@@ -1812,7 +1812,6 @@ dist_patch_DATA = \
%D%/packages/patches/python-pyreadstat-link-libiconv.patch \
%D%/packages/patches/python-pyls-black-41.patch \
%D%/packages/patches/python-pypdf-annotate-tests-appropriately.patch \
- %D%/packages/patches/python-pytorch2-system-libraries.patch \
%D%/packages/patches/python-sip-include-dirs.patch \
%D%/packages/patches/python-sgmllib3k-assertions.patch \
%D%/packages/patches/python-sphinx-prompt-docutils-0.19.patch \
@@ -4707,7 +4707,15 @@ (define %python-pytorch-for-r-torch-src
%python-pytorch-for-r-torch-version))
(sha256
(base32
- "0iirrn687i7sfv0p0i7dn89x3rf13a7l8y1y5h190h51yjxpxqxa"))))
+ "0iirrn687i7sfv0p0i7dn89x3rf13a7l8y1y5h190h51yjxpxqxa"))
+ (patches (search-patches
+ "python-pytorch-for-r-torch-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-for-r-torch-fix-codegen.patch"))))
(define-public qnnpack-pytorch-for-r-torch
(package
@@ -4723,59 +4731,28 @@ (define-public qnnpack-pytorch-for-r-torch
(snippet
(origin-snippet (package-source qnnpack-pytorch)))))))
+;; Keep in sync with r-torch
(define-public python-pytorch-for-r-torch
(package
(inherit python-pytorch)
(name "python-pytorch")
- (version "2.0.1")
- (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
- "14m7v54zyd2qg2xk9mqdpbf4ps7091mdzinzh4vq9p5k4bpznj65"))
- (patches (search-patches "python-pytorch2-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* "caffe2/CMakeLists.txt"
- (("target_link_libraries\\(\\$\\{test_name\\}_\\$\\{CPU_CAPABILITY\\} c10 sleef gtest_main\\)")
- "target_link_libraries(${test_name}_${CPU_CAPABILITY} c10 sleef gtest gtest_main)"))
- (substitute* "functorch/CMakeLists.txt"
- (("\\$\\{_rpath_portable_origin\\}/../torch/lib")
- "$ORIGIN/../torch/lib"))))))
+ (version %python-pytorch-for-r-torch-version)
+ (source %python-pytorch-for-r-torch-src)
+ (native-inputs
+ (modify-inputs (package-native-inputs python-pytorch)
+ (replace "ideep-pytorch" ideep-pytorch-for-r-torch)))
(inputs
(modify-inputs (package-inputs python-pytorch)
- (replace "xnnpack" xnnpack-for-torch2)))
+ (replace "qnnpack-pytorch" qnnpack-pytorch-for-r-torch)
+ (replace "oneapi-dnnl" oneapi-dnnl-for-r-torch)))
(propagated-inputs
(modify-inputs (package-propagated-inputs python-pytorch)
(append python-filelock
python-jinja2
python-networkx
python-opt-einsum
- python-sympy)
- (replace "onnx" onnx-for-torch2)
- (replace "onnx-optimizer" onnx-optimizer-for-torch2)))))
+ python-sympy)))
+ (supported-systems %64bit-supported-systems)))
(define-public python-pytorch-geometric
(package
new file mode 100644
@@ -0,0 +1,167 @@
+This patch fixes some scripts for generating source files. For
+gen_jit_decompositions.py, gen_mobile_upgraders.py and
+gen_jit_shape_functions.py, which depend on the compiled PyTorch library, the
+option to generate "dummy" source files is added for the initial build, which
+is later corrected. codegen_external.py is patched to avoid duplicate
+functions and add the static keyword as in the existing generated file.
+
+diff --git a/tools/gen_flatbuffers.sh b/tools/gen_flatbuffers.sh
+index cc0263dbbf..ac34e84b82 100644
+--- a/tools/gen_flatbuffers.sh
++++ b/tools/gen_flatbuffers.sh
+@@ -1,13 +1,13 @@
+ #!/bin/bash
+ ROOT=$(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 120520b139..0c8587f02d 100644
+--- a/torch/csrc/jit/tensorexpr/codegen_external.py
++++ b/torch/csrc/jit/tensorexpr/codegen_external.py
+@@ -16,9 +16,14 @@ 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():
+@@ -48,7 +53,7 @@ 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 e5287cffc5..57f3c38096 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 = {name: lst for name, lst in sorted_version_map_}
+
+@@ -379,7 +384,10 @@ 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"""
new file mode 100644
@@ -0,0 +1,399 @@
+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 96fc297..7f27b66 100644
+--- a/aten/src/ATen/CMakeLists.txt
++++ b/aten/src/ATen/CMakeLists.txt
+@@ -362,9 +362,9 @@ 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 ${MKLDNN_LIBRARIES})
+-endif(MKLDNN_FOUND)
++if(USE_MKLDNN)
++ list(APPEND ATen_CPU_DEPENDENCY_LIBS DNNL::dnnl)
++endif(USE_MKLDNN)
+
+ list(APPEND ATen_CPU_DEPENDENCY_LIBS cpuinfo)
+
+diff --git a/caffe2/CMakeLists.txt b/caffe2/CMakeLists.txt
+index 221e3f3..417f601 100644
+--- a/caffe2/CMakeLists.txt
++++ b/caffe2/CMakeLists.txt
+@@ -110,9 +110,6 @@ if(NOT MSVC AND USE_XNNPACK)
+ if(NOT TARGET fxdiv)
+ set(FXDIV_BUILD_TESTS OFF CACHE BOOL "")
+ set(FXDIV_BUILD_BENCHMARKS OFF CACHE BOOL "")
+- add_subdirectory(
+- "${FXDIV_SOURCE_DIR}"
+- "${CMAKE_BINARY_DIR}/FXdiv")
+ endif()
+ endif()
+
+@@ -975,7 +972,6 @@ elseif(USE_CUDA)
+ endif()
+
+ if(NOT MSVC AND USE_XNNPACK)
+- TARGET_LINK_LIBRARIES(torch_cpu PRIVATE fxdiv)
+ endif()
+
+ # ==========================================================
+@@ -1314,6 +1310,7 @@ 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)
+ target_include_directories(torch_cpu INTERFACE $<INSTALL_INTERFACE:include>)
+ target_include_directories(torch_cpu PRIVATE ${Caffe2_CPU_INCLUDE})
+ target_include_directories(torch_cpu SYSTEM PRIVATE "${Caffe2_DEPENDENCY_INCLUDE}")
+@@ -1570,7 +1567,7 @@ 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)
+@@ -1601,7 +1598,7 @@ 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 ${ATen_CPU_INCLUDE})
+@@ -1622,13 +1619,13 @@ if(BUILD_TEST)
+ if(NOT MSVC)
+ add_executable(${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()
+ 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>)
+@@ -1645,7 +1642,7 @@ 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})
+@@ -1703,7 +1700,7 @@ 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}>)
+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
+ ${CMAKE_CURRENT_SOURCE_DIR}/file_adapter.cc
+diff --git a/cmake/Dependencies.cmake b/cmake/Dependencies.cmake
+index 8c0e3c2..d65576a 100644
+--- a/cmake/Dependencies.cmake
++++ b/cmake/Dependencies.cmake
+@@ -298,7 +298,7 @@ endif()
+ # --- [ PocketFFT
+ set(AT_POCKETFFT_ENABLED 0)
+ if(NOT AT_MKL_ENABLED)
+- set(POCKETFFT_INCLUDE_DIR "${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")
+@@ -501,19 +501,6 @@ 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(
+@@ -562,13 +549,6 @@ 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(
+@@ -750,11 +730,6 @@ 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 ${CMAKE_CURRENT_LIST_DIR}/../third_party/googletest/googlemock/include)
+
+ # We will not need to test benchmark lib itself.
+ set(BENCHMARK_ENABLE_TESTING OFF CACHE BOOL "Disable benchmark testing as we don't need it.")
+@@ -829,16 +804,6 @@ if(USE_FBGEMM)
+ else()
+ set(FBGEMM_LIBRARY_TYPE "static" CACHE STRING "")
+ endif()
+- add_subdirectory("${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("${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang" AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER 13.0.0)
+- # See https://github.com/pytorch/pytorch/issues/74352
+- target_compile_options_if_supported(asmjit -Wno-deprecated-copy)
+- target_compile_options_if_supported(asmjit -Wno-unused-but-set-variable)
+- endif()
+ endif()
+
+ if(USE_FBGEMM)
+@@ -1001,7 +966,7 @@ if(NOT TARGET fp16 AND NOT USE_SYSTEM_FP16)
+ "${FP16_SOURCE_DIR}"
+ "${CONFU_DEPENDENCIES_BINARY_DIR}/FP16")
+ elseif(NOT TARGET fp16 AND USE_SYSTEM_FP16)
+- add_library(fp16 STATIC "/usr/include/fp16.h")
++ add_library(fp16 STATIC "#FP16_INCLUDE_DIR")
+ set_target_properties(fp16 PROPERTIES LINKER_LANGUAGE C)
+ endif()
+ list(APPEND Caffe2_DEPENDENCY_LIBS fp16)
+@@ -1395,7 +1360,6 @@ if(USE_DISTRIBUTED AND USE_TENSORPIPE)
+
+ # Tensorpipe uses cuda_add_library
+ torch_update_find_cuda_flags()
+- add_subdirectory(${PROJECT_SOURCE_DIR}/third_party/tensorpipe)
+
+ list(APPEND Caffe2_DEPENDENCY_LIBS tensorpipe)
+ if(USE_CUDA)
+@@ -1551,7 +1515,6 @@ 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)
+@@ -1582,7 +1545,7 @@ 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)
+@@ -1752,9 +1715,8 @@ 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)
+@@ -1819,7 +1781,7 @@ 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`.
+ #
+@@ -1828,7 +1790,6 @@ 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 a41343c..6075bdd 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 ${PROJECT_SOURCE_DIR}/third_party)
+
+@@ -114,6 +114,5 @@ endif()
+ # (4) Catch-all: not supported.
+ ##############################################################################
+
+-message(WARNING "Unknown platform - I don't know how to build NNPACK. "
+- "See cmake/External/nnpack.cmake for details.")
+-set(USE_NNPACK OFF)
++set(NNPACK_FOUND TRUE)
++set(USE_NNPACK ON)
+diff --git a/cmake/public/mkldnn.cmake b/cmake/public/mkldnn.cmake
+index 50404d3..ca067f0 100644
+--- a/cmake/public/mkldnn.cmake
++++ b/cmake/public/mkldnn.cmake
+@@ -4,7 +4,7 @@ if(CPU_AARCH64)
+ include(${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)
+@@ -15,7 +15,7 @@ set_property(
+ ${MKLDNN_INCLUDE_DIR})
+ set_property(
+ TARGET caffe2::mkldnn PROPERTY INTERFACE_LINK_LIBRARIES
+- ${MKLDNN_LIBRARIES})
++ DNNL::dnnl)
+ if(BUILD_ONEDNN_GRAPH)
+ if(NOT TARGET caffe2::dnnl_graph)
+ add_library(caffe2::dnnl_graph INTERFACE IMPORTED)
+diff --git a/setup.py b/setup.py
+index 34b2854..5db117f 100644
+--- a/setup.py
++++ b/setup.py
+@@ -418,13 +418,9 @@ 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 89c6b91..0c60d08 100644
+--- a/test/cpp/c10d/CMakeLists.txt
++++ b/test/cpp/c10d/CMakeLists.txt
+@@ -16,14 +16,14 @@ function(c10d_add_test test_src)
+ add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
+ endfunction()
+
+-c10d_add_test(FileStoreTest.cpp torch_cpu gtest_main)
+-c10d_add_test(TCPStoreTest.cpp torch_cpu gtest_main)
++c10d_add_test(FileStoreTest.cpp torch_cpu gtest_main gtest)
++c10d_add_test(TCPStoreTest.cpp torch_cpu gtest_main gtest)
+ if(INSTALL_TEST)
+ install(TARGETS FileStoreTest DESTINATION bin)
+ install(TARGETS TCPStoreTest DESTINATION bin)
+ endif()
+ if(NOT WIN32)
+- c10d_add_test(HashStoreTest.cpp torch_cpu gtest_main)
++ c10d_add_test(HashStoreTest.cpp torch_cpu gtest_main gtest)
+ if(INSTALL_TEST)
+ install(TARGETS HashStoreTest DESTINATION bin)
+ endif()
+@@ -31,11 +31,11 @@ endif()
+
+ if(USE_CUDA)
+ if(USE_GLOO AND USE_C10D_GLOO)
+- c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu c10d_cuda_test gtest_main)
++ c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu c10d_cuda_test gtest_main gtest)
+ if(INSTALL_TEST)
+ install(TARGETS ProcessGroupGlooTest DESTINATION bin)
+ endif()
+- c10d_add_test(ProcessGroupGlooAsyncTest.cpp torch_cpu c10d_cuda_test gtest_main)
++ c10d_add_test(ProcessGroupGlooAsyncTest.cpp torch_cpu c10d_cuda_test gtest_main gtest)
+ endif()
+ if(USE_NCCL AND USE_C10D_NCCL)
+ # NCCL is a private dependency of libtorch, but the tests include some
+@@ -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)
+- c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu gtest_main)
++ c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu gtest_main gtest)
+ endif()
+ endif()
+
+diff --git a/test/cpp/tensorexpr/CMakeLists.txt b/test/cpp/tensorexpr/CMakeLists.txt
+index 7dff706..90b1003 100644
+--- a/test/cpp/tensorexpr/CMakeLists.txt
++++ b/test/cpp/tensorexpr/CMakeLists.txt
+@@ -54,7 +54,7 @@ target_include_directories(tutorial_tensorexpr PRIVATE ${ATen_CPU_INCLUDE})
+ # pthreadpool header. For some build environment we need add the dependency
+ # explicitly.
+ if(USE_PTHREADPOOL)
+- target_link_libraries(test_tensorexpr PRIVATE pthreadpool_interface)
++ target_link_libraries(test_tensorexpr PRIVATE pthreadpool)
+ endif()
+ if(USE_CUDA)
+ target_link_libraries(test_tensorexpr PRIVATE
deleted file mode 100644
@@ -1,156 +0,0 @@
-Use our own googletest rather than the bundled one.
-Get NNPACK to use our own PeachPy rather than the bundled one.
-
-diff --git a/caffe2/CMakeLists.txt b/caffe2/CMakeLists.txt
---- a/caffe2/CMakeLists.txt 2023-12-27 12:14:24.308751288 +0100
-+++ b/caffe2/CMakeLists.txt 2023-12-27 12:30:15.941562126 +0100
-@@ -1570,7 +1570,7 @@
- add_executable(static_runtime_bench "${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)
-@@ -1601,7 +1601,7 @@
- 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 ${ATen_CPU_INCLUDE})
-@@ -1628,7 +1628,7 @@
- endif()
- else()
- add_executable(${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>)
-@@ -1645,7 +1645,7 @@
- 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})
-@@ -1666,7 +1666,7 @@
- foreach(test_src ${Caffe2_MPS_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 ${Caffe2_CPU_INCLUDE})
-diff --git a/cmake/Dependencies.cmake b/cmake/Dependencies.cmake
-index 557ab649..ee9cf410 100644
---- a/cmake/Dependencies.cmake
-+++ b/cmake/Dependencies.cmake
-@@ -732,11 +732,6 @@ if(BUILD_TEST OR BUILD_MOBILE_BENCHMARK OR BUILD_MOBILE_TEST)
- # this shouldn't be necessary anymore.
- get_property(INC_DIR_temp DIRECTORY PROPERTY INCLUDE_DIRECTORIES)
- set_property(DIRECTORY PROPERTY INCLUDE_DIRECTORIES "")
-- add_subdirectory(${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.")
-@@ -1543,7 +1538,7 @@ 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/cmake/External/nnpack.cmake b/cmake/External/nnpack.cmake
-index a41343cb..6075bdd0 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)
-diff --git a/test/cpp/c10d/CMakeLists.txt b/test/cpp/c10d/CMakeLists.txt
-index bf91460c..ef56948f 100644
---- a/test/cpp/c10d/CMakeLists.txt
-+++ b/test/cpp/c10d/CMakeLists.txt
-@@ -16,14 +16,14 @@ function(c10d_add_test test_src)
- add_test(NAME ${test_name} COMMAND $<TARGET_FILE:${test_name}>)
- endfunction()
-
--c10d_add_test(FileStoreTest.cpp torch_cpu gtest_main)
--c10d_add_test(TCPStoreTest.cpp torch_cpu gtest_main)
-+c10d_add_test(FileStoreTest.cpp torch_cpu gtest_main gtest)
-+c10d_add_test(TCPStoreTest.cpp torch_cpu gtest_main gtest)
- if(INSTALL_TEST)
- install(TARGETS FileStoreTest DESTINATION bin)
- install(TARGETS TCPStoreTest DESTINATION bin)
- endif()
- if(NOT WIN32)
-- c10d_add_test(HashStoreTest.cpp torch_cpu gtest_main)
-+ c10d_add_test(HashStoreTest.cpp torch_cpu gtest_main gtest)
- if(INSTALL_TEST)
- install(TARGETS HashStoreTest DESTINATION bin)
- endif()
-@@ -31,11 +31,11 @@ endif()
-
- if(USE_CUDA)
- if(USE_GLOO AND USE_C10D_GLOO)
-- c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu c10d_cuda_test gtest_main)
-+ c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu c10d_cuda_test gtest_main gtest)
- if(INSTALL_TEST)
- install(TARGETS ProcessGroupGlooTest DESTINATION bin)
- endif()
-- c10d_add_test(ProcessGroupGlooAsyncTest.cpp torch_cpu c10d_cuda_test gtest_main)
-+ c10d_add_test(ProcessGroupGlooAsyncTest.cpp torch_cpu c10d_cuda_test gtest_main gtest)
- 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)
- endif()
- else()
- if(USE_GLOO AND USE_C10D_GLOO)
-- c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu gtest_main)
-+ c10d_add_test(ProcessGroupGlooTest.cpp torch_cpu gtest_main gtest)
- endif()
- endif()
-
-diff --git a/test/cpp/tensorexpr/CMakeLists.txt b/test/cpp/tensorexpr/CMakeLists.txt
-index 8fc5a0a1..643202f6 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})
- # pthreadpool header. For some build environment we need add the dependency
- # explicitly.
- if(USE_PTHREADPOOL)
-- target_link_libraries(test_tensorexpr PRIVATE pthreadpool_interface)
-+ target_link_libraries(test_tensorexpr PRIVATE pthreadpool)
- endif()
- if(USE_CUDA)
- target_link_libraries(test_tensorexpr PRIVATE