CUDNN_HOME)
-          target_include_directories(${target} PRIVATE ${onnxruntime_CUDNN_HOME}/include)
-          target_link_directories(${target} PRIVATE ${onnxruntime_CUDNN_HOME}/lib)
+      include(cudnn_frontend) # also defines CUDNN::*
+      if (onnxruntime_USE_CUDA_NHWC_OPS)
+        if(CUDNN_MAJOR_VERSION GREATER 8)
+          add_compile_definitions(ENABLE_CUDA_NHWC_OPS)
+        else()
+          message( WARNING "To compile with NHWC ops enabled please compile against cuDNN 9 or newer." )
+        endif()
       endif()
+      target_link_libraries(${target} PRIVATE CUDA::cublasLt CUDA::cublas CUDNN::cudnn_all cudnn_frontend CUDA::curand CUDA::cufft CUDA::cudart
+              ${ABSEIL_LIBS} ${ONNXRUNTIME_PROVIDERS_SHARED} Boost::mp11 safeint_interface)
     endif()
 
     if (onnxruntime_USE_TRITON_KERNEL)
@@ -289,8 +293,15 @@
     config_cuda_provider_shared_module(onnxruntime_providers_cuda_obj)
   endif()
   config_cuda_provider_shared_module(onnxruntime_providers_cuda)
-
+  # Cannot use glob because the file cuda_provider_options.h should not be exposed out.
+  set(ONNXRUNTIME_CUDA_PROVIDER_PUBLIC_HEADERS
+        "${REPO_ROOT}/include/onnxruntime/core/providers/cuda/cuda_context.h"
+        "${REPO_ROOT}/include/onnxruntime/core/providers/cuda/cuda_resource.h"
+      )
+  set_target_properties(onnxruntime_providers_cuda PROPERTIES
+    PUBLIC_HEADER "${ONNXRUNTIME_CUDA_PROVIDER_PUBLIC_HEADERS}")
   install(TARGETS onnxruntime_providers_cuda
+          PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/core/providers/cuda
           ARCHIVE  DESTINATION ${CMAKE_INSTALL_LIBDIR}
           LIBRARY  DESTINATION ${CMAKE_INSTALL_LIBDIR}
           RUNTIME  DESTINATION ${CMAKE_INSTALL_BINDIR})
diff --git a/cmake/onnxruntime_providers_rocm.cmake b/cmake/onnxruntime_providers_rocm.cmake
@@ -223,8 +223,13 @@
   if (onnxruntime_ENABLE_ATEN)
     target_compile_definitions(onnxruntime_providers_rocm PRIVATE ENABLE_ATEN)
   endif()
-
+  file(GLOB ONNXRUNTIME_ROCM_PROVIDER_PUBLIC_HEADERS CONFIGURE_DEPENDS
+        "${REPO_ROOT}/include/onnxruntime/core/providers/rocm/*.h"
+      )
+  set_target_properties(onnxruntime_providers_rocm PROPERTIES
+    PUBLIC_HEADER "${ONNXRUNTIME_ROCM_PROVIDER_PUBLIC_HEADERS}")
   install(TARGETS onnxruntime_providers_rocm
+          PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/core/providers/rocm
           ARCHIVE  DESTINATION ${CMAKE_INSTALL_LIBDIR}
           LIBRARY  DESTINATION ${CMAKE_INSTALL_LIBDIR}
           RUNTIME  DESTINATION ${CMAKE_INSTALL_BINDIR})
diff --git a/cmake/onnxruntime_providers_tensorrt.cmake b/cmake/onnxruntime_providers_tensorrt.cmake
@@ -159,7 +159,7 @@
   if(onnxruntime_CUDA_MINIMAL)
     set(trt_link_libs ${CMAKE_DL_LIBS} ${TENSORRT_LIBRARY})
   else()
-    set(trt_link_libs cudnn cublas ${CMAKE_DL_LIBS} ${TENSORRT_LIBRARY})
+    set(trt_link_libs CUDNN::cudnn_all cublas ${CMAKE_DL_LIBS} ${TENSORRT_LIBRARY})
   endif()
   file(GLOB_RECURSE onnxruntime_providers_tensorrt_cc_srcs CONFIGURE_DEPENDS
     "${ONNXRUNTIME_ROOT}/core/providers/tensorrt/*.h"
@@ -183,9 +183,6 @@
   endif()
   target_include_directories(onnxruntime_providers_tensorrt PRIVATE ${ONNXRUNTIME_ROOT} ${CMAKE_CURRENT_BINARY_DIR} ${eigen_INCLUDE_DIRS}
     PUBLIC ${CUDAToolkit_INCLUDE_DIRS})
-  if(onnxruntime_CUDNN_HOME)
-    target_include_directories(onnxruntime_providers_tensorrt PRIVATE ${onnxruntime_CUDNN_HOME}/include)
-  endif()
 
   # ${CMAKE_CURRENT_BINARY_DIR} is so that #include "onnxruntime_config.h" inside tensor_shape.h is found
   set_target_properties(onnxruntime_providers_tensorrt PROPERTIES LINKER_LANGUAGE CUDA)

diff --git a/cmake/onnxruntime_python.cmake b/cmake/onnxruntime_python.cmake
@@ -98,11 +98,7 @@ endif()
 onnxruntime_add_include_to_target(onnxruntime_pybind11_state Python::Module Python::NumPy)
 target_include_directories(onnxruntime_pybind11_state PRIVATE ${ONNXRUNTIME_ROOT} ${pybind11_INCLUDE_DIRS})
 if(onnxruntime_USE_CUDA)
-    target_include_directories(onnxruntime_pybind11_state PRIVATE ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES})
-    # cudnn_home is optional for Window when cuda and cudnn are installed in the same directory.
-    if(onnxruntime_CUDNN_HOME)
-      target_include_directories(onnxruntime_pybind11_state PRIVATE ${onnxruntime_CUDNN_HOME}/include)
-    endif()
+    target_include_directories(onnxruntime_pybind11_state PRIVATE ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES} ${CUDNN_INCLUDE_DIR})
 endif()
 if(onnxruntime_USE_CANN)
     target_include_directories(onnxruntime_pybind11_state PRIVATE ${onnxruntime_CANN_HOME}/include)
@@ -512,7 +508,6 @@ file(GLOB onnxruntime_ort_format_model_srcs CONFIGURE_DEPENDS
 )
 file(GLOB onnxruntime_mobile_helpers_srcs CONFIGURE_DEPENDS
     ${REPO_ROOT}/tools/python/util/mobile_helpers/*.py
-    ${REPO_ROOT}/tools/ci_build/github/android/mobile_package.required_operators.config
     ${REPO_ROOT}/tools/ci_build/github/android/nnapi_supported_ops.md
     ${REPO_ROOT}/tools/ci_build/github/apple/coreml_supported_mlprogram_ops.md
     ${REPO_ROOT}/tools/ci_build/github/apple/coreml_supported_neuralnetwork_ops.md