@@ -1929,9 +1929,10 @@ dist_patch_DATA = \
%D%/packages/patches/python-pyan3-fix-absolute-path-bug.patch \
%D%/packages/patches/python-pyan3-fix-positional-arguments.patch \
%D%/packages/patches/python-pygpgme-fix-pinentry-tests.patch \
+ %D%/packages/patches/python-pytorch-fix-codegen.patch \
%D%/packages/patches/python-pytorch-runpath.patch \
%D%/packages/patches/python-pytorch-system-libraries.patch \
- %D%/packages/patches/python-pytorch-1.9.0-system-libraries.patch \
+ %D%/packages/patches/python-pytorch-without-kineto.patch \
%D%/packages/patches/python-robotframework-atest.patch \
%D%/packages/patches/python-robotframework-source-date-epoch.patch \
%D%/packages/patches/python-robotframework-sshlibrary-rf5-compat.patch \
@@ -105,6 +105,7 @@ (define-module (gnu packages machine-learning)
#:use-module (gnu packages parallel)
#:use-module (gnu packages perl)
#:use-module (gnu packages pkg-config)
+ #:use-module (gnu packages pretty-print)
#:use-module (gnu packages protobuf)
#:use-module (gnu packages pulseaudio)
#:use-module (gnu packages python)
@@ -123,6 +124,7 @@ (define-module (gnu packages machine-learning)
#:use-module (gnu packages swig)
#:use-module (gnu packages time)
#:use-module (gnu packages tls)
+ #:use-module (gnu packages valgrind)
#:use-module (gnu packages vulkan)
#:use-module (gnu packages video)
#:use-module (gnu packages web)
@@ -4323,6 +4325,13 @@ (define %python-pytorch-src
(sha256
(base32
"03mm0pwwb5lxdsmmiw3cch9fijgjw81kmmc4ln9rlyazkm7l1r48"))
+ (patches (search-patches "python-pytorch-system-libraries.patch"
+ "python-pytorch-runpath.patch"
+ "python-pytorch-without-kineto.patch"
+ ;; Some autogeneration scripts depend on the
+ ;; compile PyTorch library. Therefore, we create
+ ;; dummy versions which are regenerated later.
+ "python-pytorch-fix-codegen.patch"))
(modules '((guix build utils)))
(snippet
'(begin
@@ -4442,135 +4451,219 @@ (define-public qnnpack-pytorch
(define-public python-pytorch
(package
(name "python-pytorch")
- (version "1.13.1")
- (source (origin
- (method git-fetch)
- (uri (git-reference
- (url "https://github.com/pytorch/pytorch")
- (commit (string-append "v" version))
- (recursive? #t)))
- (file-name (git-file-name name version))
- (sha256
- (base32
- "17yxjzwp4zp75fz7czgz9acijzw7dpyqcza50v8y1x7hfg2gw369"))
- (patches (search-patches "python-pytorch-system-libraries.patch"
- "python-pytorch-runpath.patch"))
- (modules '((guix build utils)))
- (snippet
- '(begin
- ;; XXX: Let's be clear: this package is a bundling fest. We
- ;; delete as much as we can, but there's still a lot left.
- (for-each (lambda (directory)
- (delete-file-recursively
- (string-append "third_party/" directory)))
- '("benchmark" "cpuinfo" "eigen"
-
- ;; FIXME: QNNPACK (of which XNNPACK is a fork)
- ;; needs these.
- ;; "FP16" "FXdiv" "gemmlowp" "psimd"
-
- "gloo" "googletest" "ios-cmake" "NNPACK"
- "onnx" "protobuf" "pthreadpool"
- "pybind11" "python-enum" "python-peachpy"
- "python-six" "tbb" "XNNPACK" "zstd"))
- (substitute* "functorch/CMakeLists.txt"
- (("\\$\\{_rpath_portable_origin\\}/../torch/lib")
- "$ORIGIN/../torch/lib"))))))
+ (version %python-pytorch-version)
+ (source %python-pytorch-src)
(build-system python-build-system)
(arguments
- '(#:phases (modify-phases %standard-phases
- (add-before 'build 'use-system-libraries
- (lambda* (#:key outputs #:allow-other-keys)
- ;; Tell 'setup.py' to let 'CMakeLists.txt' know that we
- ;; want to use "system libraries" instead of the bundled
- ;; ones.
- (setenv "USE_SYSTEM_LIBS" "1")
-
- (substitute* "cmake/Dependencies.cmake"
- (("if\\(USE_SYSTEM_BIND11\\)")
- "if(TRUE)"))
-
- ;; XXX: Disable that for simplicity for now.
- (setenv "USE_FBGEMM" "0")))
- (add-before 'build 'make-things-writable
- (lambda _
- ;; The 'build_caffe2' function in
- ;; 'tools/build_pytorch_libs.py', called from the
- ;; top-level 'setup.py', needs write access to this
- ;; directory.
- (for-each make-file-writable
- (find-files "caffe2/proto" "."
- #:directories? #t))))
- (replace 'check
- (lambda* (#:key inputs outputs tests? #:allow-other-keys)
- ;; Run the test suite following the instructions in
- ;; 'CONTRIBUTING.md'. XXX: Unfortunately this doesn't
- ;; work, unless you set GUIX_PYTHONPATH presumably.
- (when tests?
- (add-installed-pythonpath inputs outputs)
- (invoke "python" "test/run_test.py"))))
- (add-after 'install 'remove-test-executables
- (lambda* (#:key inputs outputs #:allow-other-keys)
- ;; Remove test executables, but keep other executables
- ;; such as 'torch_shm_manager' and and .so files such as
- ;; 'libtorch_global_deps.so'.
- (let ((python-site (site-packages inputs outputs)))
- (for-each delete-file
- (find-files python-site
- "(^test_cpp_rpc|_test)$")))))
- (add-after 'install 'remove-caffe2-onnx-scripts
- (lambda* (#:key outputs #:allow-other-keys)
- (let* ((out (assoc-ref outputs "out"))
- (bin (string-append out "/bin")))
- ;; Remove 'convert-caffe2-to-onnx' and
- ;; 'convert-onnx-to-caffe2': they seem to be
- ;; deprecated and they cause a failure of the
- ;; 'sanity-check' phase:
- ;;
- ;; ImportError: cannot import name 'metanet_pb2' from partially initialized module 'caffe2.proto' (most likely due to a circular import)
- (for-each delete-file
- (find-files bin "^convert-.*caffe2"))
-
- (substitute* (find-files out "^entry_points\\.txt$")
- (("^convert-.*" all)
- (string-append "# " all "\n")))))))
-
- ;; XXX: Tests attempt to download data such as
- ;; <https://raw.githubusercontent.com/pytorch/test-infra/master/stats/slow-tests.json>.
- ;; We're also missing some Python modules, such as expecttest.
- #:tests? #f))
+ (list
+ #:phases
+ #~(modify-phases %standard-phases
+ (add-after 'unpack 'cmake-patches
+ (lambda _
+ (substitute* "cmake/Dependencies.cmake"
+ (("#POCKETFFT_INCLUDE_DIR")
+ (string-append
+ #$(this-package-native-input "pocketfft-cpp") "/include"))
+ (("#FP16_INCLUDE_DIR")
+ (string-append
+ #$(this-package-input "fp16") "/include")))))
+ (add-before 'build 'use-system-libraries
+ (lambda _
+ (substitute* '("caffe2/serialize/crc.cc"
+ "caffe2/serialize/inline_container.cc")
+ (("\"miniz\\.h\"") "<miniz/miniz.h>"))
+ (substitute* "aten/src/ATen/native/vulkan/api/Allocator.h"
+ (("<include/vk_mem_alloc.h>")
+ "<vk_mem_alloc.h>"))
+ ;; For Vulkan
+ (substitute* "CMakeLists.txt"
+ (("append_cxx_flag.*-Werror=(return-type|range-loop-construct).*") ""))
+ (substitute*
+ (cons*
+ "torch/csrc/Module.cpp"
+ (map
+ (lambda (name)
+ (string-append
+ "torch/utils/benchmark/utils/valgrind_wrapper/"
+ name))
+ '("compat_bindings.cpp" "timer_callgrind_template.cpp")))
+ (("<callgrind.h>") "<valgrind/callgrind.h>"))
+ (setenv "USE_FFMPEG" "1")
+ (setenv "USE_VULKAN" "1")
+ (setenv "USE_OPENCV" "1")
+ ;; Tell 'setup.py' to let 'CMakeLists.txt' know that we
+ ;; want to use "system libraries" instead of the bundled
+ ;; ones.
+ (setenv "USE_SYSTEM_LIBS" "1")
+ ;; For oneDNN
+ (setenv "USE_MKLDNN" "1")
+ ;; Only works with CUPTI
+ (setenv "USE_KINETO" "0")
+ ;; Prevent CMake error by disabling explicitely
+ (setenv "USE_ITT" "0")))
+ (add-after 'use-system-libraries 'set-max-jobs
+ (lambda _
+ (setenv "MAX_JOBS" (number->string (parallel-job-count)))))
+ (add-after 'set-max-jobs 'codegen1
+ (lambda _
+ (with-directory-excursion "torch/csrc/jit/tensorexpr"
+ (setenv "PYTHONPATH" "../../../..")
+ (invoke "python3" "codegen_external.py")
+ (setenv "PYTHONPATH" #f))
+
+ (invoke "python3" "aten/src/ATen/nnapi/codegen.py")
+
+ (invoke "bash" "tools/gen_flatbuffers.sh")
+
+ ;; Generate dummy files as the generation depends on the compiled
+ ;; library. They are regenerated later.
+ (setenv "PYTHONPATH" ".")
+ (invoke "python3"
+ "torchgen/operator_versions/gen_mobile_upgraders.py"
+ "dummy")
+ (setenv "PYTHONPATH" #f)
+
+ (invoke "python3"
+ "torchgen/shape_functions/gen_jit_shape_functions.py"
+ "dummy")
+
+ (invoke "python3"
+ "torchgen/decompositions/gen_jit_decompositions.py"
+ "dummy")))
+ ;; Properly generate autogenerated files ...
+ (add-after 'install 'codegen2
+ (lambda* (#:key inputs outputs #:allow-other-keys)
+ (add-installed-pythonpath inputs outputs)
+ (invoke "python3"
+ "torchgen/operator_versions/gen_mobile_upgraders.py")
+ (invoke "python3"
+ "torchgen/shape_functions/gen_jit_shape_functions.py")
+ (invoke "python3"
+ "torchgen/decompositions/gen_jit_decompositions.py")))
+ ;; ... rebuild their dependencies ...
+ (add-after 'codegen2 'build2
+ (lambda _
+ (invoke "python3" "setup.py" "build")))
+ ;; ... and install again.
+ (add-after 'build2 'install2
+ (lambda _
+ (invoke "python3" "setup.py" "install" (string-append "--prefix=" #$output)
+ "--no-compile" "--single-version-externally-managed" "--root=/")
+ (invoke "python" "-m" "compileall"
+ "--invalidation-mode=unchecked-hash" #$output)))
+ (replace 'check
+ (lambda* (#:key tests? #:allow-other-keys)
+ ;; Run the test suite following the instructions in
+ ;; 'CONTRIBUTING.md'. Unfortunately this doesn't work, unless
+ ;; you set PYTHONPATH or GUIX_PYTHONPATH, but this is done in
+ ;; the codegen2 phase already.
+ (when tests?
+ (invoke "python3" "test/run_test.py" "--core"))))
+ (add-after 'install2 'remove-test-executables
+ (lambda* (#:key inputs outputs #:allow-other-keys)
+ ;; Remove test executables, but keep other executables
+ ;; such as 'torch_shm_manager' and and .so files such as
+ ;; 'libtorch_global_deps.so'.
+ (let ((python-site (site-packages inputs outputs)))
+ (for-each delete-file
+ (find-files python-site
+ "(^test_cpp_rpc|_test)$")))))
+ (add-after 'install2 'remove-caffe2-onnx-scripts
+ (lambda* (#:key outputs #:allow-other-keys)
+ (let* ((out (assoc-ref outputs "out"))
+ (bin (string-append out "/bin")))
+ ;; Remove 'convert-caffe2-to-onnx' and
+ ;; 'convert-onnx-to-caffe2': they seem to be
+ ;; deprecated and they cause a failure of the
+ ;; 'sanity-check' phase:
+ ;;
+ ;; ImportError: cannot import name 'metanet_pb2' from partially initialized module 'caffe2.proto' (most likely due to a circular import)
+ (for-each delete-file
+ (find-files bin "^convert-.*caffe2"))
+
+ (substitute* (find-files out "^entry_points\\.txt$")
+ (("^convert-.*" all)
+ (string-append "# " all "\n")))))))
+
+ ;; Even only the core tests take a very long time to run.
+ #:tests? #f))
(native-inputs
- (list cmake ninja))
+ (list cmake
+ doxygen
+ ideep-pytorch
+ ninja
+ pocketfft-cpp
+ python-expecttest
+ python-pytest-flakefinder
+ python-pytest-rerunfailures-13
+ python-pytest-shard
+ python-pytest-xdist
+ python-hypothesis
+ python-types-dataclasses
+ python-typing-extensions-4.10
+ shaderc
+ valgrind))
(inputs
- (list eigen
- ;; ("fmt" ,fmt)
- fp16
- gemmlowp
- googletest
- googlebenchmark
- gloo
- nnpack
- openblas
- openmpi
- pthreadpool
- protobuf
- pybind11
- sleef
- xnnpack
- zstd))
+ (append
+ (list asmjit
+ clog
+ eigen
+ ffmpeg
+ flatbuffers-next
+ fmt
+ foxi
+ fp16
+ fxdiv
+ gemmlowp
+ gloo
+ googletest
+ googlebenchmark
+ libuv
+ miniz-for-pytorch
+ openblas
+ opencv
+ openmpi
+ pthreadpool
+ protobuf
+ pybind11
+ qnnpack
+ qnnpack-pytorch
+ sleef
+ tensorpipe
+ vulkan-headers
+ vulkan-loader
+ vulkan-memory-allocator
+ xnnpack
+ zstd)
+ ;; TODO: fix build on 32 bit systems
+ (filter
+ (lambda (pkg)
+ (member (or (%current-target-system)
+ (%current-system))
+ (package-transitive-supported-systems pkg)))
+ (list
+ nnpack
+ fbgemm
+ oneapi-dnnl))))
(propagated-inputs
- (list python-astunparse
+ (list cpuinfo
+ onnx ;propagated for its Python modules
+ onnx-optimizer
+ python-astunparse
python-click
+ python-filelock
+ python-fsspec
+ python-future
+ python-jinja2
+ python-networkx
python-numpy
+ python-optree
+ python-packaging
+ python-psutil
python-pyyaml
- python-cffi
- python-typing-extensions
- python-future
- python-six
python-requests
- onnx ;propagated for its Python modules
- onnx-optimizer
- cpuinfo))
+ python-sympy
+ python-typing-extensions))
(home-page "https://pytorch.org/")
(synopsis "Python library for tensor computation and deep neural networks")
(description
deleted file mode 100644
@@ -1,139 +0,0 @@
-Use our own googletest rather than the bundled one.
-Get NNPACK to use our own PeachPy rather than the bundled one.
-
-diff --git a/cmake/Dependencies.cmake b/cmake/Dependencies.cmake
-index 5d57b9ca78..620cca4e60 100644
---- a/cmake/Dependencies.cmake
-+++ b/cmake/Dependencies.cmake
-@@ -644,11 +644,6 @@ if(BUILD_TEST OR BUILD_MOBILE_BENCHMARK OR BUILD_MOBILE_TEST)
- # this shouldn't be necessary anymore.
- get_property(INC_DIR_temp DIRECTORY PROPERTY INCLUDE_DIRECTORIES)
- set_property(DIRECTORY PROPERTY INCLUDE_DIRECTORIES "")
-- add_subdirectory(${CMAKE_CURRENT_LIST_DIR}/../third_party/googletest)
-- set_property(DIRECTORY PROPERTY INCLUDE_DIRECTORIES ${INC_DIR_temp})
--
-- include_directories(BEFORE SYSTEM ${CMAKE_CURRENT_LIST_DIR}/../third_party/googletest/googletest/include)
-- include_directories(BEFORE SYSTEM ${CMAKE_CURRENT_LIST_DIR}/../third_party/googletest/googlemock/include)
-
- # We will not need to test benchmark lib itself.
- set(BENCHMARK_ENABLE_TESTING OFF CACHE BOOL "Disable benchmark testing as we don't need it.")
-@@ -1485,7 +1480,7 @@ if(CAFFE2_CMAKE_BUILDING_WITH_MAIN_REPO AND NOT INTERN_DISABLE_ONNX)
- endif()
- set_property(TARGET onnx_proto PROPERTY IMPORTED_LOCATION ${ONNX_PROTO_LIBRARY})
- message("-- Found onnx: ${ONNX_LIBRARY} ${ONNX_PROTO_LIBRARY}")
-- list(APPEND Caffe2_DEPENDENCY_LIBS onnx_proto onnx)
-+ list(APPEND Caffe2_DEPENDENCY_LIBS onnx_proto onnx onnx_optimizer)
- endif()
- include_directories(${FOXI_INCLUDE_DIRS})
- list(APPEND Caffe2_DEPENDENCY_LIBS foxi_loader)
-
-diff --git a/caffe2/CMakeLists.txt b/caffe2/CMakeLists.txt
-index 50ebb224ce..5953d9ddf7 100644
---- a/caffe2/CMakeLists.txt
-+++ b/caffe2/CMakeLists.txt
-@@ -1632,7 +1632,7 @@ if(BUILD_TEST)
- if(NOT MSVC)
- add_executable(${test_name}_${CPU_CAPABILITY} "${test_src}" ../aten/src/ATen/native/quantized/affine_quantizer_base.cpp)
- # TODO: Get rid of c10 dependency (which is only needed for the implementation of AT_ERROR)
-- target_link_libraries(${test_name}_${CPU_CAPABILITY} c10 sleef gtest_main)
-+ target_link_libraries(${test_name}_${CPU_CAPABILITY} c10 sleef gtest_main gtest)
- if(USE_FBGEMM)
- target_link_libraries(${test_name}_${CPU_CAPABILITY} fbgemm)
- endif()
-@@ -1655,7 +1655,7 @@ if(BUILD_TEST)
- foreach(test_src ${Caffe2_CPU_TEST_SRCS})
- get_filename_component(test_name ${test_src} NAME_WE)
- add_executable(${test_name} "${test_src}")
-- target_link_libraries(${test_name} torch_library gtest_main)
-+ target_link_libraries(${test_name} torch_library gtest_main gtest)
- target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
- target_include_directories(${test_name} PRIVATE $<BUILD_INTERFACE:${CMAKE_BINARY_DIR}/include>)
- target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
-@@ -1673,7 +1673,7 @@ if(BUILD_TEST)
- foreach(test_src ${Caffe2_GPU_TEST_SRCS})
- get_filename_component(test_name ${test_src} NAME_WE)
- cuda_add_executable(${test_name} "${test_src}")
-- target_link_libraries(${test_name} torch_library gtest_main)
-+ target_link_libraries(${test_name} torch_library gtest_main gtest)
- target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
- target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
- add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
-@@ -1691,7 +1691,7 @@ if(BUILD_TEST)
- foreach(test_src ${Caffe2_VULKAN_TEST_SRCS})
- get_filename_component(test_name ${test_src} NAME_WE)
- add_executable(${test_name} "${test_src}")
-- target_link_libraries(${test_name} torch_library gtest_main)
-+ target_link_libraries(${test_name} torch_library gtest_main gtest)
- target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
- target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
- add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
-@@ -1709,7 +1709,7 @@ if(BUILD_TEST)
- foreach(test_src ${Caffe2_HIP_TEST_SRCS})
- get_filename_component(test_name ${test_src} NAME_WE)
- add_executable(${test_name} "${test_src}")
-- target_link_libraries(${test_name} torch_library gtest_main)
-+ target_link_libraries(${test_name} torch_library gtest_main gtest)
- target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
- target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE} ${Caffe2_HIP_INCLUDE})
- target_compile_options(${test_name} PRIVATE ${HIP_CXX_FLAGS})
-
-diff --git a/torch/lib/c10d/test/CMakeLists.txt b/torch/lib/c10d/test/CMakeLists.txt
-index b74d4b65f7..fc7c207505 100644
---- a/torch/lib/c10d/test/CMakeLists.txt
-+++ b/torch/lib/c10d/test/CMakeLists.txt
-@@ -16,24 +16,24 @@ function(c10d_add_test test_src)
- add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
- endfunction()
-
--c10d_add_test(FileStoreTest.cpp c10d gtest_main)
--c10d_add_test(TCPStoreTest.cpp c10d gtest_main)
-+c10d_add_test(FileStoreTest.cpp c10d gtest_main gtest)
-+c10d_add_test(TCPStoreTest.cpp c10d gtest_main gtest)
- if(NOT WIN32)
-- c10d_add_test(HashStoreTest.cpp c10d gtest_main)
-+ c10d_add_test(HashStoreTest.cpp c10d gtest_main gtest)
- endif()
-
- if(USE_CUDA)
- if(USE_C10D_GLOO)
-- c10d_add_test(ProcessGroupGlooTest.cpp c10d c10d_cuda_test gtest_main)
-- c10d_add_test(ProcessGroupGlooAsyncTest.cpp c10d c10d_cuda_test gtest_main)
-+ c10d_add_test(ProcessGroupGlooTest.cpp c10d c10d_cuda_test gtest_main gtest)
-+ c10d_add_test(ProcessGroupGlooAsyncTest.cpp c10d c10d_cuda_test gtest_main gtest)
- endif()
- if(USE_C10D_NCCL)
-- c10d_add_test(ProcessGroupNCCLTest.cpp c10d c10d_cuda_test gtest_main)
-+ c10d_add_test(ProcessGroupNCCLTest.cpp c10d c10d_cuda_test gtest_main gtest)
- c10d_add_test(ProcessGroupNCCLErrorsTest.cpp c10d c10d_cuda_test
-- gtest_main)
-+ gtest_main gtest)
- endif()
- else()
- if(USE_C10D_GLOO)
-- c10d_add_test(ProcessGroupGlooTest.cpp c10d gtest_main)
-+ c10d_add_test(ProcessGroupGlooTest.cpp c10d gtest_main gtest)
- endif()
- endif()
-
-diff --git a/cmake/External/nnpack.cmake b/cmake/External/nnpack.cmake
-index a41343cbb5..6075bdd0a4 100644
---- a/cmake/External/nnpack.cmake
-+++ b/cmake/External/nnpack.cmake
-@@ -40,7 +40,7 @@ endif()
- # (3) Android, iOS, Linux, macOS - supported
- ##############################################################################
-
--if(ANDROID OR IOS OR ${CMAKE_SYSTEM_NAME} STREQUAL "Linux" OR ${CMAKE_SYSTEM_NAME} STREQUAL "Darwin")
-+if(FALSE)
- message(STATUS "Brace yourself, we are building NNPACK")
- set(CAFFE2_THIRD_PARTY_ROOT ${PROJECT_SOURCE_DIR}/third_party)
-
-@@ -114,6 +114,5 @@ endif()
- # (4) Catch-all: not supported.
- ##############################################################################
-
--message(WARNING "Unknown platform - I don't know how to build NNPACK. "
-- "See cmake/External/nnpack.cmake for details.")
--set(USE_NNPACK OFF)
-+set(NNPACK_FOUND TRUE)
-+set(USE_NNPACK ON)
new file mode 100644
@@ -0,0 +1,167 @@
+This patch fixes some scripts for generating source files. For
+gen_jit_decompositions.py, gen_mobile_upgraders.py and
+gen_jit_shape_functions.py, which depend on the compiled PyTorch library, the
+option to generate "dummy" source files is added for the initial build, which
+is later corrected. codegen_external.py is patched to avoid duplicate
+functions and add the static keyword as in the existing generated file.
+
+diff --git a/tools/gen_flatbuffers.sh b/tools/gen_flatbuffers.sh
+index cc0263dbbf..ac34e84b82 100644
+--- a/tools/gen_flatbuffers.sh
++++ b/tools/gen_flatbuffers.sh
+@@ -1,13 +1,13 @@
+ #!/bin/bash
+ ROOT=$(pwd)
+-FF_LOCATION="$ROOT/third_party/flatbuffers"
+-cd "$FF_LOCATION" || exit
+-mkdir build
+-cd build || exit
+-cmake ..
+-cmake --build . --target flatc
+-mkdir -p "$ROOT/build/torch/csrc/jit/serialization"
+-./flatc --cpp --gen-mutable --scoped-enums \
++#FF_LOCATION="$ROOT/third_party/flatbuffers"
++#cd "$FF_LOCATION" || exit
++#mkdir build
++#cd build || exit
++#cmake ..
++#cmake --build . --target flatc
++#mkdir -p "$ROOT/build/torch/csrc/jit/serialization"
++flatc --cpp --gen-mutable --scoped-enums \
+ -o "$ROOT/torch/csrc/jit/serialization" \
+ -c "$ROOT/torch/csrc/jit/serialization/mobile_bytecode.fbs"
+ echo '// @generated' >> "$ROOT/torch/csrc/jit/serialization/mobile_bytecode_generated.h"
+diff --git a/torch/csrc/jit/tensorexpr/codegen_external.py b/torch/csrc/jit/tensorexpr/codegen_external.py
+index bc69b05162..0f8df81de3 100644
+--- a/torch/csrc/jit/tensorexpr/codegen_external.py
++++ b/torch/csrc/jit/tensorexpr/codegen_external.py
+@@ -20,9 +20,14 @@ def gen_external(native_functions_path, tags_path, external_path):
+ native_functions = parse_native_yaml(native_functions_path, tags_path)
+ func_decls = []
+ func_registrations = []
+- for func in native_functions:
++ done_names = set()
++ for func in native_functions[0]:
+ schema = func.func
+ name = schema.name.name.base
++ if name in done_names:
++ continue
++ else:
++ done_names.add(name)
+ args = schema.arguments
+ # Only supports extern calls for functions with out variants
+ if not schema.is_out_fn():
+@@ -62,7 +67,7 @@ def gen_external(native_functions_path, tags_path, external_path):
+
+ # print(tensor_decls, name, arg_names)
+ func_decl = f"""\
+-void nnc_aten_{name}(
++static void nnc_aten_{name}(
+ int64_t bufs_num,
+ void** buf_data,
+ int64_t* buf_ranks,
+diff --git a/torchgen/decompositions/gen_jit_decompositions.py b/torchgen/decompositions/gen_jit_decompositions.py
+index 7cfbb803f9..2e69bb1868 100644
+--- a/torchgen/decompositions/gen_jit_decompositions.py
++++ b/torchgen/decompositions/gen_jit_decompositions.py
+@@ -1,8 +1,12 @@
+ #!/usr/bin/env python3
+ import os
+ from pathlib import Path
++import sys
+
+-from torch.jit._decompositions import decomposition_table
++if len(sys.argv) < 2 or sys.argv[1] != "dummy":
++ from torch.jit._decompositions import decomposition_table
++else:
++ decomposition_table = {}
+
+ # from torchgen.code_template import CodeTemplate
+
+@@ -85,7 +89,7 @@ def write_decomposition_util_file(path: str) -> None:
+
+
+ def main() -> None:
+- pytorch_dir = Path(__file__).resolve().parents[3]
++ pytorch_dir = Path(__file__).resolve().parents[2]
+ upgrader_path = pytorch_dir / "torch" / "csrc" / "jit" / "runtime"
+ write_decomposition_util_file(str(upgrader_path))
+
+diff --git a/torchgen/operator_versions/gen_mobile_upgraders.py b/torchgen/operator_versions/gen_mobile_upgraders.py
+index dab1568580..55c58715fc 100644
+--- a/torchgen/operator_versions/gen_mobile_upgraders.py
++++ b/torchgen/operator_versions/gen_mobile_upgraders.py
+@@ -2,10 +2,12 @@
+ import os
+ from enum import Enum
+ from pathlib import Path
++import sys
+ from typing import Any, Dict, List
+
+-import torch
+-from torch.jit.generate_bytecode import generate_upgraders_bytecode
++if len(sys.argv) < 2 or sys.argv[1] != "dummy":
++ import torch
++ from torch.jit.generate_bytecode import generate_upgraders_bytecode
+
+ from torchgen.code_template import CodeTemplate
+ from torchgen.operator_versions.gen_mobile_upgraders_constant import (
+@@ -262,7 +264,10 @@ def construct_register_size(register_size_from_yaml: int) -> str:
+ def construct_version_maps(
+ upgrader_bytecode_function_to_index_map: Dict[str, Any]
+ ) -> str:
+- version_map = torch._C._get_operator_version_map()
++ if len(sys.argv) < 2 or sys.argv[1] != "dummy":
++ version_map = torch._C._get_operator_version_map()
++ else:
++ version_map = {}
+ sorted_version_map_ = sorted(version_map.items(), key=lambda item: item[0]) # type: ignore[no-any-return]
+ sorted_version_map = dict(sorted_version_map_)
+
+@@ -378,7 +383,10 @@ def sort_upgrader(upgrader_list: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+
+
+ def main() -> None:
+- upgrader_list = generate_upgraders_bytecode()
++ if len(sys.argv) < 2 or sys.argv[1] != "dummy":
++ upgrader_list = generate_upgraders_bytecode()
++ else:
++ upgrader_list = []
+ sorted_upgrader_list = sort_upgrader(upgrader_list)
+ for up in sorted_upgrader_list:
+ print("after sort upgrader : ", next(iter(up)))
+diff --git a/torchgen/shape_functions/gen_jit_shape_functions.py b/torchgen/shape_functions/gen_jit_shape_functions.py
+index c6336a6951..34e394d818 100644
+--- a/torchgen/shape_functions/gen_jit_shape_functions.py
++++ b/torchgen/shape_functions/gen_jit_shape_functions.py
+@@ -18,16 +18,20 @@ you are in the root directory of the Pytorch git repo"""
+ if not file_path.exists():
+ raise Exception(err_msg)
+
+-spec = importlib.util.spec_from_file_location(module_name, file_path)
+-assert spec is not None
+-module = importlib.util.module_from_spec(spec)
+-sys.modules[module_name] = module
+-assert spec.loader is not None
+-assert module is not None
+-spec.loader.exec_module(module)
+-
+-bounded_compute_graph_mapping = module.bounded_compute_graph_mapping
+-shape_compute_graph_mapping = module.shape_compute_graph_mapping
++if len(sys.argv) < 2 or sys.argv[1] != "dummy":
++ spec = importlib.util.spec_from_file_location(module_name, file_path)
++ assert spec is not None
++ module = importlib.util.module_from_spec(spec)
++ sys.modules[module_name] = module
++ assert spec.loader is not None
++ assert module is not None
++ spec.loader.exec_module(module)
++
++ bounded_compute_graph_mapping = module.bounded_compute_graph_mapping
++ shape_compute_graph_mapping = module.shape_compute_graph_mapping
++else:
++ bounded_compute_graph_mapping = {}
++ shape_compute_graph_mapping = {}
+
+
+ SHAPE_HEADER = r"""
@@ -3,10 +3,10 @@ get installed, quite surprisingly, to 'lib/python3.8/site-packages/{bin,lib}'.
Make sure RUNPATH matches that.
diff --git a/caffe2/CMakeLists.txt b/caffe2/CMakeLists.txt
-index 5b5622f0..30d27e57 100644
+index 74836372..c8eb69d1 100644
--- a/caffe2/CMakeLists.txt
+++ b/caffe2/CMakeLists.txt
-@@ -1909,7 +1909,7 @@ if(BUILD_PYTHON)
+@@ -1910,7 +1910,7 @@ if(BUILD_PYTHON)
if(${BUILDING_WITH_TORCH_LIBS})
# site-packages/caffe2/python/caffe2_pybind11_state
# site-packages/torch/lib
@@ -16,7 +16,7 @@ index 5b5622f0..30d27e57 100644
# Must also include `CMAKE_SHARED_LINKER_FLAGS` in linker flags for
diff --git a/cmake/Dependencies.cmake b/cmake/Dependencies.cmake
-index ee9cf410..f190e69b 100644
+index acc95842..8f8fb7d7 100644
--- a/cmake/Dependencies.cmake
+++ b/cmake/Dependencies.cmake
@@ -4,7 +4,7 @@ if(APPLE)
@@ -28,3 +28,16 @@ index ee9cf410..f190e69b 100644
endif(APPLE)
# Use separate rpaths during build and install phases
set(CMAKE_SKIP_BUILD_RPATH FALSE)
+diff --git a/functorch/CMakeLists.txt b/functorch/CMakeLists.txt
+index f2f32745..db21b656 100644
+--- a/functorch/CMakeLists.txt
++++ b/functorch/CMakeLists.txt
+@@ -21,7 +21,7 @@ target_link_libraries(${PROJECT_NAME} PRIVATE pybind::pybind11)
+
+ set_target_properties(${PROJECT_NAME} PROPERTIES LIBRARY_OUTPUT_DIRECTORY
+ ${CMAKE_BINARY_DIR}/functorch)
+-set_target_properties(${PROJECT_NAME} PROPERTIES INSTALL_RPATH "${_rpath_portable_origin}/../torch/lib")
++set_target_properties(${PROJECT_NAME} PROPERTIES INSTALL_RPATH "$ORIGIN/../torch/lib")
+
+ # Copy-pasted prefix/suffix logic for Python extensions from
+ # https://github.com/pytorch/pytorch/blob/33bb8ae350611760139457b85842b1d7edf9aa11/caffe2/CMakeLists.txt#L1975
@@ -1,38 +1,104 @@
-Use our own googletest rather than the bundled one.
-Get NNPACK to use our own PeachPy rather than the bundled one.
+Patch build files to also system libraries instead of bundled ones for the
+libraries not supported or working only by specifying USE_SYSTEM_LIBS. This
+includes using the clog, cpuinfo, fbgemm, foxi, fp16, fxdiv, googletest,
+ideep, miniz, nnpack, oneapi-dnnl, pocketfft, pthreadpool, qnnpack,
+qnnpack-pytorch, tensorpipe, valgrind and xnnpack packages.
+For QNNPACK, two versions were bundled and are required: The upstream one and
+an internal fork (now in the package qnnpack-pytorch).
+diff --git a/aten/src/ATen/CMakeLists.txt b/aten/src/ATen/CMakeLists.txt
+index 2c2b967..5ac5fa6 100644
+--- a/aten/src/ATen/CMakeLists.txt
++++ b/aten/src/ATen/CMakeLists.txt
+@@ -371,9 +371,9 @@ if(AT_NNPACK_ENABLED)
+ list(APPEND ATen_CPU_DEPENDENCY_LIBS nnpack) # cpuinfo is added below
+ endif()
+
+-if(MKLDNN_FOUND)
+- list(APPEND ATen_CPU_DEPENDENCY_LIBS ${MKLDNN_LIBRARIES})
+-endif(MKLDNN_FOUND)
++if(USE_MKLDNN)
++ list(APPEND ATen_CPU_DEPENDENCY_LIBS DNNL::dnnl)
++endif(USE_MKLDNN)
+
+ if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(s390x|ppc64le)$")
+ list(APPEND ATen_CPU_DEPENDENCY_LIBS cpuinfo)
diff --git a/caffe2/CMakeLists.txt b/caffe2/CMakeLists.txt
-index d57d7ebb..5b5622f0 100644
+index 7483637..093de40 100644
--- a/caffe2/CMakeLists.txt
+++ b/caffe2/CMakeLists.txt
-@@ -1736,7 +1736,7 @@ if(BUILD_TEST)
+@@ -111,9 +111,6 @@ if(NOT MSVC AND USE_XNNPACK)
+ if(NOT TARGET fxdiv)
+ set(FXDIV_BUILD_TESTS OFF CACHE BOOL "")
+ set(FXDIV_BUILD_BENCHMARKS OFF CACHE BOOL "")
+- add_subdirectory(
+- "${FXDIV_SOURCE_DIR}"
+- "${CMAKE_BINARY_DIR}/FXdiv")
+ endif()
+ endif()
+
+@@ -1055,7 +1052,6 @@ elseif(USE_CUDA)
+ endif()
+
+ if(NOT MSVC AND USE_XNNPACK)
+- TARGET_LINK_LIBRARIES(torch_cpu PRIVATE fxdiv)
+ endif()
+
+ # ==========================================================
+@@ -1396,6 +1392,7 @@ target_link_libraries(torch_cpu PUBLIC c10)
+ target_link_libraries(torch_cpu PUBLIC ${Caffe2_PUBLIC_DEPENDENCY_LIBS})
+ target_link_libraries(torch_cpu PRIVATE ${Caffe2_DEPENDENCY_LIBS})
+ target_link_libraries(torch_cpu PRIVATE ${Caffe2_DEPENDENCY_WHOLE_LINK_LIBS})
++target_link_libraries(torch_cpu PRIVATE miniz clog)
+ if(USE_MPI)
+ target_link_libraries(torch_cpu PRIVATE MPI::MPI_CXX)
+ endif()
+@@ -1653,7 +1650,7 @@ if(BUILD_STATIC_RUNTIME_BENCHMARK)
+ add_executable(static_runtime_bench "${STATIC_RUNTIME_BENCHMARK_SRCS}")
+ add_executable(static_runtime_test "${STATIC_RUNTIME_TEST_SRCS}")
+ target_link_libraries(static_runtime_bench torch_library benchmark)
+- target_link_libraries(static_runtime_test torch_library gtest_main)
++ target_link_libraries(static_runtime_test torch_library gtest_main gtest)
+ endif()
+
+ if(BUILD_TENSOREXPR_BENCHMARK)
+@@ -1680,7 +1677,7 @@ if(BUILD_MOBILE_TEST)
+ foreach(test_src ${ATen_MOBILE_TEST_SRCS})
+ get_filename_component(test_name ${test_src} NAME_WE)
+ add_executable(${test_name} "${test_src}")
+- target_link_libraries(${test_name} torch_library gtest_main)
++ target_link_libraries(${test_name} torch_library gtest_main gtest)
+ target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
+ target_include_directories(${test_name} PRIVATE $<BUILD_INTERFACE:${CMAKE_BINARY_DIR}/include>)
+ target_include_directories(${test_name} PRIVATE ${ATen_CPU_INCLUDE})
+@@ -1701,7 +1698,7 @@ if(BUILD_TEST)
if(NOT MSVC)
- add_executable(${test_name}_${CPU_CAPABILITY} "${test_src}" ../aten/src/ATen/native/quantized/affine_quantizer_base.cpp)
+ add_executable(${test_name}_${CPU_CAPABILITY} "${test_src}" ../aten/src/ATen/native/quantized/AffineQuantizerBase.cpp)
# TODO: Get rid of c10 dependency (which is only needed for the implementation of AT_ERROR)
- target_link_libraries(${test_name}_${CPU_CAPABILITY} c10 sleef gtest_main)
+ target_link_libraries(${test_name}_${CPU_CAPABILITY} c10 sleef gtest_main gtest)
if(USE_FBGEMM)
target_link_libraries(${test_name}_${CPU_CAPABILITY} fbgemm)
endif()
-@@ -1759,7 +1759,7 @@ if(BUILD_TEST)
+@@ -1715,7 +1712,7 @@ if(BUILD_TEST)
+ endif()
+ else()
+ add_executable(${test_name}_${CPU_CAPABILITY} "${test_src}")
+- target_link_libraries(${test_name}_${CPU_CAPABILITY} torch_library gtest_main)
++ target_link_libraries(${test_name}_${CPU_CAPABILITY} torch_library gtest_main gtest)
+ endif()
+ target_include_directories(${test_name}_${CPU_CAPABILITY} PRIVATE $<INSTALL_INTERFACE:include>)
+ target_include_directories(${test_name}_${CPU_CAPABILITY} PRIVATE $<BUILD_INTERFACE:${CMAKE_BINARY_DIR}/include>)
+@@ -1732,7 +1729,7 @@ if(BUILD_TEST)
foreach(test_src ${Caffe2_CPU_TEST_SRCS})
get_filename_component(test_name ${test_src} NAME_WE)
add_executable(${test_name} "${test_src}")
- target_link_libraries(${test_name} torch_library gtest_main)
+ target_link_libraries(${test_name} torch_library gtest_main gtest)
- if(USE_OPENMP)
- # -fopenmp is a compile time flag and as result not guaranteed
- # to link executable against OpenMP runtime library
-@@ -1785,7 +1785,7 @@ if(BUILD_TEST)
- foreach(test_src ${Caffe2_GPU_TEST_SRCS})
- get_filename_component(test_name ${test_src} NAME_WE)
- add_executable(${test_name} "${test_src}")
-- target_link_libraries(${test_name} torch_library gtest_main)
-+ target_link_libraries(${test_name} torch_library gtest_main gtest)
- target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
- target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
- add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
-@@ -1803,7 +1803,7 @@ if(BUILD_TEST)
+ target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
+ target_include_directories(${test_name} PRIVATE $<BUILD_INTERFACE:${CMAKE_BINARY_DIR}/include>)
+ target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
+@@ -1795,7 +1792,7 @@ if(BUILD_TEST)
foreach(test_src ${Caffe2_VULKAN_TEST_SRCS})
get_filename_component(test_name ${test_src} NAME_WE)
add_executable(${test_name} "${test_src}")
@@ -41,20 +107,66 @@ index d57d7ebb..5b5622f0 100644
target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE})
add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
-@@ -1821,7 +1821,7 @@ if(BUILD_TEST)
- foreach(test_src ${Caffe2_HIP_TEST_SRCS})
- get_filename_component(test_name ${test_src} NAME_WE)
- add_executable(${test_name} "${test_src}")
-- target_link_libraries(${test_name} torch_library gtest_main)
-+ target_link_libraries(${test_name} torch_library gtest_main gtest)
- target_include_directories(${test_name} PRIVATE $<INSTALL_INTERFACE:include>)
- target_include_directories(${test_name} PRIVATE ${Caffe2_CPU_INCLUDE} ${Caffe2_HIP_INCLUDE})
- target_compile_options(${test_name} PRIVATE ${HIP_CXX_FLAGS})
+diff --git a/caffe2/serialize/CMakeLists.txt b/caffe2/serialize/CMakeLists.txt
+index 1552b59..67e1a9a 100644
+--- a/caffe2/serialize/CMakeLists.txt
++++ b/caffe2/serialize/CMakeLists.txt
+@@ -2,7 +2,6 @@ file(GLOB tmp *_test.cc)
+
+ set(Caffe2_CPU_TEST_SRCS ${Caffe2_CPU_TEST_SRCS} ${tmp})
+ list(APPEND Caffe2_CPU_SRCS
+- ${PROJECT_SOURCE_DIR}/third_party/miniz-2.1.0/miniz.c
+ ${CMAKE_CURRENT_SOURCE_DIR}/inline_container.cc
+ ${CMAKE_CURRENT_SOURCE_DIR}/istream_adapter.cc
+ ${CMAKE_CURRENT_SOURCE_DIR}/file_adapter.cc
diff --git a/cmake/Dependencies.cmake b/cmake/Dependencies.cmake
-index 557ab649..ee9cf410 100644
+index acc9584..97275bf 100644
--- a/cmake/Dependencies.cmake
+++ b/cmake/Dependencies.cmake
-@@ -732,11 +732,6 @@ if(BUILD_TEST OR BUILD_MOBILE_BENCHMARK OR BUILD_MOBILE_TEST)
+@@ -283,7 +283,7 @@ endif()
+ # --- [ PocketFFT
+ set(AT_POCKETFFT_ENABLED 0)
+ if(NOT AT_MKL_ENABLED)
+- set(POCKETFFT_INCLUDE_DIR "${Torch_SOURCE_DIR}/third_party/pocketfft/")
++ set(POCKETFFT_INCLUDE_DIR "#POCKETFFT_INCLUDE_DIR")
+ if(NOT EXISTS "${POCKETFFT_INCLUDE_DIR}")
+ message(FATAL_ERROR "pocketfft directory not found, expected ${POCKETFFT_INCLUDE_DIR}")
+ elif(NOT EXISTS "${POCKETFFT_INCLUDE_DIR}/pocketfft_hdronly.h")
+@@ -489,19 +489,6 @@ if(USE_QNNPACK)
+ set(QNNPACK_BUILD_TESTS OFF CACHE BOOL "")
+ set(QNNPACK_BUILD_BENCHMARKS OFF CACHE BOOL "")
+ set(QNNPACK_LIBRARY_TYPE "static" CACHE STRING "")
+- add_subdirectory(
+- "${QNNPACK_SOURCE_DIR}"
+- "${CONFU_DEPENDENCIES_BINARY_DIR}/QNNPACK")
+-
+- # TODO: See https://github.com/pytorch/pytorch/issues/56285
+- if(CMAKE_CXX_COMPILER_ID MATCHES "Clang" OR CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+- target_compile_options(qnnpack PRIVATE -Wno-deprecated-declarations)
+- endif()
+-
+- # We build static versions of QNNPACK and pthreadpool but link
+- # them into a shared library for Caffe2, so they need PIC.
+- set_property(TARGET qnnpack PROPERTY POSITION_INDEPENDENT_CODE ON)
+- set_property(TARGET cpuinfo PROPERTY POSITION_INDEPENDENT_CODE ON)
+
+ if(QNNPACK_CUSTOM_THREADPOOL)
+ target_compile_definitions(
+@@ -550,13 +537,6 @@ if(USE_PYTORCH_QNNPACK)
+ set(PYTORCH_QNNPACK_BUILD_TESTS OFF CACHE BOOL "")
+ set(PYTORCH_QNNPACK_BUILD_BENCHMARKS OFF CACHE BOOL "")
+ set(PYTORCH_QNNPACK_LIBRARY_TYPE "static" CACHE STRING "")
+- add_subdirectory(
+- "${PYTORCH_QNNPACK_SOURCE_DIR}"
+- "${CONFU_DEPENDENCIES_BINARY_DIR}/pytorch_qnnpack")
+- # We build static versions of QNNPACK and pthreadpool but link
+- # them into a shared library for Caffe2, so they need PIC.
+- set_property(TARGET pytorch_qnnpack PROPERTY POSITION_INDEPENDENT_CODE ON)
+- set_property(TARGET cpuinfo PROPERTY POSITION_INDEPENDENT_CODE ON)
+
+ if(PYTORCH_QNNPACK_CUSTOM_THREADPOOL)
+ target_compile_definitions(
+@@ -728,11 +708,6 @@ if(BUILD_TEST OR BUILD_MOBILE_BENCHMARK OR BUILD_MOBILE_TEST)
# this shouldn't be necessary anymore.
get_property(INC_DIR_temp DIRECTORY PROPERTY INCLUDE_DIRECTORIES)
set_property(DIRECTORY PROPERTY INCLUDE_DIRECTORIES "")
@@ -66,7 +178,49 @@ index 557ab649..ee9cf410 100644
# We will not need to test benchmark lib itself.
set(BENCHMARK_ENABLE_TESTING OFF CACHE BOOL "Disable benchmark testing as we don't need it.")
-@@ -1543,7 +1538,7 @@ if(CAFFE2_CMAKE_BUILDING_WITH_MAIN_REPO AND NOT INTERN_DISABLE_ONNX)
+@@ -810,16 +785,6 @@ if(USE_FBGEMM)
+ if(USE_ASAN)
+ set(USE_SANITIZER "address,undefined" CACHE STRING "-fsanitize options for FBGEMM")
+ endif()
+- add_subdirectory("${FBGEMM_SOURCE_DIR}")
+- set_property(TARGET fbgemm_generic PROPERTY POSITION_INDEPENDENT_CODE ON)
+- set_property(TARGET fbgemm_avx2 PROPERTY POSITION_INDEPENDENT_CODE ON)
+- set_property(TARGET fbgemm_avx512 PROPERTY POSITION_INDEPENDENT_CODE ON)
+- set_property(TARGET fbgemm PROPERTY POSITION_INDEPENDENT_CODE ON)
+- if("${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang" AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER 13.0.0)
+- # See https://github.com/pytorch/pytorch/issues/74352
+- target_compile_options_if_supported(asmjit -Wno-deprecated-copy)
+- target_compile_options_if_supported(asmjit -Wno-unused-but-set-variable)
+- endif()
+ endif()
+
+ if(USE_FBGEMM)
+@@ -979,7 +944,7 @@ if(NOT TARGET fp16 AND NOT USE_SYSTEM_FP16)
+ "${FP16_SOURCE_DIR}"
+ "${CONFU_DEPENDENCIES_BINARY_DIR}/FP16")
+ elseif(NOT TARGET fp16 AND USE_SYSTEM_FP16)
+- add_library(fp16 STATIC "/usr/include/fp16.h")
++ add_library(fp16 STATIC "#FP16_INCLUDE_DIR")
+ set_target_properties(fp16 PROPERTIES LINKER_LANGUAGE C)
+ endif()
+ list(APPEND Caffe2_DEPENDENCY_LIBS fp16)
+@@ -1362,7 +1327,6 @@ if(USE_DISTRIBUTED AND USE_TENSORPIPE)
+
+ # Tensorpipe uses cuda_add_library
+ torch_update_find_cuda_flags()
+- add_subdirectory(${PROJECT_SOURCE_DIR}/third_party/tensorpipe)
+
+ list(APPEND Caffe2_DEPENDENCY_LIBS tensorpipe)
+ if(USE_CUDA)
+@@ -1529,7 +1493,6 @@ if(CAFFE2_CMAKE_BUILDING_WITH_MAIN_REPO AND NOT INTERN_DISABLE_ONNX)
+ set_target_properties(onnx_proto PROPERTIES CXX_STANDARD 17)
+ endif()
+ endif()
+- add_subdirectory(${CMAKE_CURRENT_LIST_DIR}/../third_party/foxi EXCLUDE_FROM_ALL)
+
+ add_definitions(-DONNX_NAMESPACE=${ONNX_NAMESPACE})
+ if(NOT USE_SYSTEM_ONNX)
+@@ -1560,7 +1523,7 @@ if(CAFFE2_CMAKE_BUILDING_WITH_MAIN_REPO AND NOT INTERN_DISABLE_ONNX)
endif()
set_property(TARGET onnx_proto PROPERTY IMPORTED_LOCATION ${ONNX_PROTO_LIBRARY})
message("-- Found onnx: ${ONNX_LIBRARY} ${ONNX_PROTO_LIBRARY}")
@@ -75,8 +229,36 @@ index 557ab649..ee9cf410 100644
endif()
include_directories(${FOXI_INCLUDE_DIRS})
list(APPEND Caffe2_DEPENDENCY_LIBS foxi_loader)
+@@ -1739,9 +1702,8 @@ if(NOT INTERN_BUILD_MOBILE)
+ endif()
+ if(USE_MKLDNN)
+ include(${CMAKE_CURRENT_LIST_DIR}/public/mkldnn.cmake)
+- if(MKLDNN_FOUND)
++ if(DNNL_FOUND)
+ set(AT_MKLDNN_ENABLED 1)
+- include_directories(AFTER SYSTEM ${MKLDNN_INCLUDE_DIR})
+ if(BUILD_CAFFE2_OPS)
+ list(APPEND Caffe2_DEPENDENCY_LIBS caffe2::mkldnn)
+ endif(BUILD_CAFFE2_OPS)
+@@ -1796,7 +1758,7 @@ endif()
+ #
+ set(TEMP_BUILD_SHARED_LIBS ${BUILD_SHARED_LIBS})
+ set(BUILD_SHARED_LIBS OFF CACHE BOOL "Build shared libs" FORCE)
+-add_subdirectory(${PROJECT_SOURCE_DIR}/third_party/fmt)
++find_package(fmt)
+
+ # Disable compiler feature checks for `fmt`.
+ #
+@@ -1805,7 +1767,6 @@ add_subdirectory(${PROJECT_SOURCE_DIR}/third_party/fmt)
+ # CMAKE_CXX_FLAGS in ways that break feature checks. Since we already know
+ # `fmt` is compatible with a superset of the compilers that PyTorch is, it
+ # shouldn't be too bad to just disable the checks.
+-set_target_properties(fmt-header-only PROPERTIES INTERFACE_COMPILE_FEATURES "")
+
+ list(APPEND Caffe2_DEPENDENCY_LIBS fmt::fmt-header-only)
+ set(BUILD_SHARED_LIBS ${TEMP_BUILD_SHARED_LIBS} CACHE BOOL "Build shared libs" FORCE)
diff --git a/cmake/External/nnpack.cmake b/cmake/External/nnpack.cmake
-index a41343cb..6075bdd0 100644
+index 9d5f064..c3624e5 100644
--- a/cmake/External/nnpack.cmake
+++ b/cmake/External/nnpack.cmake
@@ -40,7 +40,7 @@ endif()
@@ -88,7 +270,7 @@ index a41343cb..6075bdd0 100644
message(STATUS "Brace yourself, we are building NNPACK")
set(CAFFE2_THIRD_PARTY_ROOT ${PROJECT_SOURCE_DIR}/third_party)
-@@ -114,6 +114,5 @@ endif()
+@@ -112,6 +112,5 @@ endif()
# (4) Catch-all: not supported.
##############################################################################
@@ -97,8 +279,45 @@ index a41343cb..6075bdd0 100644
-set(USE_NNPACK OFF)
+set(NNPACK_FOUND TRUE)
+set(USE_NNPACK ON)
+diff --git a/cmake/public/mkldnn.cmake b/cmake/public/mkldnn.cmake
+index 8793562..9f8fa3d 100644
+--- a/cmake/public/mkldnn.cmake
++++ b/cmake/public/mkldnn.cmake
+@@ -4,7 +4,7 @@ if(CPU_AARCH64)
+ include(${CMAKE_CURRENT_LIST_DIR}/ComputeLibrary.cmake)
+ endif()
+
+-find_package(MKLDNN QUIET)
++find_package(DNNL REQUIRED)
+
+ if(NOT TARGET caffe2::mkldnn)
+ add_library(caffe2::mkldnn INTERFACE IMPORTED)
+@@ -15,4 +15,4 @@ set_property(
+ ${MKLDNN_INCLUDE_DIR})
+ set_property(
+ TARGET caffe2::mkldnn PROPERTY INTERFACE_LINK_LIBRARIES
+- ${MKLDNN_LIBRARIES})
++ DNNL::dnnl)
+diff --git a/setup.py b/setup.py
+index 81f3c6c..3251cab 100644
+--- a/setup.py
++++ b/setup.py
+@@ -482,13 +482,9 @@ def build_deps():
+ # Windows has very poor support for them.
+ sym_files = [
+ "tools/shared/_utils_internal.py",
+- "torch/utils/benchmark/utils/valgrind_wrapper/callgrind.h",
+- "torch/utils/benchmark/utils/valgrind_wrapper/valgrind.h",
+ ]
+ orig_files = [
+ "torch/_utils_internal.py",
+- "third_party/valgrind-headers/callgrind.h",
+- "third_party/valgrind-headers/valgrind.h",
+ ]
+ for sym_file, orig_file in zip(sym_files, orig_files):
+ same = False
diff --git a/test/cpp/c10d/CMakeLists.txt b/test/cpp/c10d/CMakeLists.txt
-index bf91460c..ef56948f 100644
+index 5c89748..ef84c57 100644
--- a/test/cpp/c10d/CMakeLists.txt
+++ b/test/cpp/c10d/CMakeLists.txt
@@ -16,14 +16,14 @@ function(c10d_add_test test_src)
@@ -133,7 +352,29 @@ index bf91460c..ef56948f 100644
endif()
if(USE_NCCL AND USE_C10D_NCCL)
# NCCL is a private dependency of libtorch, but the tests include some
-@@ -56,7 +56,7 @@ if(USE_CUDA)
+@@ -44,10 +44,10 @@ if(USE_CUDA)
+ # a private dependency of the tests as well.
+ c10d_add_test(
+ ProcessGroupNCCLTest.cpp
+- torch_cpu c10d_cuda_test gtest_main __caffe2_nccl)
++ torch_cpu c10d_cuda_test gtest_main gtest __caffe2_nccl)
+ c10d_add_test(
+ ProcessGroupNCCLErrorsTest.cpp
+- torch_cpu c10d_cuda_test gtest_main __caffe2_nccl)
++ torch_cpu c10d_cuda_test gtest_main gtest __caffe2_nccl)
+ if(INSTALL_TEST)
+ install(TARGETS ProcessGroupNCCLTest DESTINATION bin)
+ install(TARGETS ProcessGroupNCCLErrorsTest DESTINATION bin)
+@@ -61,7 +61,7 @@ if(USE_CUDA)
+ # a private dependency of the tests as well.
+ c10d_add_test(
+ ProcessGroupUCCTest.cpp
+- torch_cpu c10d_cuda_test gtest_main __caffe2_ucc)
++ torch_cpu c10d_cuda_test gtest_main gtest __caffe2_ucc)
+ if(INSTALL_TEST)
+ install(TARGETS ProcessGroupUCCTest DESTINATION bin)
+ install(TARGETS c10d_cuda_test DESTINATION lib)
+@@ -69,7 +69,7 @@ if(USE_CUDA)
endif()
else()
if(USE_GLOO AND USE_C10D_GLOO)
@@ -143,10 +384,10 @@ index bf91460c..ef56948f 100644
endif()
diff --git a/test/cpp/tensorexpr/CMakeLists.txt b/test/cpp/tensorexpr/CMakeLists.txt
-index 8fc5a0a1..643202f6 100644
+index 012471d..d39b625 100644
--- a/test/cpp/tensorexpr/CMakeLists.txt
+++ b/test/cpp/tensorexpr/CMakeLists.txt
-@@ -53,7 +53,7 @@ target_include_directories(tutorial_tensorexpr PRIVATE ${ATen_CPU_INCLUDE})
+@@ -54,7 +54,7 @@ target_include_directories(tutorial_tensorexpr PRIVATE ${ATen_CPU_INCLUDE})
# pthreadpool header. For some build environment we need add the dependency
# explicitly.
if(USE_PTHREADPOOL)
@@ -154,4 +395,4 @@ index 8fc5a0a1..643202f6 100644
+ target_link_libraries(test_tensorexpr PRIVATE pthreadpool)
endif()
if(USE_CUDA)
- target_link_libraries(test_tensorexpr PRIVATE
+ target_compile_definitions(test_tensorexpr PRIVATE USE_CUDA)
new file mode 100644
@@ -0,0 +1,60 @@
+Even when building without Kineto, the <ActivityType.h> header is still
+imported and the ActivityType type is used. This patch was copied from
+https://github.com/pytorch/pytorch/pull/111048.
+
+diff --git a/torch/csrc/profiler/kineto_shim.h b/torch/csrc/profiler/kineto_shim.h
+index e92cbf00..68985ab7 100644
+--- a/torch/csrc/profiler/kineto_shim.h
++++ b/torch/csrc/profiler/kineto_shim.h
+@@ -12,7 +12,51 @@
+ #undef USE_KINETO
+ #endif
+
++#ifdef USE_KINETO
+ #include <ActivityType.h>
++#else
++namespace libkineto {
++// copied from header
++/*
++ * Copyright (c) Meta Platforms, Inc. and affiliates.
++ * All rights reserved.
++ *
++ * This source code is licensed under the BSD-style license found in the
++ * LICENSE file in the root directory of this source tree.
++ */
++
++// Note : All activity types are not enabled by default. Please add them
++// at correct position in the enum
++enum class ActivityType {
++ // Activity types enabled by default
++ CPU_OP = 0, // cpu side ops
++ USER_ANNOTATION,
++ GPU_USER_ANNOTATION,
++ GPU_MEMCPY,
++ GPU_MEMSET,
++ CONCURRENT_KERNEL, // on-device kernels
++ EXTERNAL_CORRELATION,
++ CUDA_RUNTIME, // host side cuda runtime events
++ CUDA_DRIVER, // host side cuda driver events
++ CPU_INSTANT_EVENT, // host side point-like events
++ PYTHON_FUNCTION,
++ OVERHEAD, // CUPTI induced overhead events sampled from its overhead API.
++
++ // Optional Activity types
++ CUDA_SYNC, // synchronization events between runtime and kernels
++ GLOW_RUNTIME, // host side glow runtime events
++ MTIA_RUNTIME, // host side MTIA runtime events
++ CUDA_PROFILER_RANGE, // CUPTI Profiler range for performance metrics
++ MTIA_CCP_EVENTS, // MTIA ondevice CCP events
++ HPU_OP, // HPU host side runtime event
++ XPU_RUNTIME, // host side xpu runtime events
++
++ ENUM_COUNT, // This is to add buffer and not used for any profiling logic. Add your new type before it.
++ OPTIONAL_ACTIVITY_TYPE_START = CUDA_SYNC,
++};
++}
++
++#endif
+
+ #include <torch/csrc/Export.h>
+ #include <torch/csrc/profiler/api.h>