Merge branch 'main' into qnn_ctx_node_prefix

.gitattributes

@@ -1,4 +1,4 @@
-# This sets the default behaviour, overriding core.autocrlf
+# This sets the default behavior, overriding core.autocrlf
 * text=auto
 
 # All source files should have unix line-endings in the repository,

.github/ISSUE_TEMPLATE/05-performance.yml

@@ -1,6 +1,7 @@
 name: Performance
 description: issues related to performance
 title: "[Performance] "
+labels: ["performance"]
 body:
   - type: markdown
     attributes:

.github/workflows/lint.yml

@@ -73,7 +73,7 @@ jobs:
           checkout_path: ${{ github.workspace }}
 
   lint-cpp:
-    name: Lint C++
+    name: Optional Lint C++
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@master
@@ -89,10 +89,11 @@ jobs:
       - name: Generate ONNX protobuf files
         run: cmake --build build/Debug --config Debug --target onnx_proto
       - uses: reviewdog/action-cpplint@master
+        continue-on-error: true
         with:
           github_token: ${{ secrets.github_token }}
           reporter: github-pr-check
-          level: warning
+          level: info
           flags: --linelength=120
             --exclude=java/src/main/native/*.c
             --exclude=onnxruntime/core/mlas/inc/*

.lintrunner.toml

@@ -137,6 +137,7 @@ exclude_patterns = [
     'onnxruntime/core/mickey/gemm/**', # CUTLASS based libs recommends NO automatic code formatting
     'winml/lib/Api.Image/shaders/**',  # Contains data chunks
     'onnxruntime/contrib_ops/cuda/bert/flash_attention/flash_fwd_launch_template.h', # Bool Switches hang Clang
+    'onnxruntime/core/providers/coreml/mlprogram_test_scripts/**',  # test scripts only
 ]
 command = [
     'python',

.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="1.14.1" targetFramework="native" />
+  <package id="Microsoft.AI.DirectML" version="1.15.0" targetFramework="native" />
   <package id="Microsoft.Windows.CppWinRT" version="2.0.201201.7" targetFramework="native" />
 </packages>

.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="1.14.1" targetFramework="native" />
+  <package id="Microsoft.AI.DirectML" version="1.15.0" targetFramework="native" />
   <package id="Microsoft.Windows.CppWinRT" version="2.0.201201.7" targetFramework="native" />
 </packages>

ThirdPartyNotices.txt

@@ -4820,7 +4820,7 @@ SOFTWARE.
 
 ----------------------------------------------------------------------------
 
-This is the MIT/Expat Licence. For more information see:
+This is the MIT/Expat License. For more information see:
 
 1. http://www.opensource.org/licenses/mit-license.php
 

cgmanifests/generate_cgmanifest.py

@@ -73,7 +73,7 @@ def add_github_dep(name, parsed_url):
             return
         # Make a REST call to convert to tag to a git commit
         url = f"https://api.github.com/repos/{org_name}/{repo_name}/git/refs/tags/{tag}"
-        print("requesting %s ..." % url)
+        print("requesting {url} ...")
         res = requests.get(url, auth=(args.username, args.token))
         response_json = res.json()
         tag_object = response_json["object"]

cgmanifests/generated/cgmanifest.json

@@ -116,7 +116,7 @@
       "component": {
         "type": "git",
         "git": {
-          "commitHash": "344117638c8ff7e239044fd0fa7085839fc03021",
+          "commitHash": "a6ad7fbbdc2e14fab82bb8a6d27760d700198cbf",
           "repositoryUrl": "https://github.com/google/benchmark.git"
         },
         "comments": "google_benchmark"
@@ -136,7 +136,7 @@
       "component": {
         "type": "git",
         "git": {
-          "commitHash": "530d5c8c84abd2a46f38583ee817743c9b3a42b4",
+          "commitHash": "e39786088138f2749d64e9e90e0f9902daa77c40",
           "repositoryUrl": "https://github.com/google/googletest.git"
         },
         "comments": "googletest"
@@ -256,7 +256,7 @@
       "component": {
         "type": "git",
         "git": {
-          "commitHash": "3e9dfa2866941655c56877882565e7577de6fc7b",
+          "commitHash": "941f45bcb51457884fa1afd6e24a67377d70f75c",
           "repositoryUrl": "https://github.com/pybind/pybind11.git"
         },
         "comments": "pybind11"
@@ -266,7 +266,7 @@
       "component": {
         "type": "git",
         "git": {
-          "commitHash": "959002f82d7962a473d8bf301845f2af720e0aa4",
+          "commitHash": "ca678952a9a8eaa6de112d154e8e104b22f9ab3f",
           "repositoryUrl": "https://github.com/pytorch/cpuinfo.git"
         },
         "comments": "pytorch_cpuinfo"
@@ -276,7 +276,7 @@
       "component": {
         "type": "git",
         "git": {
-          "commitHash": "2b354c6ad0d0479dcff68dab23fb0d1143a482c2",
+          "commitHash": "6dcd83d60f7944926bfd308cc13979fc53dd69ca",
           "repositoryUrl": "https://github.com/google/re2.git"
         },
         "comments": "re2"

cmake/deps.txt

@@ -26,9 +26,9 @@ eigen;https://gitlab.com/libeigen/eigen/-/archive/e7248b26a1ed53fa030c5c459f7ea0
 flatbuffers;https://github.com/google/flatbuffers/archive/refs/tags/v23.5.26.zip;59422c3b5e573dd192fead2834d25951f1c1670c
 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/v1.8.3.zip;bf9870756ee3f8d2d3b346b24ee3600a41c74d3d
+google_benchmark;https://github.com/google/benchmark/archive/refs/tags/v1.8.5.zip;cd47d3d272faf353600c8cc2fdec2b52d6f69177
 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
+googletest;https://github.com/google/googletest/archive/refs/tags/v1.15.0.zip;9d2d0af8d77ac726ea55d44a8fa727ec98311349
 googlexnnpack;https://github.com/google/XNNPACK/archive/0da379fc4808f9601faef392352018c741c0f297.zip;663883491e380b628e0a5b162b5f2658032fae73
 json;https://github.com/nlohmann/json/archive/refs/tags/v3.10.5.zip;f257f8dc27c5b8c085dc887b40cddd18ae1f725c
 microsoft_gsl;https://github.com/microsoft/GSL/archive/refs/tags/v4.0.0.zip;cf368104cd22a87b4dd0c80228919bb2df3e2a14
@@ -48,9 +48,9 @@ protoc_linux_aarch64;https://github.com/protocolbuffers/protobuf/releases/downlo
 protoc_mac_universal;https://github.com/protocolbuffers/protobuf/releases/download/v21.12/protoc-21.12-osx-universal_binary.zip;23710c3d1c2036d8d65a6a22234372fa2d7af9ef
 psimd;https://github.com/Maratyszcza/psimd/archive/072586a71b55b7f8c584153d223e95687148a900.zip;1f5454b01f06f9656b77e4a5e2e31d7422487013
 pthreadpool;https://github.com/Maratyszcza/pthreadpool/archive/4fe0e1e183925bf8cfa6aae24237e724a96479b8.zip;07a0aa91dd9bf86f31b95497e00f31d8a261a4bd
-pybind11;https://github.com/pybind/pybind11/archive/refs/tags/v2.12.0.zip;8482f57ed55c7b100672815a311d5450858723fb
-pytorch_cpuinfo;https://github.com/pytorch/cpuinfo/archive/959002f82d7962a473d8bf301845f2af720e0aa4.zip;85da3caa60eb2b148613b443fbc2bfdc30689965
-re2;https://github.com/google/re2/archive/refs/tags/2024-05-01.tar.gz;206cfee5ee0b4c6844680ba66275e9e8faa77405
+pybind11;https://github.com/pybind/pybind11/archive/refs/tags/v2.13.1.zip;9255d5c8568debcc329dd42ed8f410ee139ac7b1
+pytorch_cpuinfo;https://github.com/pytorch/cpuinfo/archive/ca678952a9a8eaa6de112d154e8e104b22f9ab3f.zip;138bf57d2a110935330d1048dce6d7b82d17d377
+re2;https://github.com/google/re2/archive/refs/tags/2024-07-02.zip;646e1728269cde7fcef990bf4a8e87b047882e88
 safeint;https://github.com/dcleblanc/SafeInt/archive/refs/tags/3.0.28.zip;23f252040ff6cb9f1fd18575b32fa8fb5928daac
 tensorboard;https://github.com/tensorflow/tensorboard/archive/373eb09e4c5d2b3cc2493f0949dc4be6b6a45e81.zip;67b833913605a4f3f499894ab11528a702c2b381
 cutlass;https://github.com/NVIDIA/cutlass/archive/refs/tags/v3.5.0.zip;ae038931b9fc2c416c17d9cda91d9706b343f56d

cmake/external/abseil-cpp.cmake

@@ -50,46 +50,96 @@ endif()
 # TODO: since multiple ORT's dependencies depend on Abseil, the list below would vary from version to version.
 # We'd better to not manually manage the list.
 set(ABSEIL_LIBS
-absl::city
+absl::absl_log
+absl::log_internal_log_impl
+absl::log_internal_strip
+absl::log_internal_message
+absl::log_internal_format
+absl::synchronization
+absl::str_format
 absl::flags
-absl::flat_hash_map
-absl::flat_hash_set
+absl::log_internal_globals
+absl::kernel_timeout_internal
+absl::str_format_internal
 absl::hash
-absl::inlined_vector
-absl::low_level_hash
-absl::node_hash_map
-absl::node_hash_set
+absl::log_internal_append_truncated
+absl::absl_vlog_is_on
+absl::flags_commandlineflag
+absl::time
+absl::symbolize
+absl::graphcycles_internal
+absl::log_internal_conditions
+absl::strings
+absl::malloc_internal
+absl::demangle_internal
 absl::optional
-absl::raw_hash_set
+absl::stacktrace
+absl::base
+absl::demangle_rust
+absl::bad_optional_access
+absl::strings_internal
+absl::debugging_internal
+absl::int128
+absl::spinlock_wait
+absl::decode_rust_punycode
 absl::raw_logging_internal
-absl::str_format
-absl::str_format_internal
+absl::flat_hash_set
+absl::flat_hash_map
+absl::node_hash_map
+absl::node_hash_set
+absl::compare
+absl::base_internal
+absl::nullability
+absl::bounded_utf8_length_sequence
+absl::log_severity
+absl::type_traits
+absl::atomic_hook
 absl::bits
-absl::fixed_array
+absl::flags_commandlineflag_internal
+absl::hash_container_defaults
 absl::numeric_representation
-absl::utility
-absl::type_traits
-absl::string_view
+absl::node_slot_policy
 absl::core_headers
-absl::nullability
+absl::dynamic_annotations
+absl::utf8_for_code_point
+absl::errno_saver
+absl::absl_check
+absl::hash_function_defaults
+absl::function_ref
+absl::city
+absl::low_level_hash
+absl::fixed_array
+absl::variant
+absl::meta
+absl::log_internal_voidify
+absl::log_sink
+absl::log_internal_log_sink_set
+absl::log_sink_registry
+absl::log_entry
+absl::log_globals
+absl::log_internal_nullguard
+absl::examine_stack
+absl::inlined_vector
+absl::log_internal_proto
+absl::strerror
+absl::log_internal_config
+absl::raw_hash_map
+absl::raw_hash_set
+absl::container_memory
+absl::algorithm_container
 absl::span
-absl::config
-absl::synchronization
-absl::base
+absl::log_internal_nullstream
+absl::vlog_config_internal
+absl::flags_reflection
+absl::flags_internal
+absl::flags_config
+absl::fast_type_id
+absl::utility
+absl::time_zone
 absl::civil_time
-absl::debugging_internal
-absl::demangle_internal
-absl::graphcycles_internal
-absl::int128
-absl::kernel_timeout_internal
-absl::log_severity
-absl::malloc_internal
-absl::spinlock_wait
-absl::stacktrace
 absl::string_view
-absl::strings
-absl::strings_internal
-absl::symbolize
 absl::throw_delegate
-absl::time
-absl::time_zone)
+absl::memory
+absl::charset
+absl::endian
+absl::config)

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.1.14.1)
+  set(DML_PACKAGE_DIR ${PACKAGES_DIR}/Microsoft.AI.DirectML.1.15.0)
 
   # Restore nuget packages, which will pull down the DirectML redist package.
   add_custom_command(

cmake/onnxruntime.cmake

@@ -27,6 +27,7 @@ function(get_c_cxx_api_headers HEADERS_VAR)
     "${REPO_ROOT}/include/onnxruntime/core/session/onnxruntime_float16.h"
     "${REPO_ROOT}/include/onnxruntime/core/session/onnxruntime_run_options_config_keys.h"
     "${REPO_ROOT}/include/onnxruntime/core/session/onnxruntime_session_options_config_keys.h"
+    "${REPO_ROOT}/include/onnxruntime/core/session/onnxruntime_lite_custom_op.h"
   )
 
   if (onnxruntime_ENABLE_TRAINING_APIS)
@@ -150,7 +151,7 @@ endif()
 
 if(CMAKE_SYSTEM_NAME STREQUAL "Android" AND onnxruntime_MINIMAL_BUILD)
   # target onnxruntime is a shared library, the dummy __cxa_demangle is only attach to it to avoid
-  # affecting downstream ort library users with the behaviour of dummy __cxa_demangle. So the dummy
+  # affecting downstream ort library users with the behavior of dummy __cxa_demangle. So the dummy
   # __cxa_demangle must not expose to libonnxruntime_common.a. It works as when the linker is
   # creating the DSO, our dummy __cxa_demangle always comes before libc++abi.a so the
   # __cxa_demangle in libc++abi.a is discarded, thus, huge binary size reduction.

cmake/onnxruntime_framework.cmake

@@ -123,7 +123,9 @@ if (WIN32)
   target_compile_definitions(onnxruntime_framework PRIVATE _SCL_SECURE_NO_WARNINGS)
 endif()
 
-if (NOT onnxruntime_BUILD_SHARED_LIB)
+if (onnxruntime_BUILD_SHARED_LIB)
+  install(FILES ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/framework/provider_options.h  DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/)
+else()
   install(DIRECTORY ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/framework  DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/core)
   install(TARGETS onnxruntime_framework
             ARCHIVE   DESTINATION ${CMAKE_INSTALL_LIBDIR}

cmake/onnxruntime_providers_openvino.cmake

@@ -17,8 +17,8 @@
 
   # Header paths
   find_package(OpenVINO REQUIRED COMPONENTS Runtime ONNX)
-  if(OpenVINO_VERSION VERSION_LESS 2023.0)
-    message(FATAL_ERROR "OpenVINO 2023.0 and newer are supported. Please, latest OpenVINO release")
+  if(OpenVINO_VERSION VERSION_LESS 2024.0)
+    message(FATAL_ERROR "OpenVINO 2024.0 and newer are supported. Please, use latest OpenVINO release")
   endif()
 
   if (WIN32)

cmake/onnxruntime_python.cmake

@@ -97,8 +97,12 @@ 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 AND onnxruntime_CUDNN_HOME)
-    target_include_directories(onnxruntime_pybind11_state PRIVATE ${onnxruntime_CUDNN_HOME}/include)
+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()
 endif()
 if(onnxruntime_USE_CANN)
     target_include_directories(onnxruntime_pybind11_state PRIVATE ${onnxruntime_CANN_HOME}/include)

cmake/onnxruntime_unittests.cmake

@@ -679,7 +679,10 @@ if(onnxruntime_USE_RKNPU)
 endif()
 
 if(onnxruntime_USE_COREML)
-  list(APPEND onnxruntime_test_framework_src_patterns  ${TEST_SRC_DIR}/providers/coreml/*)
+  list(APPEND onnxruntime_test_framework_src_patterns ${TEST_SRC_DIR}/providers/coreml/*.cc)
+  if(APPLE)
+    list(APPEND onnxruntime_test_framework_src_patterns ${TEST_SRC_DIR}/providers/coreml/*.mm)
+  endif()
   list(APPEND onnxruntime_test_framework_libs onnxruntime_providers_coreml coreml_proto)
   list(APPEND onnxruntime_test_providers_dependencies onnxruntime_providers_coreml coreml_proto)
   list(APPEND onnxruntime_test_providers_libs onnxruntime_providers_coreml coreml_proto)

cmake/patches/composable_kernel/Fix_Clang_Build.patch

@@ -44,7 +44,7 @@ index c23746e7f..bc326c8b5 100644
  find_package(HIP REQUIRED)
  # Override HIP version in config.h, if necessary.
 @@ -269,12 +248,6 @@ if( DEFINED CK_OVERRIDE_HIP_VERSION_PATCH )
-     message(STATUS "CK_HIP_VERSION_PATCH overriden with ${CK_OVERRIDE_HIP_VERSION_PATCH}")
+     message(STATUS "CK_HIP_VERSION_PATCH overridden with ${CK_OVERRIDE_HIP_VERSION_PATCH}")
  endif()
  message(STATUS "Build with HIP ${HIP_VERSION}")
 -link_libraries(hip::device)

cmake/patches/cpuinfo/9bb12d342fd9479679d505d93a478a6f9cd50a47.patch

@@ -1,22 +1,22 @@
 diff --git a/include/cpuinfo.h b/include/cpuinfo.h
-index c46b65e..8b83a64 100644
+index 03f2776..eaf6497 100644
 --- a/include/cpuinfo.h
 +++ b/include/cpuinfo.h
 @@ -18,7 +18,7 @@
- 	#define CPUINFO_ARCH_X86 1
+ #define CPUINFO_ARCH_X86 1
  #endif
 
 -#if defined(__x86_64__) || defined(__x86_64) || defined(_M_X64) || defined(_M_AMD64)
-+#if defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC)) || (defined(_M_AMD64) && !defined(_M_ARM64EC))
- 	#define CPUINFO_ARCH_X86_64 1
++#if defined(__x86_64__) || defined(__x86_64) || (defined(_M_X64) && !defined(_M_ARM64EC)) || (defined(_M_AMD64) && !defined(_M_ARM64EC))
+ #define CPUINFO_ARCH_X86_64 1
  #endif
 
 @@ -26,7 +26,7 @@
- 	#define CPUINFO_ARCH_ARM 1
+ #define CPUINFO_ARCH_ARM 1
  #endif
 
 -#if defined(__aarch64__) || defined(_M_ARM64)
 +#if defined(__aarch64__) || defined(_M_ARM64) || defined(_M_ARM64EC)
- 	#define CPUINFO_ARCH_ARM64 1
+ #define CPUINFO_ARCH_ARM64 1
  #endif