tail of build.log

file_928339.txt (text/plain), 85.31 KB, created by znjameswu on 2024-04-01 03:07:47 UTC

[1291/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/TensorFactories.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/TensorFactories.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/TensorFactories.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/TensorFactories.cu.o
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h: In static member function ‘static c10::detail::IListRefConstRef<at::OptionalTensorRef> c10::detail::IListRefTagImpl<c10::IListRefTag::Boxed, at::OptionalTensorRef>::iterator_get(const c10::List<std::optional<at::Tensor> >::const_iterator&)’:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h:171:13: warning: possibly dangling reference to a temporary [-Wdangling-reference]
  171 |     const auto& ivalue = (*it).get();
      |             ^~~~~~
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h:171:33: note: the temporary was destroyed at the end of the full expression ‘(& it)->c10::impl::ListIterator<std::optional<at::Tensor>, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::operator*().c10::impl::ListElementReference<std::optional<at::Tensor>, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::get()’
  171 |     const auto& ivalue = (*it).get();
      |                      ~~~~~~~~~~~^~
[1292/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda/cub.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub.cu.o
[1293/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/jiterator.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/jiterator.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda/jiterator.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/jiterator.cu.o
[1294/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardshrinkKernel.cu.o
[1295/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/AbsKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/AbsKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/AbsKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/AbsKernel.cu.o
[1296/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationEluKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationEluKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationEluKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationEluKernel.cu.o
[1297/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu.o
FAILED: caffe2/CMakeFiles/torch_cuda.dir/__/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu.o 
/opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/torch/csrc/distributed/c10d/quantization/quantization_gpu.cu.o
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h: In static member function ‘static c10::detail::IListRefConstRef<at::OptionalTensorRef> c10::detail::IListRefTagImpl<c10::IListRefTag::Boxed, at::OptionalTensorRef>::iterator_get(const c10::List<std::optional<at::Tensor> >::const_iterator&)’:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h:171:13: warning: possibly dangling reference to a temporary [-Wdangling-reference]
  171 |     const auto& ivalue = (*it).get();
      |             ^~~~~~
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h:171:33: note: the temporary was destroyed at the end of the full expression ‘(& it)->c10::impl::ListIterator<std::optional<at::Tensor>, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::operator*().c10::impl::ListElementReference<std::optional<at::Tensor>, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::get()’
  171 |     const auto& ivalue = (*it).get();
      |                      ~~~~~~~~~~~^~
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/boxing/impl/boxing.h: At global scope:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/boxing/impl/boxing.h:41:104: error: expected primary-expression before ‘>’ token
   41 | struct has_ivalue_to<T, guts::void_t<decltype(std::declval<IValue>().to<T>())>>
      |                                                                                                        ^
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/boxing/impl/boxing.h:41:107: error: expected primary-expression before ‘)’ token
   41 | struct has_ivalue_to<T, guts::void_t<decltype(std::declval<IValue>().to<T>())>>
      |                                                                                                           ^
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/DispatchKeyExtractor.h: In lambda function:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/DispatchKeyExtractor.h:154:24: warning: possibly dangling reference to a temporary [-Wdangling-reference]
  154 |         for (const at::Tensor& tensor : ivalue.toTensorList()) {
      |                        ^~~~~~
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/DispatchKeyExtractor.h:154:53: note: the temporary was destroyed at the end of the full expression ‘__for_begin .c10::impl::ListIterator<at::Tensor, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::operator*().c10::impl::ListElementReference<at::Tensor, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::operator std::conditional_t<true, const at::Tensor&, at::Tensor>()’
  154 |         for (const at::Tensor& tensor : ivalue.toTensorList()) {
      |                                                     ^
[1298/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardsigmoidKernel.cu.o
[1299/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationGluKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationGluKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationGluKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationGluKernel.cu.o
[1300/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationGeluKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationGeluKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationGeluKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationGeluKernel.cu.o
[1301/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardtanhKernel.cu.o
[1302/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationHardswishKernel.cu.o
[1303/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationLeakyReluKernel.cu.o
[1304/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationPreluKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationPreluKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationPreluKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationPreluKernel.cu.o
[1305/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationLogSigmoidKernel.cu.o
[1306/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationMishKernel.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationMishKernel.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/native/cuda/ActivationMishKernel.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/native/cuda/ActivationMishKernel.cu.o
[1307/1837] /usr/bin/x86_64-pc-linux-gnu-g++ -DAT_PER_OPERATOR_HEADERS -DCAFFE2_BUILD_MAIN_LIB -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DUSE_DISTRIBUTED -DUSE_EXTERNAL_MZCRC -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cpu_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/../aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/miniz-2.1.0 -I/usr/include/kineto -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/flatbuffers/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2  -march=native -mtune=sapphirerapids --param=l1-cache-size=48 --param=l2-cache-size=25600 -O3 -fgraphite-identity -floop-nest-optimize -fdevirtualize-at-ltrans -fipa-pta -fno-semantic-interposition -fuse-linker-plugin -pipe -falign-functions=32 -Wl,-O1 -Wl,--as-needed -Wl,-z,pack-relative-relocs -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DUSE_FBGEMM -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -Wall -Wextra -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow -DHAVE_AVX512_CPU_DEFINITION -DHAVE_AVX2_CPU_DEFINITION -std=gnu++17 -fPIC -DTORCH_USE_LIBUV -Wall -Wextra -Wdeprecated -Wno-unused-parameter -Wno-unused-function -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-type-limits -Wno-array-bounds -Wno-strict-overflow -Wno-strict-aliasing -Wno-maybe-uninitialized -fvisibility=hidden -fopenmp   -mavx2 -mfma -mf16c -mno-avx256-split-unaligned-load -mno-avx256-split-unaligned-store -DCPU_CAPABILITY=AVX2 -DCPU_CAPABILITY_AVX2 -MD -MT caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/GridSamplerKernel.cpp.AVX2.cpp.o -MF caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/GridSamplerKernel.cpp.AVX2.cpp.o.d -o caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/GridSamplerKernel.cpp.AVX2.cpp.o -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src/ATen/native/cpu/GridSamplerKernel.cpp.AVX2.cpp
[1308/1837] /usr/bin/x86_64-pc-linux-gnu-g++ -DAT_PER_OPERATOR_HEADERS -DCAFFE2_BUILD_MAIN_LIB -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DUSE_DISTRIBUTED -DUSE_EXTERNAL_MZCRC -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cpu_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/../aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/miniz-2.1.0 -I/usr/include/kineto -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/flatbuffers/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2  -march=native -mtune=sapphirerapids --param=l1-cache-size=48 --param=l2-cache-size=25600 -O3 -fgraphite-identity -floop-nest-optimize -fdevirtualize-at-ltrans -fipa-pta -fno-semantic-interposition -fuse-linker-plugin -pipe -falign-functions=32 -Wl,-O1 -Wl,--as-needed -Wl,-z,pack-relative-relocs -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DUSE_FBGEMM -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -Wall -Wextra -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow -DHAVE_AVX512_CPU_DEFINITION -DHAVE_AVX2_CPU_DEFINITION -std=gnu++17 -fPIC -DTORCH_USE_LIBUV -Wall -Wextra -Wdeprecated -Wno-unused-parameter -Wno-unused-function -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-type-limits -Wno-array-bounds -Wno-strict-overflow -Wno-strict-aliasing -Wno-maybe-uninitialized -fvisibility=hidden -fopenmp   -mavx2 -mfma -mf16c -mno-avx256-split-unaligned-load -mno-avx256-split-unaligned-store -DCPU_CAPABILITY=AVX2 -DCPU_CAPABILITY_AVX2 -MD -MT caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX2.cpp.o -MF caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX2.cpp.o.d -o caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX2.cpp.o -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX2.cpp
[1309/1837] /usr/bin/x86_64-pc-linux-gnu-g++ -DAT_PER_OPERATOR_HEADERS -DCAFFE2_BUILD_MAIN_LIB -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DUSE_DISTRIBUTED -DUSE_EXTERNAL_MZCRC -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cpu_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/../aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/miniz-2.1.0 -I/usr/include/kineto -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/flatbuffers/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2  -march=native -mtune=sapphirerapids --param=l1-cache-size=48 --param=l2-cache-size=25600 -O3 -fgraphite-identity -floop-nest-optimize -fdevirtualize-at-ltrans -fipa-pta -fno-semantic-interposition -fuse-linker-plugin -pipe -falign-functions=32 -Wl,-O1 -Wl,--as-needed -Wl,-z,pack-relative-relocs -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DUSE_FBGEMM -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -Wall -Wextra -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow -DHAVE_AVX512_CPU_DEFINITION -DHAVE_AVX2_CPU_DEFINITION -std=gnu++17 -fPIC -DTORCH_USE_LIBUV -Wall -Wextra -Wdeprecated -Wno-unused-parameter -Wno-unused-function -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-type-limits -Wno-array-bounds -Wno-strict-overflow -Wno-strict-aliasing -Wno-maybe-uninitialized -fvisibility=hidden -fopenmp -MD -MT caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/RegisterCPU.cpp.o -MF caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/RegisterCPU.cpp.o.d -o caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/RegisterCPU.cpp.o -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src/ATen/RegisterCPU.cpp
In file included from /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef.h:631,
                 from /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/DeviceGuard.h:3,
                 from /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src/ATen/RegisterCPU.cpp:28:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h: In static member function ‘static c10::detail::IListRefConstRef<at::OptionalTensorRef> c10::detail::IListRefTagImpl<c10::IListRefTag::Boxed, at::OptionalTensorRef>::iterator_get(const c10::List<std::optional<at::Tensor> >::const_iterator&)’:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h:171:17: warning: possibly dangling reference to a temporary [-Wdangling-reference]
  171 |     const auto& ivalue = (*it).get();
      |                 ^~~~~~
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/IListRef_inl.h:171:35: note: the temporary was destroyed at the end of the full expression ‘(& it)->c10::impl::ListIterator<std::optional<at::Tensor>, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::operator*().c10::impl::ListElementReference<std::optional<at::Tensor>, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::get()’
  171 |     const auto& ivalue = (*it).get();
      |                          ~~~~~~~~~^~
In file included from /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/OperatorEntry.h:13,
                 from /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/Dispatcher.h:6,
                 from /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/library.h:63,
                 from /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src/ATen/RegisterCPU.cpp:47:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/DispatchKeyExtractor.h: In lambda function:
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/DispatchKeyExtractor.h:154:32: warning: possibly dangling reference to a temporary [-Wdangling-reference]
  154 |         for (const at::Tensor& tensor : ivalue.toTensorList()) {
      |                                ^~~~~~
/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/core/dispatch/DispatchKeyExtractor.h:154:61: note: the temporary was destroyed at the end of the full expression ‘__for_begin .c10::impl::ListIterator<at::Tensor, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::operator*().c10::impl::ListElementReference<at::Tensor, __gnu_cxx::__normal_iterator<c10::IValue*, std::vector<c10::IValue> > >::operator std::conditional_t<true, const at::Tensor&, at::Tensor>()’
  154 |         for (const at::Tensor& tensor : ivalue.toTensorList()) {
      |                                                             ^
[1310/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub-RadixSortKeys.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub-RadixSortKeys.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda/cub-RadixSortKeys.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub-RadixSortKeys.cu.o
[1311/1837] /usr/bin/x86_64-pc-linux-gnu-g++ -DAT_PER_OPERATOR_HEADERS -DCAFFE2_BUILD_MAIN_LIB -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DUSE_DISTRIBUTED -DUSE_EXTERNAL_MZCRC -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cpu_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src/TH -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/../aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/miniz-2.1.0 -I/usr/include/kineto -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/third_party/flatbuffers/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/caffe2  -march=native -mtune=sapphirerapids --param=l1-cache-size=48 --param=l2-cache-size=25600 -O3 -fgraphite-identity -floop-nest-optimize -fdevirtualize-at-ltrans -fipa-pta -fno-semantic-interposition -fuse-linker-plugin -pipe -falign-functions=32 -Wl,-O1 -Wl,--as-needed -Wl,-z,pack-relative-relocs -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DUSE_FBGEMM -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -Wall -Wextra -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow -DHAVE_AVX512_CPU_DEFINITION -DHAVE_AVX2_CPU_DEFINITION -std=gnu++17 -fPIC -DTORCH_USE_LIBUV -Wall -Wextra -Wdeprecated -Wno-unused-parameter -Wno-unused-function -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-type-limits -Wno-array-bounds -Wno-strict-overflow -Wno-strict-aliasing -Wno-maybe-uninitialized -fvisibility=hidden -fopenmp   -mavx512f -mavx512bw -mavx512vl -mavx512dq -mfma -DCPU_CAPABILITY=AVX512 -DCPU_CAPABILITY_AVX512 -MD -MT caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX512.cpp.o -MF caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX512.cpp.o.d -o caffe2/CMakeFiles/torch_cpu.dir/__/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX512.cpp.o -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src/ATen/native/cpu/CopyKernel.cpp.AVX512.cpp
[1312/1837] /opt/cuda/bin/nvcc -forward-unknown-to-host-compiler -DAT_PER_OPERATOR_HEADERS -DGFLAGS_IS_A_DLL=0 -DGLOG_CUSTOM_PREFIX_SUPPORT -DHAVE_MALLOC_USABLE_SIZE=1 -DHAVE_MMAP=1 -DHAVE_SHM_OPEN=1 -DHAVE_SHM_UNLINK=1 -DMINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -DONNXIFI_ENABLE_EXT=1 -DONNX_ML=1 -DONNX_NAMESPACE=onnx -DPROTOBUF_USE_DLLS -DTORCH_CUDA_BUILD_MAIN_LIB -DUSE_CUDA -DUSE_DISTRIBUTED -DUSE_EXPERIMENTAL_CUDNN_V8_API -DUSE_EXTERNAL_MZCRC -DUSE_FLASH_ATTENTION -DUSE_MEM_EFF_ATTENTION -DUSE_RPC -DUSE_TENSORPIPE -D_FILE_OFFSET_BITS=64 -Dtorch_cuda_EXPORTS -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1 -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/THC -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/../../../third_party/cutlass/include -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build/caffe2/aten/src -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/cuda/../.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/c10/.. -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api -I/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/torch/csrc/api/include -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/tensorpipe/third_party/libuv/include -isystem /usr/include/opencv4 -isystem /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/cmake/../third_party/eigen -isystem /opt/cuda/include --compiler-bindir /usr/x86_64-pc-linux-gnu/gcc-bin/13 -D_GLIBCXX_USE_CXX11_ABI=1 -Xfatbin -compress-all -DONNX_NAMESPACE=onnx -gencode arch=compute_86,code=sm_86 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda  -Wno-deprecated-gpu-targets --expt-extended-lambda -DCUB_WRAPPED_NAMESPACE=at_cuda_detail -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -O2 -g -DNDEBUG -std=c++17 -Xcompiler=-fPIC -DTORCH_USE_LIBUV -Xcompiler=-Wall,-Wextra,-Wdeprecated,-Wno-unused-parameter,-Wno-unused-function,-Wno-missing-field-initializers,-Wno-unknown-pragmas,-Wno-type-limits,-Wno-array-bounds,-Wno-unknown-pragmas,-Wno-strict-overflow,-Wno-strict-aliasing,-Wno-maybe-uninitialized -Wno-deprecated-copy -MD -MT caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub-RadixSortPairs.cu.o -MF caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub-RadixSortPairs.cu.o.d -x cu -c /var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1/aten/src/ATen/cuda/cub-RadixSortPairs.cu -o caffe2/CMakeFiles/torch_cuda.dir/__/aten/src/ATen/cuda/cub-RadixSortPairs.cu.o
ninja: build stopped: subcommand failed.
 * ERROR: sci-libs/caffe2-2.2.1-r1::gentoo failed (compile phase):
 *   ninja -v -j16 -l0 failed
 * 
 * Call stack:
 *     ebuild.sh, line  136:  Called src_compile
 *   environment, line 4730:  Called cmake_src_compile
 *   environment, line 2799:  Called cmake_build
 *   environment, line 2766:  Called eninja
 *   environment, line 3342:  Called die
 * The specific snippet of code:
 *       "$@" || die -n "${*} failed"
 * 
 * If you need support, post the output of `emerge --info '=sci-libs/caffe2-2.2.1-r1::gentoo'`,
 * the complete build log and the output of `emerge -pqv '=sci-libs/caffe2-2.2.1-r1::gentoo'`.
 * The complete build log is located at '/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/temp/build.log'.
 * The ebuild environment file is located at '/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/temp/environment'.
 * Working directory: '/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1_build'
 * S: '/var/tmp/portage/sci-libs/caffe2-2.2.1-r1/work/pytorch-2.2.1'