diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conv_depthwise2d.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conv_depthwise2d.h new file mode 100644 index 0000000000000000000000000000000000000000..b0ff1f0652dfb2fb225b55aa4afc9f0cdea9e57e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conv_depthwise2d.h @@ -0,0 +1,91 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_conv_depthwise2d.out(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, SymInt[2] dilation, *, Tensor(a!) out) -> Tensor(a!) +inline const at::Tensor & _conv_depthwise2d_out(const at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), out); +} +namespace symint { + template ::value>> + const at::Tensor & _conv_depthwise2d_out(const at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), out); + } +} + +// aten::_conv_depthwise2d.out(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, SymInt[2] dilation, *, Tensor(a!) out) -> Tensor(a!) +inline const at::Tensor & _conv_depthwise2d_outf(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, const at::Tensor & out) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), out); +} +namespace symint { + template ::value>> + const at::Tensor & _conv_depthwise2d_outf(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, const at::Tensor & out) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation), out); + } +} + +// aten::_conv_depthwise2d.out(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, SymInt[2] dilation, *, Tensor(a!) out) -> Tensor(a!) +inline const at::Tensor & _conv_depthwise2d_symint_out(const at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, kernel_size, bias, stride, padding, dilation, out); +} +namespace symint { + template ::value>> + const at::Tensor & _conv_depthwise2d_out(const at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, kernel_size, bias, stride, padding, dilation, out); + } +} + +// aten::_conv_depthwise2d.out(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, SymInt[2] dilation, *, Tensor(a!) out) -> Tensor(a!) +inline const at::Tensor & _conv_depthwise2d_symint_outf(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, const at::Tensor & out) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, kernel_size, bias, stride, padding, dilation, out); +} +namespace symint { + template ::value>> + const at::Tensor & _conv_depthwise2d_outf(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, const at::Tensor & out) { + return at::_ops::_conv_depthwise2d_out::call(self, weight, kernel_size, bias, stride, padding, dilation, out); + } +} + +// aten::_conv_depthwise2d(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, SymInt[2] dilation) -> Tensor +inline at::Tensor _conv_depthwise2d(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation) { + return at::_ops::_conv_depthwise2d::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation)); +} +namespace symint { + template ::value>> + at::Tensor _conv_depthwise2d(const at::Tensor & self, const at::Tensor & weight, at::IntArrayRef kernel_size, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation) { + return at::_ops::_conv_depthwise2d::call(self, weight, c10::fromIntArrayRefSlow(kernel_size), bias, c10::fromIntArrayRefSlow(stride), c10::fromIntArrayRefSlow(padding), c10::fromIntArrayRefSlow(dilation)); + } +} + +// aten::_conv_depthwise2d(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias, SymInt[2] stride, SymInt[2] padding, SymInt[2] dilation) -> Tensor +inline at::Tensor _conv_depthwise2d_symint(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation) { + return at::_ops::_conv_depthwise2d::call(self, weight, kernel_size, bias, stride, padding, dilation); +} +namespace symint { + template ::value>> + at::Tensor _conv_depthwise2d(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation) { + return at::_ops::_conv_depthwise2d::call(self, weight, kernel_size, bias, stride, padding, dilation); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c5fa62c19f4ccb4af811639cce19bdfad1b5ee61 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_backward_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor _embedding_bag_backward_symint(const at::Tensor & grad, const at::Tensor & indices, const at::Tensor & offsets, const at::Tensor & offset2bag, const at::Tensor & bag_size, const at::Tensor & maximum_indices, c10::SymInt num_weights, bool scale_grad_by_freq, int64_t mode, bool sparse, const c10::optional & per_sample_weights, int64_t padding_idx=-1); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_max_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_max_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0758ebb4eac18683897072174139779648c12629 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_max_cpu_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API ::std::vector _foreach_clamp_max(at::TensorList self, const at::Scalar & scalar); +TORCH_API void _foreach_clamp_max_(at::TensorList self, const at::Scalar & scalar); +TORCH_API ::std::vector _foreach_clamp_max(at::TensorList self, at::TensorList other); +TORCH_API void _foreach_clamp_max_(at::TensorList self, at::TensorList other); +TORCH_API ::std::vector _foreach_clamp_max(at::TensorList self, at::ArrayRef scalars); +TORCH_API void _foreach_clamp_max_(at::TensorList self, at::ArrayRef scalars); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_div_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_div_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c7b9bceb52c5c57048a171cdcb23a0250398fede --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_div_native.h @@ -0,0 +1,40 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API void _foreach_div_Scalar_out(at::TensorList self, const at::Scalar & scalar, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_div_scalar_kernel_slow(at::TensorList self, const at::Scalar & scalar); +TORCH_API void foreach_tensor_div_scalar_kernel_slow_(at::TensorList self, const at::Scalar & scalar); +TORCH_API ::std::vector foreach_tensor_div_scalar_kernel_cuda(at::TensorList self, const at::Scalar & scalar); +TORCH_API void foreach_tensor_div_scalar_kernel_cuda_(at::TensorList self, const at::Scalar & scalar); +TORCH_API void _foreach_div_List_out(at::TensorList self, at::TensorList other, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_div_list_kernel_slow(at::TensorList self, at::TensorList other); +TORCH_API void foreach_tensor_div_list_kernel_slow_(at::TensorList self, at::TensorList other); +TORCH_API ::std::vector foreach_tensor_div_list_kernel_cuda(at::TensorList self, at::TensorList other); +TORCH_API void foreach_tensor_div_list_kernel_cuda_(at::TensorList self, at::TensorList other); +TORCH_API void _foreach_div_ScalarList_out(at::TensorList self, at::ArrayRef scalars, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_div_scalarlist_kernel_slow(at::TensorList self, at::ArrayRef scalars); +TORCH_API void foreach_tensor_div_scalarlist_kernel_slow_(at::TensorList self, at::ArrayRef scalars); +TORCH_API ::std::vector foreach_tensor_div_scalarlist_kernel_cuda(at::TensorList self, at::ArrayRef scalars); +TORCH_API void foreach_tensor_div_scalarlist_kernel_cuda_(at::TensorList self, at::ArrayRef scalars); +TORCH_API void _foreach_div_Tensor_out(at::TensorList self, const at::Tensor & other, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_div_tensor_kernel_slow(at::TensorList self, const at::Tensor & other); +TORCH_API void foreach_tensor_div_tensor_kernel_slow_(at::TensorList self, const at::Tensor & other); +TORCH_API ::std::vector foreach_tensor_div_tensor_kernel_cuda(at::TensorList self, const at::Tensor & other); +TORCH_API void foreach_tensor_div_tensor_kernel_cuda_(at::TensorList self, const at::Tensor & other); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_expm1_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_expm1_native.h new file mode 100644 index 0000000000000000000000000000000000000000..9c281778e4240ccc63a4b5acb751466e1309ba7e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_expm1_native.h @@ -0,0 +1,25 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API void _foreach_expm1_out(at::TensorList self, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_expm1_slow(at::TensorList self); +TORCH_API void foreach_tensor_expm1_slow_(at::TensorList self); +TORCH_API ::std::vector foreach_tensor_expm1_cuda(at::TensorList self); +TORCH_API void foreach_tensor_expm1_cuda_(at::TensorList self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log10_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log10_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c41c563d4cca25578ac59d23c05b351b19c8d239 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log10_native.h @@ -0,0 +1,25 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API void _foreach_log10_out(at::TensorList self, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_log10_slow(at::TensorList self); +TORCH_API void foreach_tensor_log10_slow_(at::TensorList self); +TORCH_API ::std::vector foreach_tensor_log10_cuda(at::TensorList self); +TORCH_API void foreach_tensor_log10_cuda_(at::TensorList self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_reciprocal.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_reciprocal.h new file mode 100644 index 0000000000000000000000000000000000000000..b1203ee6ff46f45a3486061b6c985c287370caa2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_reciprocal.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_foreach_reciprocal(Tensor[] self) -> Tensor[] +inline ::std::vector _foreach_reciprocal(at::TensorList self) { + return at::_ops::_foreach_reciprocal::call(self); +} + +// aten::_foreach_reciprocal_(Tensor(a!)[] self) -> () +inline void _foreach_reciprocal_(at::TensorList self) { + return at::_ops::_foreach_reciprocal_::call(self); +} + +// aten::_foreach_reciprocal.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_reciprocal_out(at::TensorList out, at::TensorList self) { + return at::_ops::_foreach_reciprocal_out::call(self, out); +} +// aten::_foreach_reciprocal.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_reciprocal_outf(at::TensorList self, at::TensorList out) { + return at::_ops::_foreach_reciprocal_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_functional_sym_constrain_range_for_size_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_functional_sym_constrain_range_for_size_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..95a3e913cd9e7ab33a619aae1b76b898aa25d1a2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_functional_sym_constrain_range_for_size_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _functional_sym_constrain_range_for_size { + using schema = at::Tensor (const at::Scalar &, c10::optional, c10::optional, const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_functional_sym_constrain_range_for_size") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_functional_sym_constrain_range_for_size(Scalar size, int? min, int? max, Tensor dep_token) -> Tensor") + static at::Tensor call(const at::Scalar & size, c10::optional min, c10::optional max, const at::Tensor & dep_token); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & size, c10::optional min, c10::optional max, const at::Tensor & dep_token); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_eigh_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_eigh_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..6fd8057e8fa55cabefbae8a41412f6bbb8de3300 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_eigh_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API ::std::tuple _linalg_eigh(const at::Tensor & A, c10::string_view UPLO="L", bool compute_v=true); +TORCH_API ::std::tuple _linalg_eigh_out(at::Tensor & eigenvalues, at::Tensor & eigenvectors, const at::Tensor & A, c10::string_view UPLO="L", bool compute_v=true); +TORCH_API ::std::tuple _linalg_eigh_outf(const at::Tensor & A, c10::string_view UPLO, bool compute_v, at::Tensor & eigenvalues, at::Tensor & eigenvectors); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_from_padded_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_from_padded_native.h new file mode 100644 index 0000000000000000000000000000000000000000..02519fded2261c87f047483e858e60aa66c0078a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_from_padded_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor & _nested_from_padded_out(const at::Tensor & padded, const at::Tensor & cpu_nested_shape_example, bool fuse_transform_0213, at::Tensor & out); +TORCH_API at::Tensor nested_from_padded_generic(const at::Tensor & padded, const at::Tensor & cpu_nested_shape_example, bool fuse_transform_0213=false); +TORCH_API at::Tensor nested_from_padded_cuda(const at::Tensor & padded, const at::Tensor & cpu_nested_shape_example, bool fuse_transform_0213=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnpack_available_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnpack_available_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..bff83d424f68893804b769008362bd60948aa01c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnpack_available_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API bool _nnpack_available(); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnz.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnz.h new file mode 100644 index 0000000000000000000000000000000000000000..50063e91a7645063e251c06062ba41859892586e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nnz.h @@ -0,0 +1,26 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_copy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_copy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..ec9b77a0e21ca36de0b10d3bac907ff1a5f02dd1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_copy_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _reshape_copy { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_reshape_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_reshape_copy(Tensor self, SymInt[] size) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef size); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef size); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_ff.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_ff.h new file mode 100644 index 0000000000000000000000000000000000000000..31f6d99f46272c090cbbf32f54ba2ee811bf1b06 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_ff.h @@ -0,0 +1,30 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_sobol_engine_ff_(Tensor(a!) self, int n, Tensor sobolstate, int dimension, int num_generated) -> Tensor(a!) +inline at::Tensor & _sobol_engine_ff_(at::Tensor & self, int64_t n, const at::Tensor & sobolstate, int64_t dimension, int64_t num_generated) { + return at::_ops::_sobol_engine_ff_::call(self, n, sobolstate, dimension, num_generated); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_log_softmax_backward_data.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_log_softmax_backward_data.h new file mode 100644 index 0000000000000000000000000000000000000000..c3465e6b605aa3da6028e32fc513e32e25c052c8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_log_softmax_backward_data.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_sparse_log_softmax_backward_data(Tensor grad_output, Tensor output, int dim, Tensor self) -> Tensor +inline at::Tensor _sparse_log_softmax_backward_data(const at::Tensor & grad_output, const at::Tensor & output, int64_t dim, const at::Tensor & self) { + return at::_ops::_sparse_log_softmax_backward_data::call(grad_output, output, dim, self); +} + +// aten::_sparse_log_softmax_backward_data.out(Tensor grad_output, Tensor output, int dim, Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _sparse_log_softmax_backward_data_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & output, int64_t dim, const at::Tensor & self) { + return at::_ops::_sparse_log_softmax_backward_data_out::call(grad_output, output, dim, self, out); +} +// aten::_sparse_log_softmax_backward_data.out(Tensor grad_output, Tensor output, int dim, Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _sparse_log_softmax_backward_data_outf(const at::Tensor & grad_output, const at::Tensor & output, int64_t dim, const at::Tensor & self, at::Tensor & out) { + return at::_ops::_sparse_log_softmax_backward_data_out::call(grad_output, output, dim, self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_functorch_fallback.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_functorch_fallback.h new file mode 100644 index 0000000000000000000000000000000000000000..118bc7e28e97694462701702225713f24b5ab9ab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_functorch_fallback.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_test_functorch_fallback(Tensor self, Tensor other) -> Tensor +inline at::Tensor _test_functorch_fallback(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::_test_functorch_fallback::call(self, other); +} + +// aten::_test_functorch_fallback.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _test_functorch_fallback_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::_test_functorch_fallback_out::call(self, other, out); +} +// aten::_test_functorch_fallback.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _test_functorch_fallback_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::_test_functorch_fallback_out::call(self, other, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward_impl_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward_impl_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..aaec544c26f209fa0f60ce88b6585df97d259144 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward_impl_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API ::std::tuple _thnn_fused_lstm_cell_backward_impl_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, const c10::optional & grad_hy, const c10::optional & grad_cy, const at::Tensor & cx, const at::Tensor & cy, const at::Tensor & workspace, bool has_bias); +TORCH_API ::std::tuple _thnn_fused_lstm_cell_backward_impl_outf(const c10::optional & grad_hy, const c10::optional & grad_cy, const at::Tensor & cx, const at::Tensor & cy, const at::Tensor & workspace, bool has_bias, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csr_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csr_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..eea2e0e9f7dc1514d89fb54e548420a66504e59c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csr_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & _to_sparse_csr_out(at::Tensor & out, const at::Tensor & self, c10::optional dense_dim=c10::nullopt); +TORCH_API at::Tensor & _to_sparse_csr_outf(const at::Tensor & self, c10::optional dense_dim, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a5d2d0df6c10f6ffd39f8e21750f33135ef95fee --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_backward_native.h @@ -0,0 +1,26 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured__upsample_nearest_exact3d_backward_out_cpu : public at::meta::structured__upsample_nearest_exact3d_backward { +void impl(const at::Tensor & grad_output, at::ArrayRef output_size, at::ArrayRef input_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & grad_input); +}; +struct TORCH_API structured__upsample_nearest_exact3d_backward_out_cuda : public at::meta::structured__upsample_nearest_exact3d_backward { +void impl(const at::Tensor & grad_output, at::ArrayRef output_size, at::ArrayRef input_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & grad_input); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_int8pack_mm.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_int8pack_mm.h new file mode 100644 index 0000000000000000000000000000000000000000..74e7b80a48fc27c20260e0b39ef8663f626afc4b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_weight_int8pack_mm.h @@ -0,0 +1,30 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_weight_int8pack_mm(Tensor self, Tensor mat2, Tensor scales) -> Tensor +inline at::Tensor _weight_int8pack_mm(const at::Tensor & self, const at::Tensor & mat2, const at::Tensor & scales) { + return at::_ops::_weight_int8pack_mm::call(self, mat2, scales); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmv.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmv.h new file mode 100644 index 0000000000000000000000000000000000000000..94231ac0b986a9c2e82ccd863fc1a76466931868 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmv.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::addmv(Tensor self, Tensor mat, Tensor vec, *, Scalar beta=1, Scalar alpha=1) -> Tensor +inline at::Tensor addmv(const at::Tensor & self, const at::Tensor & mat, const at::Tensor & vec, const at::Scalar & beta=1, const at::Scalar & alpha=1) { + return at::_ops::addmv::call(self, mat, vec, beta, alpha); +} + +// aten::addmv_(Tensor(a!) self, Tensor mat, Tensor vec, *, Scalar beta=1, Scalar alpha=1) -> Tensor(a!) +inline at::Tensor & addmv_(at::Tensor & self, const at::Tensor & mat, const at::Tensor & vec, const at::Scalar & beta=1, const at::Scalar & alpha=1) { + return at::_ops::addmv_::call(self, mat, vec, beta, alpha); +} + +// aten::addmv.out(Tensor self, Tensor mat, Tensor vec, *, Scalar beta=1, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & addmv_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & mat, const at::Tensor & vec, const at::Scalar & beta=1, const at::Scalar & alpha=1) { + return at::_ops::addmv_out::call(self, mat, vec, beta, alpha, out); +} +// aten::addmv.out(Tensor self, Tensor mat, Tensor vec, *, Scalar beta=1, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & addmv_outf(const at::Tensor & self, const at::Tensor & mat, const at::Tensor & vec, const at::Scalar & beta, const at::Scalar & alpha, at::Tensor & out) { + return at::_ops::addmv_out::call(self, mat, vec, beta, alpha, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/alias_copy_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/alias_copy_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..91a30e97276ae5688ad401101304851f9d7b6de0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/alias_copy_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & alias_copy_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & alias_copy_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan.h new file mode 100644 index 0000000000000000000000000000000000000000..d026f6cf89bea329586d9834719f9ffe17a77cb1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::atan(Tensor self) -> Tensor +inline at::Tensor atan(const at::Tensor & self) { + return at::_ops::atan::call(self); +} + +// aten::atan_(Tensor(a!) self) -> Tensor(a!) +inline at::Tensor & atan_(at::Tensor & self) { + return at::_ops::atan_::call(self); +} + +// aten::atan.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & atan_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::atan_out::call(self, out); +} +// aten::atan.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & atan_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::atan_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..40a12ecd8d81e8dd872987775c81e8315eb7f963 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_atan2 : public TensorIteratorBase { + + + void meta(const at::Tensor & self, const at::Tensor & other); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_update_stats_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_update_stats_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3103fe5a32be8e4e1895d6679a4221332a63d61e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/batch_norm_update_stats_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API batch_norm_update_stats { + using schema = ::std::tuple (const at::Tensor &, const c10::optional &, const c10::optional &, double); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::batch_norm_update_stats") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "batch_norm_update_stats(Tensor input, Tensor? running_mean, Tensor? running_var, float momentum) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & input, const c10::optional & running_mean, const c10::optional & running_var, double momentum); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const c10::optional & running_mean, const c10::optional & running_var, double momentum); +}; + +struct TORCH_API batch_norm_update_stats_out { + using schema = ::std::tuple (const at::Tensor &, const c10::optional &, const c10::optional &, double, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::batch_norm_update_stats") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "batch_norm_update_stats.out(Tensor input, Tensor? running_mean, Tensor? running_var, float momentum, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!))") + static ::std::tuple call(const at::Tensor & input, const c10::optional & running_mean, const c10::optional & running_var, double momentum, at::Tensor & out0, at::Tensor & out1); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const c10::optional & running_mean, const c10::optional & running_var, double momentum, at::Tensor & out0, at::Tensor & out1); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/binomial_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/binomial_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..06f41fbe7355857c96601293d64a8e83ea322893 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/binomial_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API binomial { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::binomial") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "binomial(Tensor count, Tensor prob, Generator? generator=None) -> Tensor") + static at::Tensor call(const at::Tensor & count, const at::Tensor & prob, c10::optional generator); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & count, const at::Tensor & prob, c10::optional generator); +}; + +struct TORCH_API binomial_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, c10::optional, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::binomial") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "binomial.out(Tensor count, Tensor prob, Generator? generator=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & count, const at::Tensor & prob, c10::optional generator, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & count, const at::Tensor & prob, c10::optional generator, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_or_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_or_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..74958804b3329861f71999c15279ea78ab449482 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_or_meta_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor bitwise_or(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_or_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_or_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & bitwise_or_(at::Tensor & self, const at::Tensor & other); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_xor_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_xor_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..667635e3ef5fd5980d07a491d9e20fb822e07ccc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_xor_cuda_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor bitwise_xor(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_xor_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_xor_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & bitwise_xor_(at::Tensor & self, const at::Tensor & other); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/blackman_window_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/blackman_window_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..e289d3e58cb394c2dcb1e51faa205bd1682db6e6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/blackman_window_ops.h @@ -0,0 +1,61 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API blackman_window { + using schema = at::Tensor (int64_t, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::blackman_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "blackman_window(int window_length, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(int64_t window_length, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API blackman_window_periodic { + using schema = at::Tensor (int64_t, bool, c10::optional, c10::optional, c10::optional, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::blackman_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "periodic") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "blackman_window.periodic(int window_length, bool periodic, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(int64_t window_length, bool periodic, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, bool periodic, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API blackman_window_out { + using schema = at::Tensor & (int64_t, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::blackman_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "blackman_window.out(int window_length, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(int64_t window_length, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, at::Tensor & out); +}; + +struct TORCH_API blackman_window_periodic_out { + using schema = at::Tensor & (int64_t, bool, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::blackman_window") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "periodic_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "blackman_window.periodic_out(int window_length, bool periodic, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(int64_t window_length, bool periodic, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, int64_t window_length, bool periodic, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bucketize.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bucketize.h new file mode 100644 index 0000000000000000000000000000000000000000..eed7416ca9d3cab1068c7ba9d96972f6856a3753 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bucketize.h @@ -0,0 +1,53 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::bucketize.Tensor(Tensor self, Tensor boundaries, *, bool out_int32=False, bool right=False) -> Tensor +inline at::Tensor bucketize(const at::Tensor & self, const at::Tensor & boundaries, bool out_int32=false, bool right=false) { + return at::_ops::bucketize_Tensor::call(self, boundaries, out_int32, right); +} + +// aten::bucketize.Tensor_out(Tensor self, Tensor boundaries, *, bool out_int32=False, bool right=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bucketize_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & boundaries, bool out_int32=false, bool right=false) { + return at::_ops::bucketize_Tensor_out::call(self, boundaries, out_int32, right, out); +} +// aten::bucketize.Tensor_out(Tensor self, Tensor boundaries, *, bool out_int32=False, bool right=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bucketize_outf(const at::Tensor & self, const at::Tensor & boundaries, bool out_int32, bool right, at::Tensor & out) { + return at::_ops::bucketize_Tensor_out::call(self, boundaries, out_int32, right, out); +} + +// aten::bucketize.Scalar(Scalar self, Tensor boundaries, *, bool out_int32=False, bool right=False) -> Tensor +inline at::Tensor bucketize(const at::Scalar & self, const at::Tensor & boundaries, bool out_int32=false, bool right=false) { + return at::_ops::bucketize_Scalar::call(self, boundaries, out_int32, right); +} + +// aten::bucketize.Scalar_out(Scalar self, Tensor boundaries, *, bool out_int32=False, bool right=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bucketize_out(at::Tensor & out, const at::Scalar & self, const at::Tensor & boundaries, bool out_int32=false, bool right=false) { + return at::_ops::bucketize_Scalar_out::call(self, boundaries, out_int32, right, out); +} +// aten::bucketize.Scalar_out(Scalar self, Tensor boundaries, *, bool out_int32=False, bool right=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bucketize_outf(const at::Scalar & self, const at::Tensor & boundaries, bool out_int32, bool right, at::Tensor & out) { + return at::_ops::bucketize_Scalar_out::call(self, boundaries, out_int32, right, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/can_cast.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/can_cast.h new file mode 100644 index 0000000000000000000000000000000000000000..52cb6eafcdb06a633b037cc8d741660a84f13283 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/can_cast.h @@ -0,0 +1,30 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::can_cast(ScalarType from, ScalarType to) -> bool +inline bool can_cast(at::ScalarType from, at::ScalarType to) { + return at::_ops::can_cast::call(from, to); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ccol_indices_copy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ccol_indices_copy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7146b858558df2970d88fcf68de6b6a091e74d64 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ccol_indices_copy_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API ccol_indices_copy { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::ccol_indices_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "ccol_indices_copy(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API ccol_indices_copy_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::ccol_indices_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "ccol_indices_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/choose_qparams_optimized_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/choose_qparams_optimized_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..04e68385f32a2bdb237de7be7b302c762dc225f8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/choose_qparams_optimized_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API choose_qparams_optimized { + using schema = ::std::tuple (const at::Tensor &, int64_t, int64_t, double, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::choose_qparams_optimized") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "choose_qparams_optimized(Tensor input, int numel, int n_bins, float ratio, int bit_width) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & input, int64_t numel, int64_t n_bins, double ratio, int64_t bit_width); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, int64_t numel, int64_t n_bins, double ratio, int64_t bit_width); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chunk_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chunk_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..aac9df715b55ef802e9a9bfed2a30d89ca82ad78 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chunk_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API chunk { + using schema = ::std::vector (const at::Tensor &, int64_t, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::chunk") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "chunk(Tensor(a -> *) self, int chunks, int dim=0) -> Tensor(a)[]") + static ::std::vector call(const at::Tensor & self, int64_t chunks, int64_t dim); + static ::std::vector redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t chunks, int64_t dim); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/count_nonzero_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/count_nonzero_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..32c2a9b1106d73f0ea7c20be136feaf400543bef --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/count_nonzero_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor count_nonzero(const at::Tensor & self, at::IntArrayRef dim); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_affine_grid_generator_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_affine_grid_generator_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7eaba3a252926b6881befd86fd7fa48d6cfad99f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_affine_grid_generator_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API cudnn_affine_grid_generator { + using schema = at::Tensor (const at::Tensor &, int64_t, int64_t, int64_t, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cudnn_affine_grid_generator") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cudnn_affine_grid_generator(Tensor theta, int N, int C, int H, int W) -> Tensor grid") + static at::Tensor call(const at::Tensor & theta, int64_t N, int64_t C, int64_t H, int64_t W); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & theta, int64_t N, int64_t C, int64_t H, int64_t W); +}; + +struct TORCH_API cudnn_affine_grid_generator_out { + using schema = at::Tensor & (const at::Tensor &, int64_t, int64_t, int64_t, int64_t, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cudnn_affine_grid_generator") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cudnn_affine_grid_generator.out(Tensor theta, int N, int C, int H, int W, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & theta, int64_t N, int64_t C, int64_t H, int64_t W, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & theta, int64_t N, int64_t C, int64_t H, int64_t W, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_scatter_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_scatter_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..70d43b3cb05987c6f9241a9bf73e371eada71ddb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_scatter_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor diagonal_scatter(const at::Tensor & self, const at::Tensor & src, int64_t offset=0, int64_t dim1=0, int64_t dim2=1); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_permuted_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_permuted_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9e4b093877f940c30aa166b79157322b666304e7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_permuted_compositeexplicitautograd_dispatch.h @@ -0,0 +1,30 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor empty_permuted(at::IntArrayRef size, at::IntArrayRef physical_layout, at::TensorOptions options={}); +TORCH_API at::Tensor empty_permuted(at::IntArrayRef size, at::IntArrayRef physical_layout, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +TORCH_API at::Tensor empty_permuted_symint(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, at::TensorOptions options={}); +TORCH_API at::Tensor empty_permuted_symint(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +TORCH_API at::Tensor & empty_permuted_out(at::Tensor & out, at::IntArrayRef size, at::IntArrayRef physical_layout); +TORCH_API at::Tensor & empty_permuted_outf(at::IntArrayRef size, at::IntArrayRef physical_layout, at::Tensor & out); +TORCH_API at::Tensor & empty_permuted_symint_out(at::Tensor & out, c10::SymIntArrayRef size, at::IntArrayRef physical_layout); +TORCH_API at::Tensor & empty_permuted_symint_outf(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/eye_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/eye_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d720fde72796a593add5ddcfeda51ce8dcb532f8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/eye_cpu_dispatch.h @@ -0,0 +1,30 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor & eye_out(at::Tensor & out, int64_t n); +TORCH_API at::Tensor & eye_outf(int64_t n, at::Tensor & out); +TORCH_API at::Tensor & eye_symint_out(at::Tensor & out, c10::SymInt n); +TORCH_API at::Tensor & eye_symint_outf(c10::SymInt n, at::Tensor & out); +TORCH_API at::Tensor & eye_out(at::Tensor & out, int64_t n, int64_t m); +TORCH_API at::Tensor & eye_outf(int64_t n, int64_t m, at::Tensor & out); +TORCH_API at::Tensor & eye_symint_out(at::Tensor & out, c10::SymInt n, c10::SymInt m); +TORCH_API at::Tensor & eye_symint_outf(c10::SymInt n, c10::SymInt m, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/feature_alpha_dropout.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/feature_alpha_dropout.h new file mode 100644 index 0000000000000000000000000000000000000000..41f9a50d7362daca19016a4f72e273d768228415 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/feature_alpha_dropout.h @@ -0,0 +1,35 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::feature_alpha_dropout(Tensor input, float p, bool train) -> Tensor +inline at::Tensor feature_alpha_dropout(const at::Tensor & input, double p, bool train) { + return at::_ops::feature_alpha_dropout::call(input, p, train); +} + +// aten::feature_alpha_dropout_(Tensor(a!) self, float p, bool train) -> Tensor(a!) +inline at::Tensor & feature_alpha_dropout_(at::Tensor & self, double p, bool train) { + return at::_ops::feature_alpha_dropout_::call(self, p, train); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_rfft_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_rfft_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..0dc1bed7b745622fc776e90da241989ef42286dc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_rfft_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API fft_rfft { + using schema = at::Tensor (const at::Tensor &, c10::optional, int64_t, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::fft_rfft") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fft_rfft(Tensor self, SymInt? n=None, int dim=-1, str? norm=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm); +}; + +struct TORCH_API fft_rfft_out { + using schema = at::Tensor & (const at::Tensor &, c10::optional, int64_t, c10::optional, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::fft_rfft") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fft_rfft.out(Tensor self, SymInt? n=None, int dim=-1, str? norm=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fmax_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fmax_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..97054aebdf2a440f0f51abf4f003663fc6d05c32 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fmax_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor fmax(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & fmax_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & fmax_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/geometric_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/geometric_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..4573c6deb4a569cc5af077dd975e5c9093d81fea --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/geometric_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API geometric_ { + using schema = at::Tensor & (at::Tensor &, double, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::geometric_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "geometric_(Tensor(a!) self, float p, *, Generator? generator=None) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, double p, c10::optional generator); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, double p, c10::optional generator); +}; + +struct TORCH_API geometric_out { + using schema = at::Tensor & (const at::Tensor &, double, c10::optional, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::geometric") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "geometric.out(Tensor self, float p, *, Generator? generator=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, double p, c10::optional generator, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, double p, c10::optional generator, at::Tensor & out); +}; + +struct TORCH_API geometric { + using schema = at::Tensor (const at::Tensor &, double, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::geometric") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "geometric(Tensor self, float p, *, Generator? generator=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, double p, c10::optional generator); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, double p, c10::optional generator); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogramdd_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogramdd_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..1cf76c428422555d355569f747f9d60e8dcc6b2e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogramdd_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API histogramdd { + using schema = ::std::tuple> (const at::Tensor &, at::IntArrayRef, c10::optional>, const c10::optional &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::histogramdd") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "histogramdd(Tensor self, int[] bins, float[]? range=None, Tensor? weight=None, bool density=False) -> (Tensor hist, Tensor[] bin_edges)") + static ::std::tuple> call(const at::Tensor & self, at::IntArrayRef bins, c10::optional> range, const c10::optional & weight, bool density); + static ::std::tuple> redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef bins, c10::optional> range, const c10::optional & weight, bool density); +}; + +struct TORCH_API histogramdd_int_bins { + using schema = ::std::tuple> (const at::Tensor &, int64_t, c10::optional>, const c10::optional &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::histogramdd") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "int_bins") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "histogramdd.int_bins(Tensor self, int bins, float[]? range=None, Tensor? weight=None, bool density=False) -> (Tensor hist, Tensor[] bin_edges)") + static ::std::tuple> call(const at::Tensor & self, int64_t bins, c10::optional> range, const c10::optional & weight, bool density); + static ::std::tuple> redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t bins, c10::optional> range, const c10::optional & weight, bool density); +}; + +struct TORCH_API histogramdd_TensorList_bins { + using schema = ::std::tuple> (const at::Tensor &, at::TensorList, c10::optional>, const c10::optional &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::histogramdd") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "TensorList_bins") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "histogramdd.TensorList_bins(Tensor self, Tensor[] bins, float[]? range=None, Tensor? weight=None, bool density=False) -> (Tensor hist, Tensor[] bin_edges)") + static ::std::tuple> call(const at::Tensor & self, at::TensorList bins, c10::optional> range, const c10::optional & weight, bool density); + static ::std::tuple> redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::TensorList bins, c10::optional> range, const c10::optional & weight, bool density); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_select_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_select_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cc81d1b303dc5d807548ea9dc781504388ed5960 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_select_backward_compositeimplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor index_select_backward(const at::Tensor & grad, at::IntArrayRef self_sizes, int64_t dim, const at::Tensor & index); +TORCH_API at::Tensor index_select_backward_symint(const at::Tensor & grad, c10::SymIntArrayRef self_sizes, int64_t dim, const at::Tensor & index); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_same_size_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_same_size_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1c7b8206515af1375770ce99df6ac17821cc3dd7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_same_size_compositeexplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API bool is_same_size(const at::Tensor & self, const at::Tensor & other); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/le_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/le_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..447d73bd4d2726489ba9dc5ad9cdb053330c09cb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/le_cuda_dispatch.h @@ -0,0 +1,30 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor le(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & le_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & le_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +TORCH_API at::Tensor & le_(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor le(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & le_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & le_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & le_(at::Tensor & self, const at::Tensor & other); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigvals_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigvals_native.h new file mode 100644 index 0000000000000000000000000000000000000000..7a435da3a8c86e02487c8a21407fe6688c63a7b2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigvals_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor linalg_eigvals(const at::Tensor & self); +TORCH_API at::Tensor & linalg_eigvals_out(const at::Tensor & self, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vander_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vander_native.h new file mode 100644 index 0000000000000000000000000000000000000000..bdaab51aa96d4300f4594bf3051569af5dfa6fe8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vander_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor linalg_vander_symint(const at::Tensor & x, c10::optional N=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..43a6a352670a6051fcdfbce164832a248812aa26 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API logit { + using schema = at::Tensor (const at::Tensor &, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::logit") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logit(Tensor self, float? eps=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::optional eps); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional eps); +}; + +struct TORCH_API logit_ { + using schema = at::Tensor & (at::Tensor &, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::logit_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logit_(Tensor(a!) self, float? eps=None) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, c10::optional eps); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, c10::optional eps); +}; + +struct TORCH_API logit_out { + using schema = at::Tensor & (const at::Tensor &, c10::optional, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::logit") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logit.out(Tensor self, float? eps=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::optional eps, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional eps, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_cell_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_cell_native.h new file mode 100644 index 0000000000000000000000000000000000000000..93592887ceed08d3bc724101999b2e5f434711b3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_cell_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple lstm_cell(const at::Tensor & input, at::TensorList hx, const at::Tensor & w_ih, const at::Tensor & w_hh, const c10::optional & b_ih={}, const c10::optional & b_hh={}); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices.h new file mode 100644 index 0000000000000000000000000000000000000000..2e3752de748c52001acdb74b2d060807fc6059c0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::max_pool3d_with_indices.out(Tensor self, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False, *, Tensor(a!) out, Tensor(b!) indices) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple max_pool3d_with_indices_out(at::Tensor & out, at::Tensor & indices, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false) { + return at::_ops::max_pool3d_with_indices_out::call(self, kernel_size, stride, padding, dilation, ceil_mode, out, indices); +} +// aten::max_pool3d_with_indices.out(Tensor self, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False, *, Tensor(a!) out, Tensor(b!) indices) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple max_pool3d_with_indices_outf(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out, at::Tensor & indices) { + return at::_ops::max_pool3d_with_indices_out::call(self, kernel_size, stride, padding, dilation, ceil_mode, out, indices); +} + +// aten::max_pool3d_with_indices(Tensor self, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False) -> (Tensor, Tensor) +inline ::std::tuple max_pool3d_with_indices(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false) { + return at::_ops::max_pool3d_with_indices::call(self, kernel_size, stride, padding, dilation, ceil_mode); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ba431dc501e925bbecfbf918f8bf3b86504516e7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool2d_cpu_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor max_unpool2d(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size); +TORCH_API at::Tensor max_unpool2d_symint(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size); +TORCH_API at::Tensor & max_unpool2d_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size); +TORCH_API at::Tensor & max_unpool2d_outf(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::Tensor & out); +TORCH_API at::Tensor & max_unpool2d_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size); +TORCH_API at::Tensor & max_unpool2d_symint_outf(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/min.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/min.h new file mode 100644 index 0000000000000000000000000000000000000000..7701603072c2d717a6df02a0e43fadc3fbcee96f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/min.h @@ -0,0 +1,81 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::min.dim(Tensor self, int dim, bool keepdim=False) -> (Tensor values, Tensor indices) +inline ::std::tuple min(const at::Tensor & self, int64_t dim, bool keepdim=false) { + return at::_ops::min_dim::call(self, dim, keepdim); +} + +// aten::min.dim_min(Tensor self, int dim, bool keepdim=False, *, Tensor(a!) min, Tensor(b!) min_indices) -> (Tensor(a!) values, Tensor(b!) indices) +inline ::std::tuple min_out(at::Tensor & min, at::Tensor & min_indices, const at::Tensor & self, int64_t dim, bool keepdim=false) { + return at::_ops::min_dim_min::call(self, dim, keepdim, min, min_indices); +} +// aten::min.dim_min(Tensor self, int dim, bool keepdim=False, *, Tensor(a!) min, Tensor(b!) min_indices) -> (Tensor(a!) values, Tensor(b!) indices) +inline ::std::tuple min_outf(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & min, at::Tensor & min_indices) { + return at::_ops::min_dim_min::call(self, dim, keepdim, min, min_indices); +} + +// aten::min.names_dim(Tensor self, Dimname dim, bool keepdim=False) -> (Tensor values, Tensor indices) +inline ::std::tuple min(const at::Tensor & self, at::Dimname dim, bool keepdim=false) { + return at::_ops::min_names_dim::call(self, dim, keepdim); +} + +// aten::min.names_dim_min(Tensor self, Dimname dim, bool keepdim=False, *, Tensor(a!) min, Tensor(b!) min_indices) -> (Tensor(a!) values, Tensor(b!) indices) +inline ::std::tuple min_out(at::Tensor & min, at::Tensor & min_indices, const at::Tensor & self, at::Dimname dim, bool keepdim=false) { + return at::_ops::min_names_dim_min::call(self, dim, keepdim, min, min_indices); +} +// aten::min.names_dim_min(Tensor self, Dimname dim, bool keepdim=False, *, Tensor(a!) min, Tensor(b!) min_indices) -> (Tensor(a!) values, Tensor(b!) indices) +inline ::std::tuple min_outf(const at::Tensor & self, at::Dimname dim, bool keepdim, at::Tensor & min, at::Tensor & min_indices) { + return at::_ops::min_names_dim_min::call(self, dim, keepdim, min, min_indices); +} + +// aten::min(Tensor self) -> Tensor +inline at::Tensor min(const at::Tensor & self) { + return at::_ops::min::call(self); +} + +// aten::min.unary_out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & min_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::min_unary_out::call(self, out); +} +// aten::min.unary_out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & min_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::min_unary_out::call(self, out); +} + +// aten::min.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & min_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::min_out::call(self, other, out); +} +// aten::min.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & min_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::min_out::call(self, other, out); +} + +// aten::min.other(Tensor self, Tensor other) -> Tensor +inline at::Tensor min(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::min_other::call(self, other); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_convolution_transpose_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_convolution_transpose_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7dfb0a0798f7684a6a6906bd14904fbeab332eea --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_convolution_transpose_compositeexplicitautograd_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & miopen_convolution_transpose_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, bool benchmark, bool deterministic); +TORCH_API at::Tensor & miopen_convolution_transpose_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef output_padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, bool benchmark, bool deterministic, at::Tensor & out); +TORCH_API at::Tensor & miopen_convolution_transpose_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, bool benchmark, bool deterministic); +TORCH_API at::Tensor & miopen_convolution_transpose_symint_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, bool benchmark, bool deterministic, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_reorder_conv2d_weight_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_reorder_conv2d_weight_native.h new file mode 100644 index 0000000000000000000000000000000000000000..f8e8a9e6046f8107845edb9c6ce59a8e98dc2977 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_reorder_conv2d_weight_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor & mkldnn_reorder_conv2d_weight_out_symint(const at::Tensor & self, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, at::OptionalSymIntArrayRef input_size, at::Tensor & out); +TORCH_API at::Tensor mkldnn_reorder_conv2d_weight(const at::Tensor & self, at::IntArrayRef padding=0, at::IntArrayRef stride=1, at::IntArrayRef dilation=1, int64_t groups=1, at::OptionalIntArrayRef input_size=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multiply.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multiply.h new file mode 100644 index 0000000000000000000000000000000000000000..fa2d655c88b7b03545cc2e712ac90be7deb85062 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multiply.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::multiply.Tensor(Tensor self, Tensor other) -> Tensor +inline at::Tensor multiply(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::multiply_Tensor::call(self, other); +} + +// aten::multiply.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & multiply_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::multiply_out::call(self, other, out); +} +// aten::multiply.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & multiply_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::multiply_out::call(self, other, out); +} + +// aten::multiply.Scalar(Tensor self, Scalar other) -> Tensor +inline at::Tensor multiply(const at::Tensor & self, const at::Scalar & other) { + return at::_ops::multiply_Scalar::call(self, other); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmedian_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmedian_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a1edac707916b876774d9fae36cb1a5c0258052c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmedian_native.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor & nanmedian_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor nanmedian_cpu(const at::Tensor & self); +TORCH_API at::Tensor nanmedian_cuda(const at::Tensor & self); +TORCH_API ::std::tuple nanmedian(const at::Tensor & self, int64_t dim, bool keepdim=false); +TORCH_API ::std::tuple nanmedian_out_cpu(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & values, at::Tensor & indices); +TORCH_API ::std::tuple nanmedian_out_cuda(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & values, at::Tensor & indices); +TORCH_API ::std::tuple nanmedian(const at::Tensor & self, at::Dimname dim, bool keepdim=false); +TORCH_API ::std::tuple nanmedian_out(const at::Tensor & self, at::Dimname dim, bool keepdim, at::Tensor & values, at::Tensor & indices); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nonzero_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nonzero_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..80a2822eae34421ac1a5ccaedfa5157ae3e57017 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nonzero_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API nonzero_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::nonzero") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "nonzero.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +struct TORCH_API nonzero { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::nonzero") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "nonzero(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/searchsorted_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/searchsorted_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5ce32be62f48c602c5da79a9f16275b85b2d5d41 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/searchsorted_cpu_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor searchsorted(const at::Tensor & sorted_sequence, const at::Tensor & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}); +TORCH_API at::Tensor & searchsorted_out(at::Tensor & out, const at::Tensor & sorted_sequence, const at::Tensor & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}); +TORCH_API at::Tensor & searchsorted_outf(const at::Tensor & sorted_sequence, const at::Tensor & self, bool out_int32, bool right, c10::optional side, const c10::optional & sorter, at::Tensor & out); +TORCH_API at::Tensor searchsorted(const at::Tensor & sorted_sequence, const at::Scalar & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}); +TORCH_API at::Tensor & searchsorted_out(at::Tensor & out, const at::Tensor & sorted_sequence, const at::Scalar & self, bool out_int32=false, bool right=false, c10::optional side=c10::nullopt, const c10::optional & sorter={}); +TORCH_API at::Tensor & searchsorted_outf(const at::Tensor & sorted_sequence, const at::Scalar & self, bool out_int32, bool right, c10::optional side, const c10::optional & sorter, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..80ccc2fa5c388d12d9bd0454c617dfe981e69eb4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API slice_backward { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, int64_t, c10::SymInt, c10::SymInt, c10::SymInt); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::slice_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "slice_backward(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step); +}; + +struct TORCH_API slice_backward_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, int64_t, c10::SymInt, c10::SymInt, c10::SymInt, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::slice_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "slice_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a628dd8859cb3e9985839a13ab557b0dcb007256 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor special_entr(const at::Tensor & self); +TORCH_API at::Tensor & special_entr_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_entr_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_laguerre_polynomial_l_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_laguerre_polynomial_l_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..7717ae152309a35778bdd17af7ffb90ce95e9227 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_laguerre_polynomial_l_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_special_laguerre_polynomial_l : public TensorIteratorBase { + + + void meta(const at::Tensor & x, const at::Tensor & n); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u.h new file mode 100644 index 0000000000000000000000000000000000000000..5c6be54e51fbb64991640bba609f3b8333425093 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_shifted_chebyshev_polynomial_u.h @@ -0,0 +1,67 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::special_shifted_chebyshev_polynomial_u(Tensor x, Tensor n) -> Tensor +inline at::Tensor special_shifted_chebyshev_polynomial_u(const at::Tensor & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_u::call(x, n); +} + +// aten::special_shifted_chebyshev_polynomial_u.x_scalar(Scalar x, Tensor n) -> Tensor +inline at::Tensor special_shifted_chebyshev_polynomial_u(const at::Scalar & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_u_x_scalar::call(x, n); +} + +// aten::special_shifted_chebyshev_polynomial_u.n_scalar(Tensor x, Scalar n) -> Tensor +inline at::Tensor special_shifted_chebyshev_polynomial_u(const at::Tensor & x, const at::Scalar & n) { + return at::_ops::special_shifted_chebyshev_polynomial_u_n_scalar::call(x, n); +} + +// aten::special_shifted_chebyshev_polynomial_u.out(Tensor x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_u_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_u_out::call(x, n, out); +} +// aten::special_shifted_chebyshev_polynomial_u.out(Tensor x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_u_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out) { + return at::_ops::special_shifted_chebyshev_polynomial_u_out::call(x, n, out); +} + +// aten::special_shifted_chebyshev_polynomial_u.x_scalar_out(Scalar x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_u_out(at::Tensor & out, const at::Scalar & x, const at::Tensor & n) { + return at::_ops::special_shifted_chebyshev_polynomial_u_x_scalar_out::call(x, n, out); +} +// aten::special_shifted_chebyshev_polynomial_u.x_scalar_out(Scalar x, Tensor n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_u_outf(const at::Scalar & x, const at::Tensor & n, at::Tensor & out) { + return at::_ops::special_shifted_chebyshev_polynomial_u_x_scalar_out::call(x, n, out); +} + +// aten::special_shifted_chebyshev_polynomial_u.n_scalar_out(Tensor x, Scalar n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_u_out(at::Tensor & out, const at::Tensor & x, const at::Scalar & n) { + return at::_ops::special_shifted_chebyshev_polynomial_u_n_scalar_out::call(x, n, out); +} +// aten::special_shifted_chebyshev_polynomial_u.n_scalar_out(Tensor x, Scalar n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_shifted_chebyshev_polynomial_u_outf(const at::Tensor & x, const at::Scalar & n, at::Tensor & out) { + return at::_ops::special_shifted_chebyshev_polynomial_u_n_scalar_out::call(x, n, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sspaddmm.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sspaddmm.h new file mode 100644 index 0000000000000000000000000000000000000000..02573affffb8a5782817c0dbc43621e20f21ba46 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sspaddmm.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::sspaddmm(Tensor self, Tensor mat1, Tensor mat2, *, Scalar beta=1, Scalar alpha=1) -> Tensor +inline at::Tensor sspaddmm(const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta=1, const at::Scalar & alpha=1) { + return at::_ops::sspaddmm::call(self, mat1, mat2, beta, alpha); +} + +// aten::sspaddmm.out(Tensor self, Tensor mat1, Tensor mat2, *, Scalar beta=1, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & sspaddmm_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta=1, const at::Scalar & alpha=1) { + return at::_ops::sspaddmm_out::call(self, mat1, mat2, beta, alpha, out); +} +// aten::sspaddmm.out(Tensor self, Tensor mat1, Tensor mat2, *, Scalar beta=1, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & sspaddmm_outf(const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta, const at::Scalar & alpha, at::Tensor & out) { + return at::_ops::sspaddmm_out::call(self, mat1, mat2, beta, alpha, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/svd.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/svd.h new file mode 100644 index 0000000000000000000000000000000000000000..ae1689e723d4f200c78528aa33ab732434ed7bef --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/svd.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::svd.U(Tensor self, bool some=True, bool compute_uv=True, *, Tensor(a!) U, Tensor(b!) S, Tensor(c!) V) -> (Tensor(a!) U, Tensor(b!) S, Tensor(c!) V) +inline ::std::tuple svd_out(at::Tensor & U, at::Tensor & S, at::Tensor & V, const at::Tensor & self, bool some=true, bool compute_uv=true) { + return at::_ops::svd_U::call(self, some, compute_uv, U, S, V); +} +// aten::svd.U(Tensor self, bool some=True, bool compute_uv=True, *, Tensor(a!) U, Tensor(b!) S, Tensor(c!) V) -> (Tensor(a!) U, Tensor(b!) S, Tensor(c!) V) +inline ::std::tuple svd_outf(const at::Tensor & self, bool some, bool compute_uv, at::Tensor & U, at::Tensor & S, at::Tensor & V) { + return at::_ops::svd_U::call(self, some, compute_uv, U, S, V); +} + +// aten::svd(Tensor self, bool some=True, bool compute_uv=True) -> (Tensor U, Tensor S, Tensor V) +inline ::std::tuple svd(const at::Tensor & self, bool some=true, bool compute_uv=true) { + return at::_ops::svd::call(self, some, compute_uv); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sym_stride.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sym_stride.h new file mode 100644 index 0000000000000000000000000000000000000000..280a226e7148ead10ec983ae90f523ed0d1276bb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sym_stride.h @@ -0,0 +1,30 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::sym_stride.int(Tensor self, int dim) -> SymInt +inline c10::SymInt __dispatch_sym_stride(const at::Tensor & self, int64_t dim) { + return at::_ops::sym_stride_int::call(self, dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b3e1f7f8d37888d037869f3bcf8ee62ae9310ff4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_meta_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor threshold(const at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value); +TORCH_API at::Tensor & threshold_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value); +TORCH_API at::Tensor & threshold_outf(const at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value, at::Tensor & out); +TORCH_API at::Tensor & threshold_(at::Tensor & self, const at::Scalar & threshold, const at::Scalar & value); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_sparse_csr_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_sparse_csr_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..e548b98f1c83bb08ca818ea3d8dc3b0fc08cbb91 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_sparse_csr_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API to_sparse_csr { + using schema = at::Tensor (const at::Tensor &, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::to_sparse_csr") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "to_sparse_csr(Tensor self, int? dense_dim=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::optional dense_dim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::optional dense_dim); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/transpose_copy.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/transpose_copy.h new file mode 100644 index 0000000000000000000000000000000000000000..ad72485e710329f64dcfd61a548e7daf47c5edc5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/transpose_copy.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::transpose_copy.int(Tensor self, int dim0, int dim1) -> Tensor +inline at::Tensor transpose_copy(const at::Tensor & self, int64_t dim0, int64_t dim1) { + return at::_ops::transpose_copy_int::call(self, dim0, dim1); +} + +// aten::transpose_copy.int_out(Tensor self, int dim0, int dim1, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & transpose_copy_out(at::Tensor & out, const at::Tensor & self, int64_t dim0, int64_t dim1) { + return at::_ops::transpose_copy_int_out::call(self, dim0, dim1, out); +} +// aten::transpose_copy.int_out(Tensor self, int dim0, int dim1, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & transpose_copy_outf(const at::Tensor & self, int64_t dim0, int64_t dim1, at::Tensor & out) { + return at::_ops::transpose_copy_int_out::call(self, dim0, dim1, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/uniform_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/uniform_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4919a090b4b0dd33001c856e3b9104c187e1a8cb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/uniform_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor & uniform_(at::Tensor & self, double from=0, double to=1, c10::optional generator=c10::nullopt); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsafe_split_with_sizes.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsafe_split_with_sizes.h new file mode 100644 index 0000000000000000000000000000000000000000..764e1ad821c4fe73efcc44f87e87b5d3d5e87c03 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsafe_split_with_sizes.h @@ -0,0 +1,91 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::unsafe_split_with_sizes(Tensor self, SymInt[] split_sizes, int dim=0) -> Tensor[] +inline ::std::vector unsafe_split_with_sizes(const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes::call(self, c10::fromIntArrayRefSlow(split_sizes), dim); +} +namespace symint { + template ::value>> + ::std::vector unsafe_split_with_sizes(const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes::call(self, c10::fromIntArrayRefSlow(split_sizes), dim); + } +} + +// aten::unsafe_split_with_sizes(Tensor self, SymInt[] split_sizes, int dim=0) -> Tensor[] +inline ::std::vector unsafe_split_with_sizes_symint(const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes::call(self, split_sizes, dim); +} +namespace symint { + template ::value>> + ::std::vector unsafe_split_with_sizes(const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes::call(self, split_sizes, dim); + } +} + +// aten::unsafe_split_with_sizes.out(Tensor self, SymInt[] split_sizes, int dim=0, *, Tensor(a!)[] out) -> () +inline void unsafe_split_with_sizes_out(at::TensorList out, const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes_out::call(self, c10::fromIntArrayRefSlow(split_sizes), dim, out); +} +namespace symint { + template ::value>> + void unsafe_split_with_sizes_out(at::TensorList out, const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes_out::call(self, c10::fromIntArrayRefSlow(split_sizes), dim, out); + } +} + +// aten::unsafe_split_with_sizes.out(Tensor self, SymInt[] split_sizes, int dim=0, *, Tensor(a!)[] out) -> () +inline void unsafe_split_with_sizes_outf(const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim, at::TensorList out) { + return at::_ops::unsafe_split_with_sizes_out::call(self, c10::fromIntArrayRefSlow(split_sizes), dim, out); +} +namespace symint { + template ::value>> + void unsafe_split_with_sizes_outf(const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim, at::TensorList out) { + return at::_ops::unsafe_split_with_sizes_out::call(self, c10::fromIntArrayRefSlow(split_sizes), dim, out); + } +} + +// aten::unsafe_split_with_sizes.out(Tensor self, SymInt[] split_sizes, int dim=0, *, Tensor(a!)[] out) -> () +inline void unsafe_split_with_sizes_symint_out(at::TensorList out, const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes_out::call(self, split_sizes, dim, out); +} +namespace symint { + template ::value>> + void unsafe_split_with_sizes_out(at::TensorList out, const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim=0) { + return at::_ops::unsafe_split_with_sizes_out::call(self, split_sizes, dim, out); + } +} + +// aten::unsafe_split_with_sizes.out(Tensor self, SymInt[] split_sizes, int dim=0, *, Tensor(a!)[] out) -> () +inline void unsafe_split_with_sizes_symint_outf(const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim, at::TensorList out) { + return at::_ops::unsafe_split_with_sizes_out::call(self, split_sizes, dim, out); +} +namespace symint { + template ::value>> + void unsafe_split_with_sizes_outf(const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim, at::TensorList out) { + return at::_ops::unsafe_split_with_sizes_out::call(self, split_sizes, dim, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsqueeze_copy_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsqueeze_copy_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1792b2da9fcb5c12b812b19eba1a0ec119781413 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsqueeze_copy_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & unsqueeze_copy_out(at::Tensor & out, const at::Tensor & self, int64_t dim); +TORCH_API at::Tensor & unsqueeze_copy_outf(const at::Tensor & self, int64_t dim, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d.h new file mode 100644 index 0000000000000000000000000000000000000000..da7d4a4460f077b90284a9b247d1a0b1e5079b05 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d.h @@ -0,0 +1,113 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::upsample_trilinear3d.vec(Tensor input, SymInt[]? output_size, bool align_corners, float[]? scale_factors) -> Tensor +inline at::Tensor upsample_trilinear3d(const at::Tensor & input, at::OptionalIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::upsample_trilinear3d_vec::call(input, output_size.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*output_size)) : c10::nullopt, align_corners, scale_factors); +} +namespace symint { + template ::value>> + at::Tensor upsample_trilinear3d(const at::Tensor & input, at::OptionalIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::upsample_trilinear3d_vec::call(input, output_size.has_value() ? c10::make_optional(c10::fromIntArrayRefSlow(*output_size)) : c10::nullopt, align_corners, scale_factors); + } +} + +// aten::upsample_trilinear3d.vec(Tensor input, SymInt[]? output_size, bool align_corners, float[]? scale_factors) -> Tensor +inline at::Tensor upsample_trilinear3d_symint(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::upsample_trilinear3d_vec::call(input, output_size, align_corners, scale_factors); +} +namespace symint { + template ::value>> + at::Tensor upsample_trilinear3d(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors) { + return at::_ops::upsample_trilinear3d_vec::call(input, output_size, align_corners, scale_factors); + } +} + +// aten::upsample_trilinear3d.out(Tensor self, SymInt[3] output_size, bool align_corners, float? scales_d=None, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & upsample_trilinear3d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_d, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & upsample_trilinear3d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_d, scales_h, scales_w, out); + } +} + +// aten::upsample_trilinear3d.out(Tensor self, SymInt[3] output_size, bool align_corners, float? scales_d=None, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & upsample_trilinear3d_outf(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::upsample_trilinear3d_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_d, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & upsample_trilinear3d_outf(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::upsample_trilinear3d_out::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_d, scales_h, scales_w, out); + } +} + +// aten::upsample_trilinear3d.out(Tensor self, SymInt[3] output_size, bool align_corners, float? scales_d=None, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & upsample_trilinear3d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d_out::call(self, output_size, align_corners, scales_d, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & upsample_trilinear3d_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d_out::call(self, output_size, align_corners, scales_d, scales_h, scales_w, out); + } +} + +// aten::upsample_trilinear3d.out(Tensor self, SymInt[3] output_size, bool align_corners, float? scales_d=None, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & upsample_trilinear3d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::upsample_trilinear3d_out::call(self, output_size, align_corners, scales_d, scales_h, scales_w, out); +} +namespace symint { + template ::value>> + at::Tensor & upsample_trilinear3d_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out) { + return at::_ops::upsample_trilinear3d_out::call(self, output_size, align_corners, scales_d, scales_h, scales_w, out); + } +} + +// aten::upsample_trilinear3d(Tensor self, SymInt[3] output_size, bool align_corners, float? scales_d=None, float? scales_h=None, float? scales_w=None) -> Tensor +inline at::Tensor upsample_trilinear3d(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_d, scales_h, scales_w); +} +namespace symint { + template ::value>> + at::Tensor upsample_trilinear3d(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d::call(self, c10::fromIntArrayRefSlow(output_size), align_corners, scales_d, scales_h, scales_w); + } +} + +// aten::upsample_trilinear3d(Tensor self, SymInt[3] output_size, bool align_corners, float? scales_d=None, float? scales_h=None, float? scales_w=None) -> Tensor +inline at::Tensor upsample_trilinear3d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d::call(self, output_size, align_corners, scales_d, scales_h, scales_w); +} +namespace symint { + template ::value>> + at::Tensor upsample_trilinear3d(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt) { + return at::_ops::upsample_trilinear3d::call(self, output_size, align_corners, scales_d, scales_h, scales_w); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xor_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xor_native.h new file mode 100644 index 0000000000000000000000000000000000000000..5ae99c1e998cd07324c163d5b42686d33c57d66d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xor_native.h @@ -0,0 +1,24 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor __xor__(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & __ixor__(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor __xor__(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & __ixor__(at::Tensor & self, const at::Tensor & other); +} // namespace native +} // namespace at