merge main

.github/workflows/gradle-wrapper-validation.yml

@@ -11,4 +11,4 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: gradle/wrapper-validation-action@v1
+      - uses: gradle/wrapper-validation-action@v2

.github/workflows/labeler.yml

@@ -3,11 +3,14 @@ on:
   issues:
     types: [opened, edited]
 
+permissions:
+  issues: write
+
 jobs:
   triage:
     runs-on: ubuntu-latest
     steps:
-    - uses: github/issue-labeler@v3.3
+    - uses: github/issue-labeler@v3.4
       with:
         repo-token: "${{ secrets.GITHUB_TOKEN }}"
         configuration-path: .github/labeler.yml

.github/workflows/publish-csharp-apidocs.yml

@@ -37,7 +37,7 @@ jobs:
         wget https://github.com/dotnet/docfx/releases/download/v${DOCFXVERSION}/docfx-linux-x64-v${DOCFXVERSION}.zip -O build/docfx/docfx.zip
         unzip build/docfx/docfx.zip -d build/docfx
     - name: Install NuGet
-      uses: nuget/setup-nuget@v1
+      uses: nuget/setup-nuget@v2
     - name: Build Documentation
       run: |
         build/docfx/docfx metadata csharp/ApiDocs/docfx.json

.github/workflows/publish-java-apidocs.yml

@@ -30,7 +30,7 @@ jobs:
           java-version: '11'
           distribution: 'adopt'
       - name: Build with Gradle
-        uses: gradle/gradle-build-action@v2
+        uses: gradle/gradle-build-action@v3
         with:
           build-root-directory: java
           gradle-executable: java/gradlew

.github/workflows/stale.yml

@@ -13,7 +13,7 @@ jobs:
       issues: write
       pull-requests: write
     steps:
-      - uses: actions/stale@v9.0.0
+      - uses: actions/stale@v8
         with:
           # Comma separated list of labels that can be assigned to issues to exclude them from being marked as stale
           exempt-issue-labels: contributions welcome, feature request, regression

.lintrunner.toml

@@ -132,6 +132,7 @@ exclude_patterns = [
     'onnxruntime/core/flatbuffers/schema/*.fbs.h', # Generated code
     'onnxruntime/core/graph/contrib_ops/quantization_defs.cc',
     'onnxruntime/core/mlas/**', # Contains assembly code
+    'onnxruntime/core/mickey/cutlass_ext/**', # CUTLASS lib recommends NO automatic code formatting
     'winml/lib/Api.Image/shaders/**',  # Contains data chunks
 ]
 command = [

.pipelines/windowsai-steps.yml

@@ -80,11 +80,11 @@ jobs:
 
     # must call vsdevcmd first to add cmake to PATH
     - script: |
-        curl -O -L https://github.com/Kitware/CMake/releases/download/v3.26.3/cmake-3.26.3-windows-x86_64.zip
-        7z x cmake-3.26.3-windows-x86_64.zip
+        curl -O -L https://github.com/Kitware/CMake/releases/download/v3.28.3/cmake-3.28.3-windows-x86_64.zip
+        7z x cmake-3.28.3-windows-x86_64.zip
         set PYTHONHOME=$(Build.BinariesDirectory)\${{ parameters.PythonPackageName }}.3.9.7\tools
         set PYTHONPATH=$(Build.BinariesDirectory)\${{ parameters.PythonPackageName }}.3.9.7\tools
-        $(Build.BinariesDirectory)\${{ parameters.PythonPackageName }}.3.9.7\tools\python.exe "$(Build.SourcesDirectory)\tools\ci_build\build.py" --build_dir $(Build.BinariesDirectory) --parallel --use_binskim_compliant_compile_flags --build_shared_lib --enable_onnx_tests --ms_experimental --use_dml --use_winml --cmake_generator "Visual Studio 17 2022" --update --config RelWithDebInfo --enable_lto --use_telemetry --disable_rtti --enable_wcos $(BuildFlags) --cmake_extra_defines "CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO=/PROFILE" "CMAKE_SHARED_LINKER_FLAGS_RELWITHDEBINFO=/PROFILE" CMAKE_SYSTEM_VERSION=10.0.19041.0 --cmake_path $(Build.BinariesDirectory)\cmake-3.26.3-windows-x86_64\bin\cmake.exe --ctest_path $(Build.BinariesDirectory)\cmake-3.26.3-windows-x86_64\bin\ctest.exe
+        $(Build.BinariesDirectory)\${{ parameters.PythonPackageName }}.3.9.7\tools\python.exe "$(Build.SourcesDirectory)\tools\ci_build\build.py" --build_dir $(Build.BinariesDirectory) --parallel --use_binskim_compliant_compile_flags --build_shared_lib --enable_onnx_tests --ms_experimental --use_dml --use_winml --cmake_generator "Visual Studio 17 2022" --update --config RelWithDebInfo --enable_lto --use_telemetry --disable_rtti --enable_wcos --windows_sdk_version "10.0.22621.0" $(BuildFlags) --cmake_extra_defines "CMAKE_EXE_LINKER_FLAGS_RELWITHDEBINFO=/PROFILE" "CMAKE_SHARED_LINKER_FLAGS_RELWITHDEBINFO=/PROFILE"  --cmake_path $(Build.BinariesDirectory)\cmake-3.28.3-windows-x86_64\bin\cmake.exe --ctest_path $(Build.BinariesDirectory)\cmake-3.28.3-windows-x86_64\bin\ctest.exe
       workingDirectory: '$(Build.BinariesDirectory)'
       displayName: 'Generate cmake config'
 

.vscode/settings.json

@@ -21,5 +21,8 @@
     "cpplint.filters": [
         "-build/include_subdir",
         "-runtime/references"
-    ]
+    ],
+    "files.associations": {
+        "span": "cpp"
+    }
 }

CITATION.cff

@@ -3,8 +3,7 @@ title: ONNX Runtime
 message: "Please use this information to cite ONNX Runtime in
   research or other publications."
 authors:
-  - affiliation: Microsoft Corporation
-    given-names: ONNX Runtime developers
+  - name: ONNX Runtime developers
 date-released: 2018-11-29
 url: "https://onnxruntime.ai"
 repository-code: "https://github.com/microsoft/onnxruntime"

cgmanifests/generated/cgmanifest.json

@@ -42,6 +42,16 @@
         "comments": "abseil_cpp"
       }
     },
+    {
+      "component": {
+        "type": "git",
+        "git": {
+          "commitHash": "dbb0094fd0cb936469e35320bf37e866ef7a1da4",
+          "repositoryUrl": "https://github.com/apple/coremltools.git"
+        },
+        "comments": "coremltools"
+      }
+    },
     {
       "component": {
         "type": "git",
@@ -106,7 +116,7 @@
       "component": {
         "type": "git",
         "git": {
-          "commitHash": "361e8d1cfe0c6c36d30b39f1b61302ece5507320",
+          "commitHash": "344117638c8ff7e239044fd0fa7085839fc03021",
           "repositoryUrl": "https://github.com/google/benchmark.git"
         },
         "comments": "google_benchmark"

cmake/CMakeLists.txt

@@ -88,7 +88,7 @@ option(onnxruntime_USE_QNN "Build with QNN support" OFF)
 option(onnxruntime_USE_SNPE "Build with SNPE support" OFF)
 option(onnxruntime_USE_RKNPU "Build with RKNPU support" OFF)
 option(onnxruntime_USE_DNNL "Build with DNNL support" OFF)
-option(onnxruntime_USE_NEURAL_SPEED "Build with Neural Speed support" ON)
+option(onnxruntime_USE_NEURAL_SPEED "Build with Neural Speed support" OFF)
 option(onnxruntime_USE_JSEP "Build with JavaScript implemented kernels support" OFF)
 option(onnxruntime_BUILD_UNIT_TESTS "Build ONNXRuntime unit tests" ON)
 option(onnxruntime_BUILD_CSHARP "Build C# library" OFF)
@@ -117,8 +117,7 @@ option(onnxruntime_CROSS_COMPILING "Cross compiling onnx runtime" OFF)
 option(onnxruntime_GCOV_COVERAGE "Compile with options necessary to run code coverage" OFF)
 option(onnxruntime_DONT_VECTORIZE "Do not vectorize operations in Eigen" OFF)
 
-#It's preferred to turn it OFF when onnxruntime is dynamically linked to PROTOBUF. But Tensort always required the full version of protobuf.
-cmake_dependent_option(onnxruntime_USE_FULL_PROTOBUF "Link to libprotobuf instead of libprotobuf-lite when this option is ON" OFF "NOT onnxruntime_USE_TENSORRT" ON)
+option(onnxruntime_USE_FULL_PROTOBUF "Link to libprotobuf instead of libprotobuf-lite when this option is ON" OFF)
 option(tensorflow_C_PACKAGE_PATH "Path to tensorflow C package installation dir")
 option(onnxruntime_ENABLE_LANGUAGE_INTEROP_OPS "Enable operator implemented in language other than cpp" OFF)
 option(onnxruntime_DEBUG_NODE_INPUTS_OUTPUTS "Dump debug information about node inputs and outputs when executing the model." OFF)
@@ -325,15 +324,27 @@ if (onnxruntime_USE_ROCM)
   endif()
 
   # replicate strategy used by pytorch to get ROCM_VERSION
-  # https://github.com/pytorch/pytorch/blob/8eb21488fdcdb8b0e6fa2e46179b5fa6c42e75af/cmake/public/LoadHIP.cmake#L153-L173
-  file(READ "${onnxruntime_ROCM_HOME}/.info/version-dev" ROCM_VERSION_DEV_RAW)
-  string(REGEX MATCH "^([0-9]+)\.([0-9]+)\.([0-9]+)-.*$" ROCM_VERSION_DEV_MATCH ${ROCM_VERSION_DEV_RAW})
-  if (ROCM_VERSION_DEV_MATCH)
+  # https://github.com/pytorch/pytorch/blob/5c5b71b6eebae76d744261715231093e62f0d090/cmake/public/LoadHIP.cmake
+  # with modification
+  if (EXISTS "${onnxruntime_ROCM_HOME}/.info/version-dev")
+    file(READ "${onnxruntime_ROCM_HOME}/.info/version-dev" ROCM_VERSION_DEV_RAW)
+    string(REGEX MATCH "^([0-9]+)\.([0-9]+)\.([0-9]+)-.*$" ROCM_VERSION_MATCH ${ROCM_VERSION_DEV_RAW})
+  elseif (EXISTS "${onnxruntime_ROCM_HOME}/include/rocm_version.h")
+    file(READ "${onnxruntime_ROCM_HOME}/include/rocm_version.h" ROCM_VERSION_H_RAW)
+    string(REGEX MATCH "\"([0-9]+)\.([0-9]+)\.([0-9]+).*\"" ROCM_VERSION_MATCH ${ROCM_VERSION_H_RAW})
+  elseif (EXISTS "${onnxruntime_ROCM_HOME}/include/rocm-core/rocm_version.h")
+    file(READ "${onnxruntime_ROCM_HOME}/include/rocm-core/rocm_version.h" ROCM_VERSION_H_RAW)
+    string(REGEX MATCH "\"([0-9]+)\.([0-9]+)\.([0-9]+).*\"" ROCM_VERSION_MATCH ${ROCM_VERSION_H_RAW})
+  endif()
+
+  if (ROCM_VERSION_MATCH)
     set(ROCM_VERSION_DEV_MAJOR ${CMAKE_MATCH_1})
     set(ROCM_VERSION_DEV_MINOR ${CMAKE_MATCH_2})
     set(ROCM_VERSION_DEV_PATCH ${CMAKE_MATCH_3})
     set(ROCM_VERSION_DEV "${ROCM_VERSION_DEV_MAJOR}.${ROCM_VERSION_DEV_MINOR}.${ROCM_VERSION_DEV_PATCH}")
     math(EXPR ROCM_VERSION_DEV_INT "(${ROCM_VERSION_DEV_MAJOR}*10000) + (${ROCM_VERSION_DEV_MINOR}*100) + ${ROCM_VERSION_DEV_PATCH}")
+  else()
+    message(FATAL_ERROR "Cannot determine ROCm version string")
   endif()
   message("\n***** ROCm version from ${onnxruntime_ROCM_HOME}/.info/version-dev ****\n")
   message("ROCM_VERSION_DEV: ${ROCM_VERSION_DEV}")
@@ -641,6 +652,7 @@ else()
   check_cxx_compiler_flag(-Wunused-but-set-variable HAS_UNUSED_BUT_SET_VARIABLE)
   check_cxx_compiler_flag(-Wunused-variable HAS_UNUSED_VARIABLE)
   check_cxx_compiler_flag(-Wuseless-cast HAS_USELESS_CAST)
+  check_cxx_compiler_flag(-Wstringop-overflow HAS_STRINGOP_OVERFLOW)
   check_function_exists(reallocarray HAS_REALLOCARRAY)
   if (NOT APPLE AND NOT CMAKE_SYSTEM_NAME STREQUAL "Emscripten" AND onnxruntime_target_platform STREQUAL "aarch64")
    check_cxx_compiler_flag(-march=armv8.2-a+bf16 HAS_ARM64_BFLOAT16)
@@ -715,6 +727,9 @@ if (onnxruntime_USE_CUDA)
     set(onnxruntime_USE_FLASH_ATTENTION OFF)
     set(onnxruntime_USE_MEMORY_EFFICIENT_ATTENTION OFF)
   endif()
+  if (CMAKE_CUDA_COMPILER_VERSION VERSION_LESS 11.4)
+    message( FATAL_ERROR "Failed build due to CUDA compiler version < 11.4")
+  endif()
 else()
   set(onnxruntime_USE_FLASH_ATTENTION OFF)
   set(onnxruntime_USE_MEMORY_EFFICIENT_ATTENTION OFF)
@@ -735,8 +750,8 @@ if (onnxruntime_USE_CUDA)
       list(APPEND ORT_PROVIDER_FLAGS -DUSE_MEMORY_EFFICIENT_ATTENTION=1)
       list(APPEND ORT_PROVIDER_CMAKE_FLAGS -Donnxruntime_USE_MEMORY_EFFICIENT_ATTENTION=1)
     endif()
-
 endif()
+
 if (onnxruntime_USE_VITISAI)
     list(APPEND ORT_PROVIDER_FLAGS -DUSE_VITISAI=1)
     list(APPEND ORT_PROVIDER_CMAKE_FLAGS -Donnxruntime_USE_VITISAI=1)
@@ -984,9 +999,12 @@ function(onnxruntime_set_compile_flags target_name)
       foreach(FLAG ${ORT_WARNING_FLAGS})
         target_compile_options(${target_name} PRIVATE "$<$<COMPILE_LANGUAGE:CUDA>:SHELL:--compiler-options ${FLAG}>")
       endforeach()
-      if ((NVCC_HAS_STRICT_ALIASING AND "${target_name}" MATCHES "cuda") OR (HAS_STRICT_ALIASING AND NOT "${target_name}" MATCHES "cuda"))
+      if (NVCC_HAS_STRICT_ALIASING AND "${target_name}" MATCHES "cuda")
         target_compile_options(${target_name} PRIVATE "$<$<COMPILE_LANGUAGE:CUDA>:-Wno-strict-aliasing>")
       endif()
+      if (HAS_STRICT_ALIASING AND NOT "${target_name}" MATCHES "cuda")
+          target_compile_options(${target_name} PRIVATE "$<$<COMPILE_LANGUAGE:CXX>:-Wno-strict-aliasing>")
+      endif()
     endif()
     if (onnxruntime_USE_ROCM)
       # flags are detected with CXX language mode, some flags are not supported with hipclang
@@ -1256,11 +1274,7 @@ endif()
 #Dependencies end. In the next we'll enable "treat warning as error"
 
 #Adjust warning flags
-if (onnxruntime_USE_CUDA)
-  set_msvc_c_cpp_compiler_warning_level(3)
-else()
-  set_msvc_c_cpp_compiler_warning_level(4)
-endif()
+set_msvc_c_cpp_compiler_warning_level(4)
 
 set(onnxruntime_DELAYLOAD_FLAGS "")
 
@@ -1397,6 +1411,10 @@ endif()
 if (onnxruntime_USE_CUDA)
   set(CMAKE_CUDA_RUNTIME_LIBRARY Shared)
   set(CMAKE_CUDA_STANDARD 17)
+  if(onnxruntime_CUDA_HOME)
+    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()
@@ -1597,7 +1615,7 @@ if (UNIX AND onnxruntime_USE_NCCL)
 else()
   set(onnxruntime_USE_NCCL OFF)
   set(onnxruntime_USE_MPI OFF)
-message( WARNING "MPI and NCCL disabled on Win build." )
+  message( WARNING "MPI and NCCL are disabled because build is on Windows or USE_NCCL is set to OFF." )
 endif()
 
 if (onnxruntime_USE_MPI)
@@ -1726,14 +1744,12 @@ if(onnxruntime_BUILD_KERNEL_EXPLORER)
 endif()
 
 # When GDK_PLATFORM is set then WINAPI_FAMILY is defined in gdk_toolchain.cmake (along with other relevant flags/definitions).
-if (WIN32 AND NOT GDK_PLATFORM)
+if (WIN32 AND NOT GDK_PLATFORM AND NOT CMAKE_CROSSCOMPILING)
   if (NOT CMAKE_CXX_STANDARD_LIBRARIES MATCHES kernel32.lib)
     # On onecore, link to the onecore build of the MSVC runtime
     get_filename_component(msvc_path "${CMAKE_C_COMPILER}/../../../.." ABSOLUTE)
     link_directories(BEFORE "${msvc_path}/lib/onecore/${onnxruntime_target_platform}")
-    # The .lib files in the MSVC runtime have a DEFAULITLIB entry for onecore.lib, which in turn links to reverse forwarders.
-    # We ignore that entry and use onecore_apiset.lib instead, since system components must not rely on reverse forwarders.
-    add_link_options("/NODEFAULTLIB:onecore.lib")
+    # The .lib files in the MSVC runtime have a DEFAULITLIB entry for onecore.lib, but it shold not cause any conflict with onecoreuap.lib
   endif()
 endif()
 

cmake/adjust_global_compile_flags.cmake

@@ -92,7 +92,7 @@ if (onnxruntime_MINIMAL_BUILD)
   endif()
 endif()
 
-# enable stream for all the non-minimal build
+# Enable stream for all the non-minimal build
 if (NOT onnxruntime_MINIMAL_BUILD)
   add_compile_definitions(ORT_ENABLE_STREAM)
 endif()
@@ -205,7 +205,7 @@ endif()
 
 
 macro(check_nvcc_compiler_flag _FLAG _RESULT)
-    execute_process(COMMAND ${onnxruntime_CUDA_HOME}/bin/nvcc "${_FLAG}" RESULT_VARIABLE NVCC_OUT ERROR_VARIABLE NVCC_ERROR)
+    execute_process(COMMAND ${CUDAToolkit_BIN_DIR}/nvcc "${_FLAG}" RESULT_VARIABLE NVCC_OUT ERROR_VARIABLE NVCC_ERROR)
     message("NVCC_ERROR = ${NVCC_ERROR}")
     message("NVCC_OUT = ${NVCC_OUT}")
     if ("${NVCC_OUT}" MATCHES "0")

cmake/deps.txt

@@ -13,6 +13,7 @@
 # See https://microsoft.sharepoint.com/teams/ONNX2/_layouts/OneNote.aspx?id=%2Fteams%2FONNX2%2FShared%20Documents%2FNotebooks%2FONNX%20Ecosystem%20Team%20Notebook&wd=target%28Development.one%7C63D3AB47-51D1-4A62-9965-66882234BD44%2FAdd%20or%20update%20a%20dependency%20in%20deps.txt%7C0E9ED71D-89D5-40FA-B05F-C0123289C591%2F%29
 #
 abseil_cpp;https://github.com/abseil/abseil-cpp/archive/refs/tags/20240116.0.zip;bc2cec6baaad67fcb6c0c38972b687d4797927e9
+coremltools;https://github.com/apple/coremltools/archive/refs/tags/7.1.zip;f1bab0f30966f2e217d8e01207d518f230a1641a
 cxxopts;https://github.com/jarro2783/cxxopts/archive/3c73d91c0b04e2b59462f0a741be8c07024c1bc0.zip;6c6ca7f8480b26c8d00476e0e24b7184717fe4f0
 date;https://github.com/HowardHinnant/date/archive/refs/tags/v3.0.1.zip;2dac0c81dc54ebdd8f8d073a75c053b04b56e159
 dlpack;https://github.com/dmlc/dlpack/archive/refs/tags/v0.6.zip;4d565dd2e5b31321e5549591d78aa7f377173445
@@ -25,7 +26,7 @@ eigen;https://gitlab.com/libeigen/eigen/-/archive/e7248b26a1ed53fa030c5c459f7ea0
 flatbuffers;https://github.com/google/flatbuffers/archive/refs/tags/v1.12.0.zip;ba0a75fd12dbef8f6557a74e611b7a3d0c5fe7bf
 fp16;https://github.com/Maratyszcza/FP16/archive/0a92994d729ff76a58f692d3028ca1b64b145d91.zip;b985f6985a05a1c03ff1bb71190f66d8f98a1494
 fxdiv;https://github.com/Maratyszcza/FXdiv/archive/63058eff77e11aa15bf531df5dd34395ec3017c8.zip;a5658f4036402dbca7cebee32be57fb8149811e1
-google_benchmark;https://github.com/google/benchmark/archive/refs/tags/v1.7.0.zip;e97c368b176e8614e3f1bf13dd9abcf6a7ad9908
+google_benchmark;https://github.com/google/benchmark/archive/refs/tags/v1.8.3.zip;bf9870756ee3f8d2d3b346b24ee3600a41c74d3d
 google_nsync;https://github.com/google/nsync/archive/refs/tags/1.26.0.zip;5e7c00ef6bf5b787386fc040067903ec774e2752
 googletest;https://github.com/google/googletest/archive/530d5c8c84abd2a46f38583ee817743c9b3a42b4.zip;5e3a61db2aa975cfd0f97ba92c818744e7fa7034
 googlexnnpack;https://github.com/google/XNNPACK/archive/0da379fc4808f9601faef392352018c741c0f297.zip;663883491e380b628e0a5b162b5f2658032fae73
@@ -36,8 +37,8 @@ mimalloc;https://github.com/microsoft/mimalloc/archive/refs/tags/v2.1.1.zip;d5ee
 mp11;https://github.com/boostorg/mp11/archive/refs/tags/boost-1.82.0.zip;9bc9e01dffb64d9e0773b2e44d2f22c51aace063
 neural_speed;https://github.com/intel/neural-speed/archive/refs/tags/bestlav0.1.1.zip;65b0f7a0d04f72f0d5a8d48af70f0366f2ab3939
 onnx;https://github.com/onnx/onnx/archive/refs/tags/v1.15.0.zip;54c3f960a0541c5d8d3e60c2933e11f5d3688a11
-#use the commit of supporting all the plugins and TRT 8.6-GA (https://github.com/onnx/onnx-tensorrt/commit/0462dc31ae78f48744b6141ae376df1f96d3f459)
-onnx_tensorrt;https://github.com/onnx/onnx-tensorrt/archive/a43ce67187bab219520fd80f21af8bbd4354bc8c.zip;572535aefef477050f86744dfab1fef840198035
+#use the commit of Final DDS removal. DDS output is now supported by ORT TRT.
+onnx_tensorrt;https://github.com/onnx/onnx-tensorrt/archive/bacfaaa951653cd4e72efe727a543567cb38f7de.zip;26434329612e804164ab7baa6ae629ada56c1b26
 protobuf;https://github.com/protocolbuffers/protobuf/archive/refs/tags/v21.12.zip;7cf2733949036c7d52fda017badcab093fe73bfa
 protoc_win64;https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win64.zip;b4521f7ada5b260380f94c4bd7f1b7684c76969a
 protoc_win32;https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-win32.zip;3688010318192c46ce73213cdfb6b3e5656da874
@@ -55,4 +56,4 @@ tensorboard;https://github.com/tensorflow/tensorboard/archive/373eb09e4c5d2b3cc2
 cutlass;https://github.com/NVIDIA/cutlass/archive/refs/tags/v3.1.0.zip;757f90a795034a89d4f48a79d1f009f7a04c8dee
 utf8_range;https://github.com/protocolbuffers/utf8_range/archive/72c943dea2b9240cd09efde15191e144bc7c7d38.zip;9925739c9debc0efa2adcb194d371a35b6a03156
 extensions;https://github.com/microsoft/onnxruntime-extensions/archive/94142d8391c9791ec71c38336436319a2d4ac7a0.zip;4365ac5140338b4cb75a39944a4be276e3829b3c
-composable_kernel;https://github.com/ROCmSoftwarePlatform/composable_kernel/archive/5356c4a943a35e74d7cdc69486afcb8703b9a59a.zip;522382c2af437e09124287e5879ab64af5b2e299
+composable_kernel;https://github.com/ROCmSoftwarePlatform/composable_kernel/archive/5356c4a943a35e74d7cdc69486afcb8703b9a59a.zip;522382c2af437e09124287e5879ab64af5b2e299