git: c8875afebacf - main - misc/pytorch: update 2.2.2 → 2.3.1

From: Yuri Victorovich <yuri_at_FreeBSD.org>
Date: Mon, 17 Jun 2024 01:21:01 UTC
The branch main has been updated by yuri:

URL: https://cgit.FreeBSD.org/ports/commit/?id=c8875afebacf9b1f5e57564f2a48d6ed64541b33

commit c8875afebacf9b1f5e57564f2a48d6ed64541b33
Author:     Yuri Victorovich <yuri@FreeBSD.org>
AuthorDate: 2024-06-17 01:12:35 +0000
Commit:     Yuri Victorovich <yuri@FreeBSD.org>
CommitDate: 2024-06-17 01:20:37 +0000

    misc/pytorch: update 2.2.2 → 2.3.1
---
 misc/pytorch/Makefile                              |   5 +-
 misc/pytorch/distinfo                              |   6 +-
 .../patch-third__party_cpuinfo_CMakeLists.txt      |  22 +--
 misc/pytorch/pkg-plist                             | 176 +++++++++++++++++++--
 4 files changed, 177 insertions(+), 32 deletions(-)

diff --git a/misc/pytorch/Makefile b/misc/pytorch/Makefile
index 780bdba53a62..766c6b52d1d2 100644
--- a/misc/pytorch/Makefile
+++ b/misc/pytorch/Makefile
@@ -1,6 +1,6 @@
 PORTNAME=	pytorch
 DISTVERSIONPREFIX=	v
-DISTVERSION=	2.2.2
+DISTVERSION=	2.3.1
 CATEGORIES=	misc # machine-learning
 MASTER_SITES=	https://github.com/pytorch/pytorch/releases/download/v${DISTVERSION}/
 DIST_SUBDIR=	${PORTNAME}
@@ -37,7 +37,8 @@ CMAKE_ARGS=	-DPSIMD_SOURCE_DIR=${WRKSRC}/third_party/psimd \
 		-DPYTHON_EXECUTABLE=${PYTHON_CMD}
 
 MAKE_ENV=	USE_NINJA=no # ninja breaks for some reason
-LDFLAGS+=	-lexecinfo
+LDFLAGS+=	-lexecinfo \
+		-pthread
 
 BINARY_ALIAS=	make=${GMAKE} git=true
 
diff --git a/misc/pytorch/distinfo b/misc/pytorch/distinfo
index cdcc31006860..d0547799e54e 100644
--- a/misc/pytorch/distinfo
+++ b/misc/pytorch/distinfo
@@ -1,3 +1,3 @@
-TIMESTAMP = 1713844760
-SHA256 (pytorch/pytorch-v2.2.2.tar.gz) = 57a1136095bdfe769acb87876dce77212da2c995c61957a67a1f16172d235d17
-SIZE (pytorch/pytorch-v2.2.2.tar.gz) = 288213626
+TIMESTAMP = 1718421830
+SHA256 (pytorch/pytorch-v2.3.1.tar.gz) = 6c66b59345091907cd62a693b647cee224558e7f15a9b04f4f322f4f6ffeb75b
+SIZE (pytorch/pytorch-v2.3.1.tar.gz) = 277997681
diff --git a/misc/pytorch/files/patch-third__party_cpuinfo_CMakeLists.txt b/misc/pytorch/files/patch-third__party_cpuinfo_CMakeLists.txt
index 059eaaedadcf..cb63845b4f12 100644
--- a/misc/pytorch/files/patch-third__party_cpuinfo_CMakeLists.txt
+++ b/misc/pytorch/files/patch-third__party_cpuinfo_CMakeLists.txt
@@ -1,25 +1,25 @@
---- third_party/cpuinfo/CMakeLists.txt.orig	2023-10-16 12:32:17 UTC
+--- third_party/cpuinfo/CMakeLists.txt.orig	2024-06-05 19:17:57 UTC
 +++ third_party/cpuinfo/CMakeLists.txt
-@@ -77,7 +77,7 @@ IF(NOT CMAKE_SYSTEM_PROCESSOR)
+@@ -92,7 +92,7 @@ IF(NOT CMAKE_SYSTEM_PROCESSOR)
        "cpuinfo will compile, but cpuinfo_initialize() will always fail.")
      SET(CPUINFO_SUPPORTED_PLATFORM FALSE)
    ENDIF()
--ELSEIF(NOT CPUINFO_TARGET_PROCESSOR MATCHES "^(i[3-6]86|AMD64|x86(_64)?|armv[5-8].*|aarch64|arm64|ARM64)$")
-+ELSEIF(NOT CPUINFO_TARGET_PROCESSOR MATCHES "^(i[3-6]86|amd64|x86(_64)?|armv[5-8].*|aarch64|arm64|ARM64)$")
+-ELSEIF(NOT CPUINFO_TARGET_PROCESSOR MATCHES "^(i[3-6]86|AMD64|x86(_64)?|armv[5-8].*|aarch64|arm64.*|ARM64.*)$")
++ELSEIF(NOT CPUINFO_TARGET_PROCESSOR MATCHES "^(i[3-6]86|amd64|x86(_64)?|armv[5-8].*|aarch64|arm64.*|ARM64.*)$")
    MESSAGE(WARNING
      "Target processor architecture \"${CPUINFO_TARGET_PROCESSOR}\" is not supported in cpuinfo. "
      "cpuinfo will compile, but cpuinfo_initialize() will always fail.")
-@@ -89,7 +89,7 @@ IF(NOT CMAKE_SYSTEM_NAME)
+@@ -105,7 +105,7 @@ IF(NOT CMAKE_SYSTEM_NAME)
        "Target operating system is not specified. "
        "cpuinfo will compile, but cpuinfo_initialize() will always fail.")
    SET(CPUINFO_SUPPORTED_PLATFORM FALSE)
 -ELSEIF(NOT CMAKE_SYSTEM_NAME MATCHES "^(Windows|WindowsStore|CYGWIN|MSYS|Darwin|Linux|Android)$")
 +ELSEIF(NOT CMAKE_SYSTEM_NAME MATCHES "^(Windows|WindowsStore|CYGWIN|MSYS|Darwin|Linux|FreeBSD|Android)$")
-   IF(${CMAKE_VERSION} VERSION_GREATER_EQUAL "3.14" AND NOT CMAKE_SYSTEM_NAME STREQUAL "iOS")
+   IF(${CMAKE_VERSION} VERSION_GREATER_EQUAL "3.14" AND NOT IS_APPLE_OS)
      MESSAGE(WARNING
        "Target operating system \"${CMAKE_SYSTEM_NAME}\" is not supported in cpuinfo. "
-@@ -135,7 +135,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM)
-   src/cache.c)
+@@ -158,7 +158,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM)
+ SET(CPUINFO_SRCS src/api.c src/cache.c src/init.c src/log.c)
  
  IF(CPUINFO_SUPPORTED_PLATFORM)
 -  IF(NOT CMAKE_SYSTEM_NAME STREQUAL "Emscripten" AND (CPUINFO_TARGET_PROCESSOR MATCHES "^(i[3-6]86|AMD64|x86(_64)?)$" OR IOS_ARCH MATCHES "^(i386|x86_64)$"))
@@ -27,7 +27,7 @@
      LIST(APPEND CPUINFO_SRCS
        src/x86/init.c
        src/x86/info.c
-@@ -341,7 +341,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM AND CPUINFO_BUILD_MOCK_T
+@@ -354,7 +354,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM AND CPUINFO_BUILD_MOCK_T
  # ---[ cpuinfo mock library and mock tests
  IF(CPUINFO_SUPPORTED_PLATFORM AND CPUINFO_BUILD_MOCK_TESTS)
    SET(CPUINFO_MOCK_SRCS "${CPUINFO_SRCS}")
@@ -36,7 +36,7 @@
      LIST(APPEND CPUINFO_MOCK_SRCS src/x86/mockcpuid.c)
    ENDIF()
    IF(CMAKE_SYSTEM_NAME STREQUAL "Linux" OR CMAKE_SYSTEM_NAME STREQUAL "Android")
-@@ -785,7 +785,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM AND CPUINFO_BUILD_UNIT_T
+@@ -798,7 +798,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM AND CPUINFO_BUILD_UNIT_T
      ADD_TEST(NAME get-current-test COMMAND get-current-test)
    ENDIF()
  
@@ -45,7 +45,7 @@
      ADD_EXECUTABLE(brand-string-test test/name/brand-string.cc)
      CPUINFO_TARGET_ENABLE_CXX11(brand-string-test)
      CPUINFO_TARGET_RUNTIME_LIBRARY(brand-string-test)
-@@ -852,7 +852,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM AND CPUINFO_BUILD_TOOLS)
+@@ -865,7 +865,7 @@ IF(CPUINFO_SUPPORTED_PLATFORM AND CPUINFO_BUILD_TOOLS)
      CPUINFO_TARGET_RUNTIME_LIBRARY(cpuinfo-dump)
    ENDIF()
  
diff --git a/misc/pytorch/pkg-plist b/misc/pytorch/pkg-plist
index 0c609f56a2fa..40237a65f011 100644
--- a/misc/pytorch/pkg-plist
+++ b/misc/pytorch/pkg-plist
@@ -25,10 +25,12 @@ include/ATen/Config.h
 include/ATen/Context.h
 include/ATen/DLConvertor.h
 include/ATen/Device.h
+include/ATen/DeviceAccelerator.h
 include/ATen/DeviceGuard.h
 include/ATen/DimVector.h
 include/ATen/Dimname.h
 include/ATen/Dispatch.h
+include/ATen/Dispatch_v2.h
 include/ATen/DynamicLibrary.h
 include/ATen/EmptyTensor.h
 include/ATen/ExpandBase.h
@@ -132,6 +134,7 @@ include/ATen/core/List.h
 include/ATen/core/List_inl.h
 include/ATen/core/MT19937RNGEngine.h
 include/ATen/core/NamedTensor.h
+include/ATen/core/NestedIntSymNodeImpl.h
 include/ATen/core/PhiloxRNGEngine.h
 include/ATen/core/PythonFallbackKernel.h
 include/ATen/core/PythonOpRegistrationTrampoline.h
@@ -244,6 +247,7 @@ include/ATen/cpu/vec/vec512/vec512_int.h
 include/ATen/cpu/vec/vec512/vec512_qint.h
 include/ATen/cpu/vec/vec_base.h
 include/ATen/cpu/vec/vec_half.h
+include/ATen/cpu/vec/vec_n.h
 include/ATen/cpu/vml.h
 include/ATen/cuda/ATenCUDAGeneral.h
 include/ATen/cuda/ApplyGridUtils.cuh
@@ -292,6 +296,13 @@ include/ATen/cuda/detail/UnpackRaw.cuh
 include/ATen/cuda/jiterator.h
 include/ATen/cuda/jiterator_impl.h
 include/ATen/cuda/llvm_jit_strings.h
+include/ATen/cuda/tunable/GemmCommon.h
+include/ATen/cuda/tunable/GemmHipblaslt.h
+include/ATen/cuda/tunable/GemmRocblas.h
+include/ATen/cuda/tunable/StreamTimer.h
+include/ATen/cuda/tunable/Tunable.h
+include/ATen/cuda/tunable/TunableGemm.h
+include/ATen/cuda/tunable/TunableOp.h
 include/ATen/cudnn/Descriptors.h
 include/ATen/cudnn/Exceptions.h
 include/ATen/cudnn/Handle.h
@@ -299,6 +310,7 @@ include/ATen/cudnn/Handles.h
 include/ATen/cudnn/Types.h
 include/ATen/cudnn/Utils.h
 include/ATen/cudnn/cudnn-wrapper.h
+include/ATen/detail/AcceleratorHooksInterface.h
 include/ATen/detail/CUDAHooksInterface.h
 include/ATen/detail/FunctionTraits.h
 include/ATen/detail/HIPHooksInterface.h
@@ -349,6 +361,7 @@ include/ATen/mps/MPSProfiler.h
 include/ATen/mps/MPSStream.h
 include/ATen/native/Activation.h
 include/ATen/native/AdaptivePooling.h
+include/ATen/native/AmpKernels.h
 include/ATen/native/BatchLinearAlgebra.h
 include/ATen/native/BinaryOps.h
 include/ATen/native/BucketizationUtils.h
@@ -459,6 +472,7 @@ include/ATen/native/cpu/StackKernel.h
 include/ATen/native/cpu/UpSampleKernelAVXAntialias.h
 include/ATen/native/cpu/WeightNormKernel.h
 include/ATen/native/cpu/avx_mathfun.h
+include/ATen/native/cpu/int_mm_kernel.h
 include/ATen/native/cpu/mixed_data_type.h
 include/ATen/native/cpu/moments_utils.h
 include/ATen/native/cpu/utils.h
@@ -491,7 +505,6 @@ include/ATen/native/cuda/MultiTensorApply.cuh
 include/ATen/native/cuda/Normalization.cuh
 include/ATen/native/cuda/PersistentSoftmax.cuh
 include/ATen/native/cuda/Pow.cuh
-include/ATen/native/cuda/ROCmLoops.cuh
 include/ATen/native/cuda/Randperm.cuh
 include/ATen/native/cuda/Reduce.cuh
 include/ATen/native/cuda/ReduceOps.h
@@ -525,12 +538,19 @@ include/ATen/native/im2col.h
 include/ATen/native/im2col_shape_check.h
 include/ATen/native/layer_norm.h
 include/ATen/native/mps/Copy.h
+include/ATen/native/mps/MPSGraphSonomaOps.h
 include/ATen/native/mps/MPSGraphVenturaOps.h
 include/ATen/native/mps/OperationUtils.h
 include/ATen/native/mps/TensorFactory.h
 include/ATen/native/mps/UnaryConstants.h
 include/ATen/native/mps/operations/BinaryKernel.h
 include/ATen/native/mps/operations/Indexing.h
+include/ATen/native/nested/NestedTensorBinaryOps.h
+include/ATen/native/nested/NestedTensorFactories.h
+include/ATen/native/nested/NestedTensorMath.h
+include/ATen/native/nested/NestedTensorTransformerFunctions.h
+include/ATen/native/nested/NestedTensorTransformerUtils.h
+include/ATen/native/nested/NestedTensorUtils.h
 include/ATen/native/quantized/AffineQuantizer.h
 include/ATen/native/quantized/AffineQuantizerBase.h
 include/ATen/native/quantized/ConvUtils.h
@@ -607,11 +627,13 @@ include/ATen/ops/_aminmax_native.h
 include/ATen/ops/_aminmax_ops.h
 include/ATen/ops/_amp_foreach_non_finite_check_and_unscale.h
 include/ATen/ops/_amp_foreach_non_finite_check_and_unscale_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_amp_foreach_non_finite_check_and_unscale_cpu_dispatch.h
 include/ATen/ops/_amp_foreach_non_finite_check_and_unscale_cuda_dispatch.h
 include/ATen/ops/_amp_foreach_non_finite_check_and_unscale_native.h
 include/ATen/ops/_amp_foreach_non_finite_check_and_unscale_ops.h
 include/ATen/ops/_amp_update_scale.h
 include/ATen/ops/_amp_update_scale_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_amp_update_scale_cpu_dispatch.h
 include/ATen/ops/_amp_update_scale_cuda_dispatch.h
 include/ATen/ops/_amp_update_scale_meta_dispatch.h
 include/ATen/ops/_amp_update_scale_native.h
@@ -621,6 +643,10 @@ include/ATen/ops/_assert_async_cpu_dispatch.h
 include/ATen/ops/_assert_async_cuda_dispatch.h
 include/ATen/ops/_assert_async_native.h
 include/ATen/ops/_assert_async_ops.h
+include/ATen/ops/_assert_scalar.h
+include/ATen/ops/_assert_scalar_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_assert_scalar_native.h
+include/ATen/ops/_assert_scalar_ops.h
 include/ATen/ops/_assert_tensor_metadata.h
 include/ATen/ops/_assert_tensor_metadata_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_assert_tensor_metadata_native.h
@@ -699,6 +725,10 @@ include/ATen/ops/_choose_qparams_per_tensor.h
 include/ATen/ops/_choose_qparams_per_tensor_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_choose_qparams_per_tensor_native.h
 include/ATen/ops/_choose_qparams_per_tensor_ops.h
+include/ATen/ops/_chunk_cat.h
+include/ATen/ops/_chunk_cat_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_chunk_cat_native.h
+include/ATen/ops/_chunk_cat_ops.h
 include/ATen/ops/_coalesce.h
 include/ATen/ops/_coalesce_compositeexplicitautograd_dispatch.h
 include/ATen/ops/_coalesce_native.h
@@ -747,6 +777,7 @@ include/ATen/ops/_convert_indices_from_csr_to_coo_meta_dispatch.h
 include/ATen/ops/_convert_indices_from_csr_to_coo_native.h
 include/ATen/ops/_convert_indices_from_csr_to_coo_ops.h
 include/ATen/ops/_convert_weight_to_int4pack.h
+include/ATen/ops/_convert_weight_to_int4pack_cpu_dispatch.h
 include/ATen/ops/_convert_weight_to_int4pack_cuda_dispatch.h
 include/ATen/ops/_convert_weight_to_int4pack_native.h
 include/ATen/ops/_convert_weight_to_int4pack_ops.h
@@ -779,6 +810,10 @@ include/ATen/ops/_cslt_sparse_mm.h
 include/ATen/ops/_cslt_sparse_mm_cuda_dispatch.h
 include/ATen/ops/_cslt_sparse_mm_native.h
 include/ATen/ops/_cslt_sparse_mm_ops.h
+include/ATen/ops/_cslt_sparse_mm_search.h
+include/ATen/ops/_cslt_sparse_mm_search_cuda_dispatch.h
+include/ATen/ops/_cslt_sparse_mm_search_native.h
+include/ATen/ops/_cslt_sparse_mm_search_ops.h
 include/ATen/ops/_ctc_loss.h
 include/ATen/ops/_ctc_loss_backward.h
 include/ATen/ops/_ctc_loss_backward_compositeexplicitautograd_dispatch.h
@@ -1253,6 +1288,10 @@ include/ATen/ops/_functional_assert_async.h
 include/ATen/ops/_functional_assert_async_cpu_dispatch.h
 include/ATen/ops/_functional_assert_async_native.h
 include/ATen/ops/_functional_assert_async_ops.h
+include/ATen/ops/_functional_assert_scalar.h
+include/ATen/ops/_functional_assert_scalar_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_functional_assert_scalar_native.h
+include/ATen/ops/_functional_assert_scalar_ops.h
 include/ATen/ops/_functional_sym_constrain_range.h
 include/ATen/ops/_functional_sym_constrain_range_compositeexplicitautograd_dispatch.h
 include/ATen/ops/_functional_sym_constrain_range_for_size.h
@@ -1288,6 +1327,11 @@ include/ATen/ops/_fused_sdp_choice_cuda_dispatch.h
 include/ATen/ops/_fused_sdp_choice_meta_dispatch.h
 include/ATen/ops/_fused_sdp_choice_native.h
 include/ATen/ops/_fused_sdp_choice_ops.h
+include/ATen/ops/_fused_sgd.h
+include/ATen/ops/_fused_sgd_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_fused_sgd_cuda_dispatch.h
+include/ATen/ops/_fused_sgd_native.h
+include/ATen/ops/_fused_sgd_ops.h
 include/ATen/ops/_fw_primal.h
 include/ATen/ops/_fw_primal_compositeexplicitautograd_dispatch.h
 include/ATen/ops/_fw_primal_copy.h
@@ -1363,6 +1407,10 @@ include/ATen/ops/_is_zerotensor.h
 include/ATen/ops/_is_zerotensor_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_is_zerotensor_native.h
 include/ATen/ops/_is_zerotensor_ops.h
+include/ATen/ops/_lazy_clone.h
+include/ATen/ops/_lazy_clone_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_lazy_clone_native.h
+include/ATen/ops/_lazy_clone_ops.h
 include/ATen/ops/_linalg_check_errors.h
 include/ATen/ops/_linalg_check_errors_compositeexplicitautograd_dispatch.h
 include/ATen/ops/_linalg_check_errors_native.h
@@ -1383,6 +1431,11 @@ include/ATen/ops/_linalg_eigh_meta.h
 include/ATen/ops/_linalg_eigh_meta_dispatch.h
 include/ATen/ops/_linalg_eigh_native.h
 include/ATen/ops/_linalg_eigh_ops.h
+include/ATen/ops/_linalg_eigvals.h
+include/ATen/ops/_linalg_eigvals_cpu_dispatch.h
+include/ATen/ops/_linalg_eigvals_cuda_dispatch.h
+include/ATen/ops/_linalg_eigvals_native.h
+include/ATen/ops/_linalg_eigvals_ops.h
 include/ATen/ops/_linalg_slogdet.h
 include/ATen/ops/_linalg_slogdet_compositeexplicitautogradnonfunctional_dispatch.h
 include/ATen/ops/_linalg_slogdet_cpu_dispatch.h
@@ -1539,6 +1592,26 @@ include/ATen/ops/_nested_from_padded_cpu_dispatch.h
 include/ATen/ops/_nested_from_padded_cuda_dispatch.h
 include/ATen/ops/_nested_from_padded_native.h
 include/ATen/ops/_nested_from_padded_ops.h
+include/ATen/ops/_nested_get_jagged_dummy.h
+include/ATen/ops/_nested_get_jagged_dummy_native.h
+include/ATen/ops/_nested_get_jagged_dummy_ops.h
+include/ATen/ops/_nested_get_lengths.h
+include/ATen/ops/_nested_get_lengths_native.h
+include/ATen/ops/_nested_get_lengths_ops.h
+include/ATen/ops/_nested_get_offsets.h
+include/ATen/ops/_nested_get_offsets_native.h
+include/ATen/ops/_nested_get_offsets_ops.h
+include/ATen/ops/_nested_get_ragged_idx.h
+include/ATen/ops/_nested_get_ragged_idx_native.h
+include/ATen/ops/_nested_get_ragged_idx_ops.h
+include/ATen/ops/_nested_get_values.h
+include/ATen/ops/_nested_get_values_copy.h
+include/ATen/ops/_nested_get_values_copy_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_nested_get_values_copy_compositeexplicitautogradnonfunctional_dispatch.h
+include/ATen/ops/_nested_get_values_copy_native.h
+include/ATen/ops/_nested_get_values_copy_ops.h
+include/ATen/ops/_nested_get_values_native.h
+include/ATen/ops/_nested_get_values_ops.h
 include/ATen/ops/_nested_select_backward.h
 include/ATen/ops/_nested_select_backward_native.h
 include/ATen/ops/_nested_select_backward_ops.h
@@ -1585,6 +1658,14 @@ include/ATen/ops/_nested_view_from_buffer_cpu_dispatch.h
 include/ATen/ops/_nested_view_from_buffer_cuda_dispatch.h
 include/ATen/ops/_nested_view_from_buffer_native.h
 include/ATen/ops/_nested_view_from_buffer_ops.h
+include/ATen/ops/_nested_view_from_jagged.h
+include/ATen/ops/_nested_view_from_jagged_copy.h
+include/ATen/ops/_nested_view_from_jagged_copy_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_nested_view_from_jagged_copy_compositeexplicitautogradnonfunctional_dispatch.h
+include/ATen/ops/_nested_view_from_jagged_copy_native.h
+include/ATen/ops/_nested_view_from_jagged_copy_ops.h
+include/ATen/ops/_nested_view_from_jagged_native.h
+include/ATen/ops/_nested_view_from_jagged_ops.h
 include/ATen/ops/_new_zeros_with_same_feature_meta.h
 include/ATen/ops/_new_zeros_with_same_feature_meta_compositeexplicitautograd_dispatch.h
 include/ATen/ops/_new_zeros_with_same_feature_meta_native.h
@@ -1647,6 +1728,10 @@ include/ATen/ops/_prelu_kernel_cpu_dispatch.h
 include/ATen/ops/_prelu_kernel_cuda_dispatch.h
 include/ATen/ops/_prelu_kernel_native.h
 include/ATen/ops/_prelu_kernel_ops.h
+include/ATen/ops/_print.h
+include/ATen/ops/_print_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_print_native.h
+include/ATen/ops/_print_ops.h
 include/ATen/ops/_propagate_xla_data.h
 include/ATen/ops/_propagate_xla_data_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_propagate_xla_data_native.h
@@ -1697,6 +1782,10 @@ include/ATen/ops/_scaled_dot_product_attention_math.h
 include/ATen/ops/_scaled_dot_product_attention_math_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_scaled_dot_product_attention_math_native.h
 include/ATen/ops/_scaled_dot_product_attention_math_ops.h
+include/ATen/ops/_scaled_dot_product_cudnn_attention.h
+include/ATen/ops/_scaled_dot_product_cudnn_attention_cuda_dispatch.h
+include/ATen/ops/_scaled_dot_product_cudnn_attention_native.h
+include/ATen/ops/_scaled_dot_product_cudnn_attention_ops.h
 include/ATen/ops/_scaled_dot_product_efficient_attention.h
 include/ATen/ops/_scaled_dot_product_efficient_attention_backward.h
 include/ATen/ops/_scaled_dot_product_efficient_attention_backward_cuda_dispatch.h
@@ -1707,12 +1796,18 @@ include/ATen/ops/_scaled_dot_product_efficient_attention_native.h
 include/ATen/ops/_scaled_dot_product_efficient_attention_ops.h
 include/ATen/ops/_scaled_dot_product_flash_attention.h
 include/ATen/ops/_scaled_dot_product_flash_attention_backward.h
-include/ATen/ops/_scaled_dot_product_flash_attention_backward_cpu_dispatch.h
 include/ATen/ops/_scaled_dot_product_flash_attention_backward_cuda_dispatch.h
 include/ATen/ops/_scaled_dot_product_flash_attention_backward_native.h
 include/ATen/ops/_scaled_dot_product_flash_attention_backward_ops.h
-include/ATen/ops/_scaled_dot_product_flash_attention_cpu_dispatch.h
 include/ATen/ops/_scaled_dot_product_flash_attention_cuda_dispatch.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu_backward.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu_backward_cpu_dispatch.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu_backward_native.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu_backward_ops.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu_cpu_dispatch.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu_native.h
+include/ATen/ops/_scaled_dot_product_flash_attention_for_cpu_ops.h
 include/ATen/ops/_scaled_dot_product_flash_attention_native.h
 include/ATen/ops/_scaled_dot_product_flash_attention_ops.h
 include/ATen/ops/_scaled_mm.h
@@ -1939,6 +2034,10 @@ include/ATen/ops/_test_optional_intlist_compositeexplicitautograd_dispatch.h
 include/ATen/ops/_test_optional_intlist_cpu_dispatch.h
 include/ATen/ops/_test_optional_intlist_native.h
 include/ATen/ops/_test_optional_intlist_ops.h
+include/ATen/ops/_test_parallel_materialize.h
+include/ATen/ops/_test_parallel_materialize_compositeexplicitautograd_dispatch.h
+include/ATen/ops/_test_parallel_materialize_native.h
+include/ATen/ops/_test_parallel_materialize_ops.h
 include/ATen/ops/_test_serialization_subcmul.h
 include/ATen/ops/_test_serialization_subcmul_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_test_serialization_subcmul_native.h
@@ -2219,9 +2318,14 @@ include/ATen/ops/_version_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_version_native.h
 include/ATen/ops/_version_ops.h
 include/ATen/ops/_weight_int4pack_mm.h
+include/ATen/ops/_weight_int4pack_mm_cpu_dispatch.h
 include/ATen/ops/_weight_int4pack_mm_cuda_dispatch.h
 include/ATen/ops/_weight_int4pack_mm_native.h
 include/ATen/ops/_weight_int4pack_mm_ops.h
+include/ATen/ops/_weight_int8pack_mm.h
+include/ATen/ops/_weight_int8pack_mm_cpu_dispatch.h
+include/ATen/ops/_weight_int8pack_mm_native.h
+include/ATen/ops/_weight_int8pack_mm_ops.h
 include/ATen/ops/_weight_norm.h
 include/ATen/ops/_weight_norm_compositeimplicitautograd_dispatch.h
 include/ATen/ops/_weight_norm_differentiable_backward.h
@@ -3145,7 +3249,6 @@ include/ATen/ops/cudnn_convolution_add_relu_compositeexplicitautograd_dispatch.h
 include/ATen/ops/cudnn_convolution_add_relu_cuda_dispatch.h
 include/ATen/ops/cudnn_convolution_add_relu_native.h
 include/ATen/ops/cudnn_convolution_add_relu_ops.h
-include/ATen/ops/cudnn_convolution_compositeexplicitautograd_dispatch.h
 include/ATen/ops/cudnn_convolution_cuda_dispatch.h
 include/ATen/ops/cudnn_convolution_native.h
 include/ATen/ops/cudnn_convolution_ops.h
@@ -4423,6 +4526,8 @@ include/ATen/ops/linalg_eigh_native.h
 include/ATen/ops/linalg_eigh_ops.h
 include/ATen/ops/linalg_eigvals.h
 include/ATen/ops/linalg_eigvals_compositeimplicitautograd_dispatch.h
+include/ATen/ops/linalg_eigvals_cpu_dispatch.h
+include/ATen/ops/linalg_eigvals_cuda_dispatch.h
 include/ATen/ops/linalg_eigvals_native.h
 include/ATen/ops/linalg_eigvals_ops.h
 include/ATen/ops/linalg_eigvalsh.h
@@ -6131,6 +6236,10 @@ include/ATen/ops/slice_copy_compositeexplicitautograd_dispatch.h
 include/ATen/ops/slice_copy_compositeexplicitautogradnonfunctional_dispatch.h
 include/ATen/ops/slice_copy_native.h
 include/ATen/ops/slice_copy_ops.h
+include/ATen/ops/slice_inverse.h
+include/ATen/ops/slice_inverse_compositeexplicitautograd_dispatch.h
+include/ATen/ops/slice_inverse_native.h
+include/ATen/ops/slice_inverse_ops.h
 include/ATen/ops/slice_native.h
 include/ATen/ops/slice_ops.h
 include/ATen/ops/slice_scatter.h
@@ -6680,6 +6789,7 @@ include/ATen/ops/split_with_sizes_compositeexplicitautograd_dispatch.h
 include/ATen/ops/split_with_sizes_copy.h
 include/ATen/ops/split_with_sizes_copy_compositeexplicitautograd_dispatch.h
 include/ATen/ops/split_with_sizes_copy_compositeexplicitautogradnonfunctional_dispatch.h
+include/ATen/ops/split_with_sizes_copy_cuda_dispatch.h
 include/ATen/ops/split_with_sizes_copy_native.h
 include/ATen/ops/split_with_sizes_copy_ops.h
 include/ATen/ops/split_with_sizes_native.h
@@ -7332,6 +7442,11 @@ include/ATen/ops/zeros_ops.h
 include/ATen/quantized/QTensorImpl.h
 include/ATen/quantized/Quantizer.h
 include/ATen/record_function.h
+include/ATen/xpu/XPUContext.h
+include/ATen/xpu/XPUDevice.h
+include/ATen/xpu/XPUEvent.h
+include/ATen/xpu/XPUGeneratorImpl.h
+include/ATen/xpu/detail/XPUHooks.h
 include/c10/core/Allocator.h
 include/c10/core/AutogradState.h
 include/c10/core/Backend.h
@@ -7364,7 +7479,6 @@ include/c10/core/SafePyObject.h
 include/c10/core/Scalar.h
 include/c10/core/ScalarType.h
 include/c10/core/ScalarTypeToTypeMeta.h
-include/c10/core/SingletonSymNodeImpl.h
 include/c10/core/Storage.h
 include/c10/core/StorageImpl.h
 include/c10/core/Stream.h
@@ -7380,6 +7494,8 @@ include/c10/core/TensorOptions.h
 include/c10/core/UndefinedTensorImpl.h
 include/c10/core/WrapDimMinimal.h
 include/c10/core/alignment.h
+include/c10/core/impl/COW.h
+include/c10/core/impl/COWDeleter.h
 include/c10/core/impl/DeviceGuardImplInterface.h
 include/c10/core/impl/FakeGuardImpl.h
 include/c10/core/impl/GPUTrace.h
@@ -7395,8 +7511,6 @@ include/c10/core/impl/SizesAndStrides.h
 include/c10/core/impl/TorchDispatchModeTLS.h
 include/c10/core/impl/VirtualGuardImpl.h
 include/c10/core/impl/alloc_cpu.h
-include/c10/core/impl/cow/COW.h
-include/c10/core/impl/cow/COWDeleter.h
 include/c10/core/thread_pool.h
 include/c10/cuda/CUDAAlgorithm.h
 include/c10/cuda/CUDAAllocatorConfig.h
@@ -7422,8 +7536,10 @@ include/c10/mobile/CPUProfilingAllocator.h
 include/c10/test/util/Macros.h
 include/c10/test/util/complex_math_test_common.h
 include/c10/test/util/complex_test_common.h
+include/c10/util/AbortHandler.h
 include/c10/util/AlignOf.h
 include/c10/util/ApproximateClock.h
+include/c10/util/Array.h
 include/c10/util/ArrayRef.h
 include/c10/util/BFloat16-inl.h
 include/c10/util/BFloat16-math.h
@@ -7449,6 +7565,7 @@ include/c10/util/Float8_e5m2-inl.h
 include/c10/util/Float8_e5m2.h
 include/c10/util/Float8_e5m2fnuz-inl.h
 include/c10/util/Float8_e5m2fnuz.h
+include/c10/util/Float8_fnuz_cvt.h
 include/c10/util/FunctionRef.h
 include/c10/util/Half-inl.h
 include/c10/util/Half.h
@@ -7461,6 +7578,7 @@ include/c10/util/MaybeOwned.h
 include/c10/util/Metaprogramming.h
 include/c10/util/Optional.h
 include/c10/util/OptionalArrayRef.h
+include/c10/util/ParallelGuard.h
 include/c10/util/Registry.h
 include/c10/util/ScopeExit.h
 include/c10/util/SmallBuffer.h
@@ -7485,20 +7603,17 @@ include/c10/util/complex.h
 include/c10/util/complex_math.h
 include/c10/util/complex_utils.h
 include/c10/util/copysign.h
-include/c10/util/either.h
 include/c10/util/env.h
 include/c10/util/flat_hash_map.h
 include/c10/util/floating_point_utils.h
 include/c10/util/generic_math.h
 include/c10/util/hash.h
-include/c10/util/in_place.h
 include/c10/util/int128.h
 include/c10/util/intrusive_ptr.h
 include/c10/util/irange.h
 include/c10/util/llvmMathExtras.h
 include/c10/util/logging_is_google_glog.h
 include/c10/util/logging_is_not_google_glog.h
-include/c10/util/math_compat.h
 include/c10/util/numa.h
 include/c10/util/order_preserving_flat_hash_map.h
 include/c10/util/overloaded.h
@@ -7522,6 +7637,14 @@ include/c10/util/tempfile.h
 include/c10/util/thread_name.h
 include/c10/util/typeid.h
 include/c10/util/win32-headers.h
+include/c10/xpu/XPUCachingAllocator.h
+include/c10/xpu/XPUDeviceProp.h
+include/c10/xpu/XPUException.h
+include/c10/xpu/XPUFunctions.h
+include/c10/xpu/XPUMacros.h
+include/c10/xpu/XPUStream.h
+include/c10/xpu/impl/XPUGuardImpl.h
+include/c10/xpu/test/impl/XPUTest.h
 include/caffe2/contrib/aten/aten_op.h
 include/caffe2/contrib/aten/aten_op_template.h
 include/caffe2/contrib/fakelowp/batch_matmul_fp16_fake_op.h
@@ -8187,7 +8310,6 @@ include/caffe2/video/optical_flow.h
 include/caffe2/video/video_decoder.h
 include/caffe2/video/video_input_op.h
 include/caffe2/video/video_io.h
-include/clog.h
 include/cpuinfo.h
 include/dnnl.h
 include/dnnl.hpp
@@ -8220,6 +8342,7 @@ include/kineto/GenericTraceActivity.h
 include/kineto/IActivityProfiler.h
 include/kineto/ILoggerObserver.h
 include/kineto/ITraceActivity.h
+include/kineto/LoggingAPI.h
 include/kineto/ThreadUtil.h
 include/kineto/TraceSpan.h
 include/kineto/libkineto.h
@@ -8429,6 +8552,7 @@ include/torch/csrc/api/include/torch/torch.h
 include/torch/csrc/api/include/torch/types.h
 include/torch/csrc/api/include/torch/utils.h
 include/torch/csrc/api/include/torch/version.h
+include/torch/csrc/api/include/torch/xpu.h
 include/torch/csrc/autograd/FunctionsManual.h
 include/torch/csrc/autograd/InferenceMode.h
 include/torch/csrc/autograd/VariableTypeUtils.h
@@ -8450,6 +8574,7 @@ include/torch/csrc/autograd/functions/tensor.h
 include/torch/csrc/autograd/functions/utils.h
 include/torch/csrc/autograd/generated/Functions.h
 include/torch/csrc/autograd/generated/VariableType.h
+include/torch/csrc/autograd/generated/ViewFuncs.h
 include/torch/csrc/autograd/generated/python_functions.h
 include/torch/csrc/autograd/generated/python_return_types.h
 include/torch/csrc/autograd/generated/variable_factories.h
@@ -8491,6 +8616,7 @@ include/torch/csrc/autograd/utils/python_arg_parsing.h
 include/torch/csrc/autograd/utils/warnings.h
 include/torch/csrc/autograd/utils/wrap_outputs.h
 include/torch/csrc/autograd/variable.h
+include/torch/csrc/autograd/variable_info.h
 include/torch/csrc/copy_utils.h
 include/torch/csrc/cpu/Module.h
 include/torch/csrc/cuda/CUDAPluggableAllocator.h
@@ -8523,8 +8649,8 @@ include/torch/csrc/distributed/autograd/rpc_messages/rref_backward_req.h
 include/torch/csrc/distributed/autograd/rpc_messages/rref_backward_resp.h
 include/torch/csrc/distributed/autograd/utils.h
 include/torch/csrc/distributed/c10d/Backend.hpp
+include/torch/csrc/distributed/c10d/FakeProcessGroup.hpp
 include/torch/csrc/distributed/c10d/FileStore.hpp
-include/torch/csrc/distributed/c10d/Functional.hpp
 include/torch/csrc/distributed/c10d/GlooDeviceFactory.hpp
 include/torch/csrc/distributed/c10d/GroupRegistry.hpp
 include/torch/csrc/distributed/c10d/HashStore.hpp
@@ -8557,6 +8683,7 @@ include/torch/csrc/distributed/c10d/debug.h
 include/torch/csrc/distributed/c10d/default_comm_hooks.hpp
 include/torch/csrc/distributed/c10d/error.h
 include/torch/csrc/distributed/c10d/exception.h
+include/torch/csrc/distributed/c10d/intra_node_comm.hpp
 include/torch/csrc/distributed/c10d/logger.hpp
 include/torch/csrc/distributed/c10d/logging.h
 include/torch/csrc/distributed/c10d/python_comm_hook.h
@@ -8599,21 +8726,34 @@ include/torch/csrc/distributed/rpc/types.h
 include/torch/csrc/distributed/rpc/unpickled_python_call.h
 include/torch/csrc/distributed/rpc/unpickled_python_remote_call.h
 include/torch/csrc/distributed/rpc/utils.h
+include/torch/csrc/dynamo/cache_entry.h
 include/torch/csrc/dynamo/compiled_autograd.h
 include/torch/csrc/dynamo/cpp_shim.h
 include/torch/csrc/dynamo/cpython_defs.h
+include/torch/csrc/dynamo/debug_macros.h
 include/torch/csrc/dynamo/eval_frame.h
+include/torch/csrc/dynamo/extra_state.h
 include/torch/csrc/dynamo/guards.h
 include/torch/csrc/dynamo/init.h
 include/torch/csrc/dynamo/python_compiled_autograd.h
+include/torch/csrc/dynamo/utils.h
 include/torch/csrc/functorch/init.h
-include/torch/csrc/inductor/aoti_model_container_runner.h
-include/torch/csrc/inductor/aoti_model_container_runner_cuda.h
+include/torch/csrc/inductor/aoti_runner/model_container_runner.h
+include/torch/csrc/inductor/aoti_runner/model_container_runner_cpu.h
+include/torch/csrc/inductor/aoti_runner/model_container_runner_cuda.h
+include/torch/csrc/inductor/aoti_runner/pybind.h
+include/torch/csrc/inductor/aoti_runtime/arrayref_tensor.h
 include/torch/csrc/inductor/aoti_runtime/device_utils.h
 include/torch/csrc/inductor/aoti_runtime/interface.h
 include/torch/csrc/inductor/aoti_runtime/model.h
 include/torch/csrc/inductor/aoti_runtime/model_container.h
+include/torch/csrc/inductor/aoti_runtime/scalar_to_tensor.h
+include/torch/csrc/inductor/aoti_runtime/thread_local.h
+include/torch/csrc/inductor/aoti_runtime/utils.h
+include/torch/csrc/inductor/aoti_runtime/utils_cuda.h
 include/torch/csrc/inductor/aoti_torch/c/shim.h
+include/torch/csrc/inductor/aoti_torch/generated/c_shim_cpu.h
+include/torch/csrc/inductor/aoti_torch/generated/c_shim_cuda.h
 include/torch/csrc/inductor/aoti_torch/proxy_executor.h
 include/torch/csrc/inductor/aoti_torch/tensor_converter.h
 include/torch/csrc/inductor/aoti_torch/utils.h
@@ -9120,7 +9260,7 @@ include/torch/csrc/utils.h
 include/torch/csrc/utils/byte_order.h
 include/torch/csrc/utils/cpp_stacktraces.h
 include/torch/csrc/utils/cuda_enabled.h
-include/torch/csrc/utils/cuda_lazy_init.h
+include/torch/csrc/utils/device_lazy_init.h
 include/torch/csrc/utils/disable_torch_function.h
 include/torch/csrc/utils/init.h
 include/torch/csrc/utils/invalid_arguments.h
@@ -9161,6 +9301,9 @@ include/torch/csrc/utils/throughput_benchmark.h
 include/torch/csrc/utils/torch_dispatch_mode.h
 include/torch/csrc/utils/variadic.h
 include/torch/csrc/utils/verbose.h
+include/torch/csrc/xpu/Event.h
+include/torch/csrc/xpu/Module.h
+include/torch/csrc/xpu/Stream.h
 include/torch/custom_class.h
 include/torch/custom_class_detail.h
 include/torch/extension.h
@@ -9174,7 +9317,6 @@ lib/libCaffe2_perfkernels_avx.a
 lib/libCaffe2_perfkernels_avx2.a
 lib/libCaffe2_perfkernels_avx512.a
 lib/libc10.so
-lib/libclog.a
 lib/libcpuinfo.a
 lib/libdnnl.a
 lib/libkineto.a
@@ -9193,6 +9335,7 @@ share/cmake/Caffe2/Caffe2Targets-%%CMAKE_BUILD_TYPE%%.cmake
 share/cmake/Caffe2/Caffe2Targets.cmake
 share/cmake/Caffe2/FindCUDAToolkit.cmake
 share/cmake/Caffe2/FindCUSPARSELT.cmake
+share/cmake/Caffe2/FindSYCLToolkit.cmake
 share/cmake/Caffe2/Modules_CUDA_fix/FindCUDA.cmake
 share/cmake/Caffe2/Modules_CUDA_fix/FindCUDNN.cmake
 share/cmake/Caffe2/Modules_CUDA_fix/README.md
@@ -9213,6 +9356,7 @@ share/cmake/Caffe2/public/mkl.cmake
 share/cmake/Caffe2/public/mkldnn.cmake
 share/cmake/Caffe2/public/protobuf.cmake
 share/cmake/Caffe2/public/utils.cmake
+share/cmake/Caffe2/public/xpu.cmake
 share/cmake/Torch/TorchConfig.cmake
 share/cmake/Torch/TorchConfigVersion.cmake
 share/cmake/kineto/kinetoLibraryConfig-%%CMAKE_BUILD_TYPE%%.cmake