Backmerging with Msft commits

.github/workflows/windows_webgpu.yml

@@ -22,6 +22,7 @@ jobs:
     strategy:
       matrix:
         vcpkg_option: [novcpkg, vcpkg]
+        wgsl_template: [static, dynamic]
     env:
       OrtPackageId: Microsoft.ML.OnnxRuntime
       OnnxRuntimeBuildDirectory: ${{ github.workspace }}
@@ -123,6 +124,7 @@ jobs:
             --build_nodejs `
             --build_java `
             --use_webgpu `
+            --wgsl_template ${{ matrix.wgsl_template }} `
             ${{ matrix.vcpkg_option == 'vcpkg' && '--use_vcpkg' || '' }} `
             --cmake_extra_defines `
             onnxruntime_BUILD_UNIT_TESTS=ON `

cmake/CMakeLists.txt

@@ -151,6 +151,7 @@ option(onnxruntime_DISABLE_SPARSE_TENSORS "Disable sparse tensors data types" OF
 option(onnxruntime_DISABLE_OPTIONAL_TYPE "Disable optional type" OFF)
 option(onnxruntime_DISABLE_FLOAT8_TYPES "Disable float 8 types" OFF)
 option(onnxruntime_MINIMAL_BUILD "Exclude as much as possible from the build. Support ORT format models. No support for ONNX format models." OFF)
+option(onnxruntime_CLIENT_PACKAGE_BUILD "Enables default settings that are more appropriate for client/on-device workloads." OFF)
 cmake_dependent_option(onnxruntime_DISABLE_RTTI "Disable RTTI" ON "NOT onnxruntime_ENABLE_PYTHON;NOT onnxruntime_USE_CUDA" OFF)
 # For now onnxruntime_DISABLE_EXCEPTIONS will only work with onnxruntime_MINIMAL_BUILD, more changes (ONNX, non-CPU EP, ...) are required to run this standalone
 cmake_dependent_option(onnxruntime_DISABLE_EXCEPTIONS "Disable exception handling. Requires onnxruntime_MINIMAL_BUILD currently." ON "onnxruntime_MINIMAL_BUILD;NOT onnxruntime_ENABLE_PYTHON" OFF)

cmake/adjust_global_compile_flags.cmake

@@ -95,6 +95,11 @@ if (onnxruntime_MINIMAL_BUILD)
   endif()
 endif()
 
+# ORT build with default settings more appropriate for client/on-device workloads.
+if (onnxruntime_CLIENT_PACKAGE_BUILD)
+  add_compile_definitions(ORT_CLIENT_PACKAGE_BUILD)
+endif()
+
 if (onnxruntime_ENABLE_LTO)
     include(CheckIPOSupported)
     check_ipo_supported(RESULT ipo_enabled OUTPUT ipo_output)

cmake/external/onnxruntime_external_deps.cmake

@@ -774,13 +774,24 @@ if (onnxruntime_USE_WEBGPU)
   endif()
 
   if (NOT CMAKE_SYSTEM_NAME STREQUAL "Emscripten" AND onnxruntime_WGSL_TEMPLATE STREQUAL "dynamic")
-    onnxruntime_fetchcontent_declare(
-      duktape
-      URL ${DEP_URL_duktape}
-      URL_HASH SHA1=${DEP_SHA1_duktape}
-      EXCLUDE_FROM_ALL
-    )
-    onnxruntime_fetchcontent_makeavailable(duktape)
+    if(onnxruntime_USE_VCPKG)
+      find_package(unofficial-duktape CONFIG REQUIRED)
+      add_library(duktape_static ALIAS unofficial::duktape::duktape)
+    else()
+      onnxruntime_fetchcontent_declare(
+        duktape
+        URL ${DEP_URL_duktape}
+        URL_HASH SHA1=${DEP_SHA1_duktape}
+        EXCLUDE_FROM_ALL
+      )
+      onnxruntime_fetchcontent_makeavailable(duktape)
+
+      if(NOT TARGET duktape_static)
+        add_library(duktape_static STATIC "${duktape_SOURCE_DIR}/src/duktape.c")
+        target_compile_features(duktape_static PRIVATE c_std_99)
+        target_include_directories(duktape_static INTERFACE $<BUILD_INTERFACE:${duktape_SOURCE_DIR}/src>)
+      endif()
+    endif()
   endif()
 endif()
 

cmake/onnxruntime_mlas.cmake

@@ -31,6 +31,7 @@ onnxruntime_add_static_library(onnxruntime_mlas
   ${MLAS_SRC_DIR}/eltwise.cpp
   ${MLAS_SRC_DIR}/erf.cpp
   ${MLAS_SRC_DIR}/compute.cpp
+  ${MLAS_SRC_DIR}/dequantize.cpp
   ${MLAS_SRC_DIR}/quantize.cpp
   ${MLAS_SRC_DIR}/qgemm_kernel_default.cpp
   ${MLAS_SRC_DIR}/qladd.cpp

cmake/onnxruntime_providers_tensorrt.cmake

@@ -72,26 +72,21 @@
   endif()
 
   # TensorRT 10 GA onwards, the TensorRT libraries will have major version appended to the end on Windows,
-  # for example, nvinfer_10.dll, nvinfer_plugin_10.dll, nvonnxparser_10.dll ...
+  # for example, nvinfer_10.dll, nvonnxparser_10.dll ...
   if (WIN32 AND TRT_GREATER_OR_EQUAL_TRT_10_GA)
     set(NVINFER_LIB "nvinfer_${NV_TENSORRT_MAJOR}")
-    set(NVINFER_PLUGIN_LIB "nvinfer_plugin_${NV_TENSORRT_MAJOR}")
     set(PARSER_LIB "nvonnxparser_${NV_TENSORRT_MAJOR}")
   endif()
 
   if (NOT NVINFER_LIB)
      set(NVINFER_LIB "nvinfer")
   endif()
 
-  if (NOT NVINFER_PLUGIN_LIB)
-     set(NVINFER_PLUGIN_LIB "nvinfer_plugin")
-  endif()
-
   if (NOT PARSER_LIB)
      set(PARSER_LIB "nvonnxparser")
   endif()
 
-  MESSAGE(STATUS "Looking for ${NVINFER_LIB} and ${NVINFER_PLUGIN_LIB}")
+  MESSAGE(STATUS "Looking for ${NVINFER_LIB}")
 
   find_library(TENSORRT_LIBRARY_INFER ${NVINFER_LIB}
     HINTS ${TENSORRT_ROOT}
@@ -101,14 +96,6 @@
     MESSAGE(STATUS "Can't find ${NVINFER_LIB}")
   endif()
 
-  find_library(TENSORRT_LIBRARY_INFER_PLUGIN ${NVINFER_PLUGIN_LIB}
-    HINTS  ${TENSORRT_ROOT}
-    PATH_SUFFIXES lib lib64 lib/x64)
-
-  if (NOT TENSORRT_LIBRARY_INFER_PLUGIN)
-    MESSAGE(STATUS "Can't find ${NVINFER_PLUGIN_LIB}")
-  endif()
-
   if (onnxruntime_USE_TENSORRT_BUILTIN_PARSER)
     MESSAGE(STATUS "Looking for ${PARSER_LIB}")
 
@@ -120,7 +107,7 @@
       MESSAGE(STATUS "Can't find ${PARSER_LIB}")
     endif()
 
-    set(TENSORRT_LIBRARY ${TENSORRT_LIBRARY_INFER} ${TENSORRT_LIBRARY_INFER_PLUGIN} ${TENSORRT_LIBRARY_NVONNXPARSER})
+    set(TENSORRT_LIBRARY ${TENSORRT_LIBRARY_INFER} ${TENSORRT_LIBRARY_NVONNXPARSER})
     MESSAGE(STATUS "Find TensorRT libs at ${TENSORRT_LIBRARY}")
   else()
     if (TRT_GREATER_OR_EQUAL_TRT_10_GA)
@@ -153,15 +140,15 @@
     endif()
     # Static libraries are just nvonnxparser_static on all platforms
     set(onnxparser_link_libs nvonnxparser_static)
-    set(TENSORRT_LIBRARY ${TENSORRT_LIBRARY_INFER} ${TENSORRT_LIBRARY_INFER_PLUGIN})
+    set(TENSORRT_LIBRARY ${TENSORRT_LIBRARY_INFER})
     MESSAGE(STATUS "Find TensorRT libs at ${TENSORRT_LIBRARY}")
   endif()
 
   # ${TENSORRT_LIBRARY} is empty if we link nvonnxparser_static.
   # nvonnxparser_static is linked against tensorrt libraries in onnx-tensorrt
   # See https://github.com/onnx/onnx-tensorrt/blob/8af13d1b106f58df1e98945a5e7c851ddb5f0791/CMakeLists.txt#L121
   # However, starting from TRT 10 GA, nvonnxparser_static doesn't link against tensorrt libraries.
-  # Therefore, the above code finds ${TENSORRT_LIBRARY_INFER} and ${TENSORRT_LIBRARY_INFER_PLUGIN}.
+  # Therefore, the above code finds ${TENSORRT_LIBRARY_INFER}.
   if(onnxruntime_CUDA_MINIMAL)
     set(trt_link_libs ${CMAKE_DL_LIBS} ${TENSORRT_LIBRARY})
   else()