diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_amp_update_scale_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_amp_update_scale_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..67874b0520f37d95ac6ab34923a24c98332add32 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_amp_update_scale_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 _amp_update_scale_ { + using schema = at::Tensor & (at::Tensor &, at::Tensor &, const at::Tensor &, double, 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::_amp_update_scale_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_amp_update_scale_(Tensor(a!) self, Tensor(b!) growth_tracker, Tensor found_inf, float scale_growth_factor, float scale_backoff_factor, int growth_interval) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, at::Tensor & growth_tracker, const at::Tensor & found_inf, double scale_growth_factor, double scale_backoff_factor, int64_t growth_interval); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, at::Tensor & growth_tracker, const at::Tensor & found_inf, double scale_growth_factor, double scale_backoff_factor, int64_t growth_interval); +}; + +struct TORCH_API _amp_update_scale_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &, const at::Tensor &, double, double, 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::_amp_update_scale") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_amp_update_scale.out(Tensor self, Tensor(b!) growth_tracker, Tensor found_inf, float scale_growth_factor, float scale_backoff_factor, int growth_interval, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & growth_tracker, const at::Tensor & found_inf, double scale_growth_factor, double scale_backoff_factor, int64_t growth_interval, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & growth_tracker, const at::Tensor & found_inf, double scale_growth_factor, double scale_backoff_factor, int64_t growth_interval, at::Tensor & out); +}; + +struct TORCH_API _amp_update_scale { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, double, 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::_amp_update_scale") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_amp_update_scale(Tensor self, Tensor growth_tracker, Tensor found_inf, float scale_growth_factor, float scale_backoff_factor, int growth_interval) -> (Tensor, Tensor growth_tracker_out)") + static ::std::tuple call(const at::Tensor & self, const at::Tensor & growth_tracker, const at::Tensor & found_inf, double scale_growth_factor, double scale_backoff_factor, int64_t growth_interval); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & growth_tracker, const at::Tensor & found_inf, double scale_growth_factor, double scale_backoff_factor, int64_t growth_interval); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..bbc3e8ed49cb551d3016779d6cc1cf5bf97f75f2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_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 void _assert_scalar(const at::Scalar & self, c10::string_view assert_msg); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_physical_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_physical_native.h new file mode 100644 index 0000000000000000000000000000000000000000..8459dda1f7ee72db8f2d37750f8dadee591b918a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_physical_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 _conj_physical(const at::Tensor & self); +TORCH_API at::Tensor & _conj_physical_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor conj_physical_sparse_csr(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_copy_from_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_copy_from_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..db978e3c878381977c2af867a5a54bd705b49bf4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_copy_from_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 _copy_from { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_copy_from") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_copy_from(Tensor self, Tensor dst, bool non_blocking=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & dst, bool non_blocking); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & dst, bool non_blocking); +}; + +struct TORCH_API _copy_from_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, 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::_copy_from") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_copy_from.out(Tensor self, Tensor dst, bool non_blocking=False, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & dst, bool non_blocking, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & dst, bool non_blocking, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2b92fd940a35bfe6b1e44c0f300224bdd3661b1f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_cpu_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 cpu { + +TORCH_API ::std::tuple _embedding_bag_forward_only(const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq=false, int64_t mode=0, bool sparse=false, const c10::optional & per_sample_weights={}, bool include_last_offset=false, int64_t padding_idx=-1); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_max_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_max_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..42a92e3c5acc201534f63d111640cdebc43a61b4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_clamp_max_cuda_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 cuda { + +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 cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log2_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log2_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..97e764d2879bcd8f8a6d47e891110a9769880ecf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log2_cpu_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 cpu { + +TORCH_API ::std::vector _foreach_log2(at::TensorList self); +TORCH_API void _foreach_log2_(at::TensorList self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_zero_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_zero_native.h new file mode 100644 index 0000000000000000000000000000000000000000..e98e622b3b846997481ef15a98ac27b95233a2a0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_zero_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 ::std::vector _foreach_zero(at::TensorList self); +TORCH_API void _foreach_zero_out(at::TensorList self, at::TensorList out); +TORCH_API void foreach_tensor_zero_slow_(at::TensorList self); +TORCH_API void foreach_tensor_zero_cuda_(at::TensorList self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_is_any_true_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_is_any_true_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7fda9572c3d229e49dc94c440cf196662f650104 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_is_any_true_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 _is_any_true { + 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::_is_any_true") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_is_any_true(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/_make_per_tensor_quantized_tensor_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_per_tensor_quantized_tensor_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..efa99b6c547cc1e76a759b9b33c0f9af5ab6a5eb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_per_tensor_quantized_tensor_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 & _make_per_tensor_quantized_tensor_out(at::Tensor & out, const at::Tensor & self, double scale, int64_t zero_point); +TORCH_API at::Tensor & _make_per_tensor_quantized_tensor_outf(const at::Tensor & self, double scale, int64_t zero_point, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution_transpose_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution_transpose_native.h new file mode 100644 index 0000000000000000000000000000000000000000..6013337aa4ef0ac37917548828bee4e30210c5f7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_mps_convolution_transpose_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 & _mps_convolution_transpose_out_symint(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_copy_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_copy_native.h new file mode 100644 index 0000000000000000000000000000000000000000..0ed3a730a268d4f59b4142a98c45f17b5f16c4e3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_copy_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 & _nested_view_from_jagged_copy_out(const at::Tensor & self, const at::Tensor & offsets, const at::Tensor & dummy, const c10::optional & lengths, int64_t ragged_idx, at::Tensor & out); +TORCH_API at::Tensor _nested_view_from_jagged_copy(const at::Tensor & self, const at::Tensor & offsets, const at::Tensor & dummy, const c10::optional & lengths={}, int64_t ragged_idx=1); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..149af92a478895163506cf740c55ac446a6e261c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_view_from_jagged_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 _nested_view_from_jagged { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, const c10::optional &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_nested_view_from_jagged") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_view_from_jagged(Tensor(a) self, Tensor offsets, Tensor dummy, Tensor? lengths=None, int ragged_idx=1) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, const at::Tensor & offsets, const at::Tensor & dummy, const c10::optional & lengths, int64_t ragged_idx); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & offsets, const at::Tensor & dummy, const c10::optional & lengths, int64_t ragged_idx); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_csc_tensor_unsafe_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_csc_tensor_unsafe_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..12344f8e996d845a269b83e45926aef4b540b189 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_csc_tensor_unsafe_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 _sparse_csc_tensor_unsafe { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, at::IntArrayRef, 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::_sparse_csc_tensor_unsafe") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_sparse_csc_tensor_unsafe(Tensor ccol_indices, Tensor row_indices, Tensor values, int[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(const at::Tensor & ccol_indices, const at::Tensor & row_indices, const at::Tensor & values, at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & ccol_indices, const at::Tensor & row_indices, const at::Tensor & values, at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a0d4d19069ed0f3ea081606d249fa9015f9b7ec0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_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 ::std::tuple _thnn_differentiable_gru_cell_backward(const at::Tensor & grad_hy, const at::Tensor & input_gates, const at::Tensor & hidden_gates, const at::Tensor & hx, const c10::optional & input_bias, const c10::optional & hidden_bias); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b8773e00032dc0d54e14425c7e400d2bddb364c9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_differentiable_gru_cell_backward_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 _thnn_differentiable_gru_cell_backward { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const c10::optional &, const c10::optional &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_thnn_differentiable_gru_cell_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_thnn_differentiable_gru_cell_backward(Tensor grad_hy, Tensor input_gates, Tensor hidden_gates, Tensor hx, Tensor? input_bias, Tensor? hidden_bias) -> (Tensor, Tensor, Tensor, Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & grad_hy, const at::Tensor & input_gates, const at::Tensor & hidden_gates, const at::Tensor & hx, const c10::optional & input_bias, const c10::optional & hidden_bias); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_hy, const at::Tensor & input_gates, const at::Tensor & hidden_gates, const at::Tensor & hx, const c10::optional & input_bias, const c10::optional & hidden_bias); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unique_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unique_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cd37717750acef4cd0a611bc469d04eb12710aeb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unique_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 _unique_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & self, bool sorted=true, bool return_inverse=false); +TORCH_API ::std::tuple _unique_outf(const at::Tensor & self, bool sorted, bool return_inverse, at::Tensor & out0, at::Tensor & out1); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_native.h new file mode 100644 index 0000000000000000000000000000000000000000..aa7f917da7380ef160e65eb62589c254260dc7b1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_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 argsort(const at::Tensor & self, int64_t dim=-1, bool descending=false); +TORCH_API at::Tensor & argsort_stable_out(const at::Tensor & self, bool stable, int64_t dim, bool descending, at::Tensor & out); +TORCH_API at::Tensor argsort_stable(const at::Tensor & self, bool stable, int64_t dim=-1, bool descending=false); +TORCH_API at::Tensor argsort(const at::Tensor & self, at::Dimname dim, bool descending=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_right_shift_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_right_shift_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b86c0b04f9829fd18c3261d00294e062d6d16007 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_right_shift_compositeexplicitautogradnonfunctional_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 compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor bitwise_right_shift(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_right_shift_(at::Tensor & self, const at::Tensor & other); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7c094d7f83bd88fb770e504923190a5639687223 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_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 at::Tensor cat(const at::ITensorListRef & tensors, int64_t dim=0); +TORCH_API at::Tensor & cat_out(at::Tensor & out, const at::ITensorListRef & tensors, int64_t dim=0); +TORCH_API at::Tensor & cat_outf(const at::ITensorListRef & tensors, int64_t dim, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cholesky_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cholesky_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..53e8b1502f9c757594c7e02938720593df2b5870 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cholesky_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 cholesky_out { + using schema = at::Tensor & (const at::Tensor &, 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::cholesky") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cholesky.out(Tensor self, bool upper=False, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, bool upper, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool upper, at::Tensor & out); +}; + +struct TORCH_API cholesky { + using schema = at::Tensor (const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cholesky") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cholesky(Tensor self, bool upper=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, bool upper); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool upper); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_max_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_max_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f4e2e606f28f98b82b96985f1879a663c0a7f208 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_max_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 clamp_max(const at::Tensor & self, const at::Scalar & max); +TORCH_API at::Tensor & clamp_max_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & max); +TORCH_API at::Tensor & clamp_max_outf(const at::Tensor & self, const at::Scalar & max, at::Tensor & out); +TORCH_API at::Tensor & clamp_max_(at::Tensor & self, const at::Scalar & max); +TORCH_API at::Tensor clamp_max(const at::Tensor & self, const at::Tensor & max); +TORCH_API at::Tensor & clamp_max_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & max); +TORCH_API at::Tensor & clamp_max_outf(const at::Tensor & self, const at::Tensor & max, at::Tensor & out); +TORCH_API at::Tensor & clamp_max_(at::Tensor & self, const at::Tensor & max); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clip_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clip_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8adc9b9838f3aee6b05b15a2c942e971ac354c7b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clip_compositeimplicitautograd_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 compositeimplicitautograd { + +TORCH_API at::Tensor clip(const at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor & clip_out(at::Tensor & out, const at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor & clip_outf(const at::Tensor & self, const c10::optional & min, const c10::optional & max, at::Tensor & out); +TORCH_API at::Tensor & clip_(at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor clip(const at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); +TORCH_API at::Tensor & clip_out(at::Tensor & out, const at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); +TORCH_API at::Tensor & clip_outf(const at::Tensor & self, const c10::optional & min, const c10::optional & max, at::Tensor & out); +TORCH_API at::Tensor & clip_(at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/combinations.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/combinations.h new file mode 100644 index 0000000000000000000000000000000000000000..e0b54b1f663d89a1e6aeac801b16a38b763f0d45 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/combinations.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::combinations(Tensor self, int r=2, bool with_replacement=False) -> Tensor +inline at::Tensor combinations(const at::Tensor & self, int64_t r=2, bool with_replacement=false) { + return at::_ops::combinations::call(self, r, with_replacement); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_tbc_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_tbc_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..91e7af05536b4f7c764d9edabc36ce768d69b0ac --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_tbc_backward_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 conv_tbc_backward { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::conv_tbc_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "conv_tbc_backward(Tensor self, Tensor input, Tensor weight, Tensor bias, int pad) -> (Tensor, Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & self, const at::Tensor & input, const at::Tensor & weight, const at::Tensor & bias, int64_t pad); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & input, const at::Tensor & weight, const at::Tensor & bias, int64_t pad); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_transpose3d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_transpose3d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..dd3b3ee24abe81393b25796107d5ad65edc59cb9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_transpose3d_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 conv_transpose3d_input { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const c10::optional &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymInt, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::conv_transpose3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "conv_transpose3d.input(Tensor input, Tensor weight, Tensor? bias=None, SymInt[3] stride=1, SymInt[3] padding=0, SymInt[3] output_padding=0, SymInt groups=1, SymInt[3] dilation=1) -> Tensor") + static at::Tensor call(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymInt groups, c10::SymIntArrayRef dilation); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymInt groups, c10::SymIntArrayRef dilation); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cos.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cos.h new file mode 100644 index 0000000000000000000000000000000000000000..eb25f79f39f70667dac828f4546371bcbb5ce413 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cos.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::cos(Tensor self) -> Tensor +inline at::Tensor cos(const at::Tensor & self) { + return at::_ops::cos::call(self); +} + +// aten::cos_(Tensor(a!) self) -> Tensor(a!) +inline at::Tensor & cos_(at::Tensor & self) { + return at::_ops::cos_::call(self); +} + +// aten::cos.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & cos_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::cos_out::call(self, out); +} +// aten::cos.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & cos_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::cos_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3867516ddcb4830284078f960ca3f885822b5c2c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cosh_cpu_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 cpu { + +TORCH_API at::Tensor cosh(const at::Tensor & self); +TORCH_API at::Tensor & cosh_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & cosh_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & cosh_(at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_relu_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_relu_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5c688ce325bae7142bedad64c7ed5df231980b69 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_relu_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 & cudnn_convolution_relu_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups); +TORCH_API at::Tensor & cudnn_convolution_relu_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, int64_t groups, at::Tensor & out); +TORCH_API at::Tensor & cudnn_convolution_relu_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups); +TORCH_API at::Tensor & cudnn_convolution_relu_symint_outf(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef dilation, c10::SymInt groups, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/deg2rad_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/deg2rad_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..26458e6b05ed233ed19076ce3b5f7909070903a7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/deg2rad_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 deg2rad(const at::Tensor & self); +TORCH_API at::Tensor & deg2rad_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & deg2rad_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & deg2rad_(at::Tensor & self); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/exp2_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/exp2_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..957976aea53b2c6e591d42b48fa23830351e7186 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/exp2_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 exp2 { + 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::exp2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "exp2(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 exp2_ { + using schema = 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::exp2_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "exp2_(Tensor(a!) self) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self); +}; + +struct TORCH_API exp2_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::exp2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "exp2.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/fbgemm_linear_quantize_weight_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_quantize_weight_native.h new file mode 100644 index 0000000000000000000000000000000000000000..91e8ebad46f550d6e32eec5ca62ee9cd9de1cb4a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fbgemm_linear_quantize_weight_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 fbgemm_linear_quantize_weight(const at::Tensor & input); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fix_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fix_native.h new file mode 100644 index 0000000000000000000000000000000000000000..46e226b6491cd9c992d9b73cee62fb4aee143ebb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fix_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 fix(const at::Tensor & self); +TORCH_API at::Tensor & fix_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & fix_(at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..75706f0c730b7db8b517effadf90dee28de1f3ba --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d_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 fractional_max_pool3d_output { + using schema = ::std::tuple (const at::Tensor &, at::IntArrayRef, at::IntArrayRef, const at::Tensor &, 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::fractional_max_pool3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "output") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fractional_max_pool3d.output(Tensor self, int[3] kernel_size, int[3] output_size, Tensor random_samples, *, Tensor(a!) output, Tensor(b!) indices) -> (Tensor(a!), Tensor(b!))") + static ::std::tuple call(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples, at::Tensor & output, at::Tensor & indices); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples, at::Tensor & output, at::Tensor & indices); +}; + +struct TORCH_API fractional_max_pool3d { + using schema = ::std::tuple (const at::Tensor &, at::IntArrayRef, at::IntArrayRef, 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::fractional_max_pool3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fractional_max_pool3d(Tensor self, int[3] kernel_size, int[3] output_size, Tensor random_samples) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/frexp_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/frexp_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7f23ed030ecac100ae8bc0be877ab6b85a91a3e6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/frexp_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 ::std::tuple frexp(const at::Tensor & self); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e257e0bcbdd5ebb32a2692394de5c899a9d1b8c4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_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 gather(const at::Tensor & self, int64_t dim, const at::Tensor & index, bool sparse_grad=false); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..937017142f0e35ac3aed2ee764d67f49c14619c4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_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_gather : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, int64_t dim, const at::Tensor & index, bool sparse_grad); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gradient_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gradient_native.h new file mode 100644 index 0000000000000000000000000000000000000000..732b6c24f1c8c47faa3657b819bf0a3a8f45f74a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gradient_native.h @@ -0,0 +1,27 @@ +#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::vector gradient(const at::Tensor & self, const c10::optional & spacing=c10::nullopt, c10::optional dim=c10::nullopt, int64_t edge_order=1); +TORCH_API ::std::vector gradient(const at::Tensor & self, const at::Scalar & spacing, at::IntArrayRef dim, int64_t edge_order=1); +TORCH_API ::std::vector gradient(const at::Tensor & self, at::IntArrayRef dim, int64_t edge_order=1); +TORCH_API ::std::vector gradient(const at::Tensor & self, at::ArrayRef spacing, c10::optional dim=c10::nullopt, int64_t edge_order=1); +TORCH_API ::std::vector gradient(const at::Tensor & self, at::ArrayRef spacing, at::IntArrayRef dim, int64_t edge_order=1); +TORCH_API ::std::vector gradient(const at::Tensor & self, at::TensorList spacing, c10::optional dim=c10::nullopt, int64_t edge_order=1); +TORCH_API ::std::vector gradient(const at::Tensor & self, at::TensorList spacing, at::IntArrayRef dim, int64_t edge_order=1); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hypot.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hypot.h new file mode 100644 index 0000000000000000000000000000000000000000..589c8fea89cc8bf0a5eea98958f07fc311bd875e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hypot.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::hypot.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hypot_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::hypot_out::call(self, other, out); +} +// aten::hypot.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & hypot_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::hypot_out::call(self, other, out); +} + +// aten::hypot(Tensor self, Tensor other) -> Tensor +inline at::Tensor hypot(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::hypot::call(self, other); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_fill_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_fill_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8da068c69cda4236c7ddfe482473834fd9c9ef4b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_fill_cuda_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 cuda { + +TORCH_API at::Tensor & index_fill_(at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Scalar & value); +TORCH_API at::Tensor & index_fill_(at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & value); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/infinitely_differentiable_gelu_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/infinitely_differentiable_gelu_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b950db631fa9823335a5089f05b332c84120c8d0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/infinitely_differentiable_gelu_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 infinitely_differentiable_gelu_backward(const at::Tensor & grad, const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_inference.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_inference.h new file mode 100644 index 0000000000000000000000000000000000000000..61a0783697ce0ebee6ec99bed41dd983fb477623 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_inference.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::is_inference(Tensor self) -> bool +inline bool __dispatch_is_inference(const at::Tensor & self) { + return at::_ops::is_inference::call(self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp_native.h new file mode 100644 index 0000000000000000000000000000000000000000..9ecd5dd360a34c8877f59ab9365d7e95dd5da487 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp_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_lerp_Scalar : public at::meta::structured_lerp_Scalar { +void impl(const at::Tensor & self, const at::Tensor & end, const at::Scalar & weight, const at::Tensor & out); +}; +struct TORCH_API structured_lerp_Tensor : public at::meta::structured_lerp_Tensor { +void impl(const at::Tensor & self, const at::Tensor & end, const at::Tensor & weight, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_inv_ex_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_inv_ex_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..d95562e1ea8caff4d754688e41ebe1f71d484745 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_inv_ex_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_linalg_inv_ex : public at::impl::MetaBase { + + + void meta(const at::Tensor & A, bool check_errors); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_inv_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_inv_native.h new file mode 100644 index 0000000000000000000000000000000000000000..bc9263d7d6e73cd4579f7a17d26bcd2f4e3419e7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_inv_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_inv(const at::Tensor & A); +TORCH_API at::Tensor & linalg_inv_out(const at::Tensor & A, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2629caf8a0300efb62320ca9b85151be6687b5dd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_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 ::std::tuple max(const at::Tensor & self, int64_t dim, bool keepdim=false); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..6eb548130c5cf2cfc2f9bc972db8ab7e44bd0059 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_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 max_pool2d(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..567d20779158cf2ecd6ba26885c85801be37f56e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_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 max_pool3d(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride={}, at::IntArrayRef padding=0, at::IntArrayRef dilation=1, bool ceil_mode=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d.h new file mode 100644 index 0000000000000000000000000000000000000000..44834f2e452abfa5b81d3eb6cd9a135b1d49ecfe --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d.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::max_unpool3d.out(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & max_unpool3d_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d_out::call(self, indices, c10::fromIntArrayRefSlow(output_size), stride, padding, out); +} +namespace symint { + template ::value>> + at::Tensor & max_unpool3d_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d_out::call(self, indices, c10::fromIntArrayRefSlow(output_size), stride, padding, out); + } +} + +// aten::max_unpool3d.out(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & max_unpool3d_outf(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out) { + return at::_ops::max_unpool3d_out::call(self, indices, c10::fromIntArrayRefSlow(output_size), stride, padding, out); +} +namespace symint { + template ::value>> + at::Tensor & max_unpool3d_outf(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out) { + return at::_ops::max_unpool3d_out::call(self, indices, c10::fromIntArrayRefSlow(output_size), stride, padding, out); + } +} + +// aten::max_unpool3d.out(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & max_unpool3d_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d_out::call(self, indices, output_size, stride, padding, out); +} +namespace symint { + template ::value>> + at::Tensor & max_unpool3d_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d_out::call(self, indices, output_size, stride, padding, out); + } +} + +// aten::max_unpool3d.out(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & max_unpool3d_symint_outf(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out) { + return at::_ops::max_unpool3d_out::call(self, indices, output_size, stride, padding, out); +} +namespace symint { + template ::value>> + at::Tensor & max_unpool3d_outf(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out) { + return at::_ops::max_unpool3d_out::call(self, indices, output_size, stride, padding, out); + } +} + +// aten::max_unpool3d(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding) -> Tensor +inline at::Tensor max_unpool3d(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d::call(self, indices, c10::fromIntArrayRefSlow(output_size), stride, padding); +} +namespace symint { + template ::value>> + at::Tensor max_unpool3d(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d::call(self, indices, c10::fromIntArrayRefSlow(output_size), stride, padding); + } +} + +// aten::max_unpool3d(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding) -> Tensor +inline at::Tensor max_unpool3d_symint(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d::call(self, indices, output_size, stride, padding); +} +namespace symint { + template ::value>> + at::Tensor max_unpool3d(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding) { + return at::_ops::max_unpool3d::call(self, indices, output_size, stride, padding); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/meshgrid.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/meshgrid.h new file mode 100644 index 0000000000000000000000000000000000000000..f60c6e49067eb6e57f734ff40e5976123e7d5bef --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/meshgrid.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::meshgrid(Tensor[] tensors) -> Tensor[] +inline ::std::vector meshgrid(at::TensorList tensors) { + return at::_ops::meshgrid::call(tensors); +} + +// aten::meshgrid.indexing(Tensor[] tensors, *, str indexing) -> Tensor[] +inline ::std::vector meshgrid(at::TensorList tensors, c10::string_view indexing) { + return at::_ops::meshgrid_indexing::call(tensors, indexing); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mish_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mish_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a150e80649b0b6d42d767d9210c770e98d21aaf7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mish_backward_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 at::Tensor mish_backward(const at::Tensor & grad_output, const at::Tensor & self); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nansum.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nansum.h new file mode 100644 index 0000000000000000000000000000000000000000..39681928979d4d6c8c4389e44bd2ad38098cfbc0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nansum.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::nansum(Tensor self, int[1]? dim=None, bool keepdim=False, *, ScalarType? dtype=None) -> Tensor +inline at::Tensor nansum(const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt) { + return at::_ops::nansum::call(self, dim, keepdim, dtype); +} + +// aten::nansum.out(Tensor self, int[1]? dim=None, bool keepdim=False, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & nansum_out(at::Tensor & out, const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt) { + return at::_ops::nansum_out::call(self, dim, keepdim, dtype, out); +} +// aten::nansum.out(Tensor self, int[1]? dim=None, bool keepdim=False, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & nansum_outf(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out) { + return at::_ops::nansum_out::call(self, dim, keepdim, dtype, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ab2a4599a5e8d6f82b006669865531dd8d81ad58 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_native.h @@ -0,0 +1,36 @@ +#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 { +TORCH_API at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::ScalarType dtype); +TORCH_API at::Tensor & norm_ScalarOpt_dtype_out(const at::Tensor & self, const c10::optional & p, at::ScalarType dtype, at::Tensor & out); +TORCH_API at::Tensor norm(const at::Tensor & self, const at::Scalar & p=2); +TORCH_API at::Tensor & norm_Scalar_out(const at::Tensor & self, const at::Scalar & p, at::Tensor & out); +struct TORCH_API structured_norm_dtype_out : public at::meta::structured_norm_ScalarOpt_dim_dtype { +void impl(const at::Tensor & self, at::OptionalScalarRef p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype, const at::Tensor & out); +}; +TORCH_API at::Tensor sparse_dtype_norm(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype); +struct TORCH_API structured_norm_out : public at::meta::structured_norm_ScalarOpt_dim { +void impl(const at::Tensor & self, at::OptionalScalarRef p, at::IntArrayRef dim, bool keepdim, const at::Tensor & out); +}; +TORCH_API at::Tensor sparse_norm(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim=false); +TORCH_API at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype); +TORCH_API at::Tensor & norm_out(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype, at::Tensor & out); +TORCH_API at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim=false); +TORCH_API at::Tensor & norm_out(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..09039bedfb358bc22ce3a83c5deb8e39bef6f733 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_ops.h @@ -0,0 +1,149 @@ +#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 norm_ScalarOpt_dtype { + using schema = at::Tensor (const at::Tensor &, const c10::optional &, at::ScalarType); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "ScalarOpt_dtype") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.ScalarOpt_dtype(Tensor self, Scalar? p, *, ScalarType dtype) -> Tensor") + static at::Tensor call(const at::Tensor & self, const c10::optional & p, at::ScalarType dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::ScalarType dtype); +}; + +struct TORCH_API norm_Scalar { + using schema = at::Tensor (const at::Tensor &, const at::Scalar &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.Scalar(Tensor self, Scalar p=2) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & p); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & p); +}; + +struct TORCH_API norm_ScalarOpt_dim_dtype { + using schema = at::Tensor (const at::Tensor &, const c10::optional &, at::IntArrayRef, bool, at::ScalarType); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "ScalarOpt_dim_dtype") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.ScalarOpt_dim_dtype(Tensor self, Scalar? p, int[1] dim, bool keepdim, *, ScalarType dtype) -> Tensor") + static at::Tensor call(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype); +}; + +struct TORCH_API norm_ScalarOpt_dim { + using schema = at::Tensor (const at::Tensor &, const c10::optional &, at::IntArrayRef, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "ScalarOpt_dim") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.ScalarOpt_dim(Tensor self, Scalar? p, int[1] dim, bool keepdim=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim); +}; + +struct TORCH_API norm_dtype_out { + using schema = at::Tensor & (const at::Tensor &, const c10::optional &, at::IntArrayRef, bool, at::ScalarType, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dtype_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.dtype_out(Tensor self, Scalar? p, int[1] dim, bool keepdim, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype, at::Tensor & out); +}; + +struct TORCH_API norm_out { + using schema = at::Tensor & (const at::Tensor &, const c10::optional &, at::IntArrayRef, 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::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.out(Tensor self, Scalar? p, int[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::Tensor & out); +}; + +struct TORCH_API norm_names_ScalarOpt_dim_dtype { + using schema = at::Tensor (const at::Tensor &, const c10::optional &, at::DimnameList, bool, at::ScalarType); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_ScalarOpt_dim_dtype") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.names_ScalarOpt_dim_dtype(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim, *, ScalarType dtype) -> Tensor") + static at::Tensor call(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype); +}; + +struct TORCH_API norm_names_ScalarOpt_dim { + using schema = at::Tensor (const at::Tensor &, const c10::optional &, at::DimnameList, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_ScalarOpt_dim") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.names_ScalarOpt_dim(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim); +}; + +struct TORCH_API norm_names_dtype_out { + using schema = at::Tensor & (const at::Tensor &, const c10::optional &, at::DimnameList, bool, at::ScalarType, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_dtype_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.names_dtype_out(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype, at::Tensor & out); +}; + +struct TORCH_API norm_names_out { + using schema = at::Tensor & (const at::Tensor &, const c10::optional &, at::DimnameList, 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::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.names_out(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::Tensor & out); +}; + +struct TORCH_API norm_ScalarOpt_dtype_out { + using schema = at::Tensor & (const at::Tensor &, const c10::optional &, at::ScalarType, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "ScalarOpt_dtype_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.ScalarOpt_dtype_out(Tensor self, Scalar? p, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const c10::optional & p, at::ScalarType dtype, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::optional & p, at::ScalarType dtype, at::Tensor & out); +}; + +struct TORCH_API norm_Scalar_out { + using schema = at::Tensor & (const at::Tensor &, const at::Scalar &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "norm.Scalar_out(Tensor self, Scalar p=2, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Scalar & p, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & p, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ormqr.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ormqr.h new file mode 100644 index 0000000000000000000000000000000000000000..85d20d27aa0c9e9e76a783316dfdeec33b9f9f12 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ormqr.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::ormqr.out(Tensor self, Tensor input2, Tensor input3, bool left=True, bool transpose=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & ormqr_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & input2, const at::Tensor & input3, bool left=true, bool transpose=false) { + return at::_ops::ormqr_out::call(self, input2, input3, left, transpose, out); +} +// aten::ormqr.out(Tensor self, Tensor input2, Tensor input3, bool left=True, bool transpose=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & ormqr_outf(const at::Tensor & self, const at::Tensor & input2, const at::Tensor & input3, bool left, bool transpose, at::Tensor & out) { + return at::_ops::ormqr_out::call(self, input2, input3, left, transpose, out); +} + +// aten::ormqr(Tensor self, Tensor input2, Tensor input3, bool left=True, bool transpose=False) -> Tensor +inline at::Tensor ormqr(const at::Tensor & self, const at::Tensor & input2, const at::Tensor & input3, bool left=true, bool transpose=false) { + return at::_ops::ormqr::call(self, input2, input3, left, transpose); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ormqr_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ormqr_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ee7220759d3c5a50526c0d7dcf9083b8ca9d3356 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ormqr_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 ormqr(const at::Tensor & self, const at::Tensor & input2, const at::Tensor & input3, bool left=true, bool transpose=false); +TORCH_API at::Tensor & ormqr_out(const at::Tensor & self, const at::Tensor & input2, const at::Tensor & input3, bool left, bool transpose, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/put_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/put_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..e1f78e0c55db94335f45f5941c230739e213dd20 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/put_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 put_ { + using schema = at::Tensor & (at::Tensor &, const at::Tensor &, const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::put_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "put_(Tensor(a!) self, Tensor index, Tensor source, bool accumulate=False) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Tensor & index, const at::Tensor & source, bool accumulate); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Tensor & index, const at::Tensor & source, bool accumulate); +}; + +struct TORCH_API put { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::put") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "put(Tensor self, Tensor index, Tensor source, bool accumulate=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & index, const at::Tensor & source, bool accumulate); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & index, const at::Tensor & source, bool accumulate); +}; + +struct TORCH_API put_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Tensor &, 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::put") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "put.out(Tensor self, Tensor index, Tensor source, bool accumulate=False, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & index, const at::Tensor & source, bool accumulate, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & index, const at::Tensor & source, bool accumulate, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/randperm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/randperm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b7b27802bbf1f57078f05af29fd8a28215633f79 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/randperm_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 randperm { + using schema = at::Tensor (c10::SymInt, 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::randperm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randperm(SymInt n, *, ScalarType? dtype=long, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(c10::SymInt n, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, c10::SymInt n, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API randperm_generator { + using schema = at::Tensor (c10::SymInt, c10::optional, 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::randperm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "generator") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randperm.generator(SymInt n, *, Generator? generator, ScalarType? dtype=long, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(c10::SymInt n, c10::optional generator, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, c10::SymInt n, c10::optional generator, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API randperm_out { + using schema = at::Tensor & (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::randperm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randperm.out(SymInt n, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(c10::SymInt n, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, c10::SymInt n, at::Tensor & out); +}; + +struct TORCH_API randperm_generator_out { + using schema = at::Tensor & (c10::SymInt, 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::randperm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "generator_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "randperm.generator_out(SymInt n, *, Generator? generator, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(c10::SymInt n, c10::optional generator, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, c10::SymInt n, 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/range_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/range_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0b4679bf6ab1bb9884483e93d5b4cdead0e37ef1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/range_compositeexplicitautograd_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 compositeexplicitautograd { + +TORCH_API at::Tensor range(const at::Scalar & start, const at::Scalar & end, const at::Scalar & step=1, at::TensorOptions options={}); +TORCH_API at::Tensor range(const at::Scalar & start, const at::Scalar & end, const at::Scalar & step, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +TORCH_API at::Tensor range(const at::Scalar & start, const at::Scalar & end, at::TensorOptions options={}); +TORCH_API at::Tensor range(const at::Scalar & start, const at::Scalar & end, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +TORCH_API at::Tensor & range_out(at::Tensor & out, const at::Scalar & start, const at::Scalar & end); +TORCH_API at::Tensor & range_outf(const at::Scalar & start, const at::Scalar & end, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sgn_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sgn_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..b12d2ca913121e2ecf9bfac216a0b5eefa6ba4df --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sgn_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_sgn : public TensorIteratorBase { + + + void meta(const at::Tensor & self); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..05061067c6c6e7d8b1bb826cd6a3d54e0b81da62 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_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 silu { + 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::silu") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "silu(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 silu_ { + using schema = 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::silu_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "silu_(Tensor(a!) self) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self); +}; + +struct TORCH_API silu_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::silu") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "silu.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/sinc_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinc_native.h new file mode 100644 index 0000000000000000000000000000000000000000..6875effe199e73df53c80ddc5ef6b5596ee88e39 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinc_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 +#include + +namespace at { +namespace native { +struct TORCH_API structured_sinc_out : public at::meta::structured_sinc { +void impl(const at::Tensor & self, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/size.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/size.h new file mode 100644 index 0000000000000000000000000000000000000000..4fabdc247ffa5375051ea64981614d862eee5ffc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/size.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::size.int(Tensor self, int dim) -> int +inline int64_t __dispatch_size(const at::Tensor & self, int64_t dim) { + return at::_ops::size_int::call(self, dim); +} + +// aten::size.Dimname(Tensor self, Dimname dim) -> int +inline int64_t size(const at::Tensor & self, at::Dimname dim) { + return at::_ops::size_Dimname::call(self, dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_native.h new file mode 100644 index 0000000000000000000000000000000000000000..68f82cf5ff8d46066e4b9dd7800f60f20778fc8b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_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 +#include + +namespace at { +namespace native { +struct TORCH_API structured_smooth_l1_loss_out : public at::meta::structured_smooth_l1_loss { +void impl(const at::Tensor & self, const at::Tensor & target, int64_t reduction, double beta, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_mask.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_mask.h new file mode 100644 index 0000000000000000000000000000000000000000..0faeeb1e100e997bfabbb9ada2b383f8626f665c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_mask.h @@ -0,0 +1,34 @@ +#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_mask.out(Tensor self, Tensor mask, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & sparse_mask_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & mask) { + return at::_ops::sparse_mask_out::call(self, mask, out); +} +// aten::sparse_mask.out(Tensor self, Tensor mask, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & sparse_mask_outf(const at::Tensor & self, const at::Tensor & mask, at::Tensor & out) { + return at::_ops::sparse_mask_out::call(self, mask, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_sampled_addmm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_sampled_addmm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..a0a6971522a99e9b89fb97e14d529d5aec206fda --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_sampled_addmm_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 sparse_sampled_addmm_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Scalar &, const at::Scalar &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::sparse_sampled_addmm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "sparse_sampled_addmm.out(Tensor self, Tensor mat1, Tensor mat2, *, Scalar beta=1, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta, const at::Scalar & alpha, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta, const at::Scalar & alpha, at::Tensor & out); +}; + +struct TORCH_API sparse_sampled_addmm { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Scalar &, const at::Scalar &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::sparse_sampled_addmm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "sparse_sampled_addmm(Tensor self, Tensor mat1, Tensor mat2, *, Scalar beta=1, Scalar alpha=1) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta, const at::Scalar & alpha); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta, const at::Scalar & alpha); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_exp2_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_exp2_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a39c665ed569b2345d11e48f07cb685a0f66befc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_exp2_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 special_exp2(const at::Tensor & self); +TORCH_API at::Tensor & special_exp2_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/special_modified_bessel_i0_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i0_native.h new file mode 100644 index 0000000000000000000000000000000000000000..94e2978df3a17f278bf40e63c79e54b0bcc10fd7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i0_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 +#include + +namespace at { +namespace native { +struct TORCH_API structured_special_modified_bessel_i0_out : public at::meta::structured_special_modified_bessel_i0 { +void impl(const at::Tensor & self, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tan.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tan.h new file mode 100644 index 0000000000000000000000000000000000000000..1c5ee0014025f3c4a050a26319e30c2351f110f7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tan.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::tan(Tensor self) -> Tensor +inline at::Tensor tan(const at::Tensor & self) { + return at::_ops::tan::call(self); +} + +// aten::tan_(Tensor(a!) self) -> Tensor(a!) +inline at::Tensor & tan_(at::Tensor & self) { + return at::_ops::tan_::call(self); +} + +// aten::tan.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & tan_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::tan_out::call(self, out); +} +// aten::tan.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & tan_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::tan_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense.h new file mode 100644 index 0000000000000000000000000000000000000000..591be3a19ac6a1814f2c0ee7577f83240686f85b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense.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/to_mkldnn_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_mkldnn_native.h new file mode 100644 index 0000000000000000000000000000000000000000..e93c33efde68f4dd3d3919818c42e8f1717a2b84 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_mkldnn_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 & to_mkldnn_out(const at::Tensor & self, c10::optional dtype, at::Tensor & out); +TORCH_API at::Tensor dense_to_mkldnn(const at::Tensor & self, c10::optional dtype=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unflatten_dense_tensors_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unflatten_dense_tensors_native.h new file mode 100644 index 0000000000000000000000000000000000000000..9c56cc113680cf9b47f376438c201b33b3007a31 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unflatten_dense_tensors_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::vector unflatten_dense_tensors(const at::Tensor & flat, at::TensorList tensors); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsafe_split_with_sizes_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsafe_split_with_sizes_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..6f7c9db51ef65c0c349c512fa6c77e2c74d68ed1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsafe_split_with_sizes_compositeexplicitautograd_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 compositeexplicitautograd { + +TORCH_API ::std::vector unsafe_split_with_sizes(const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim=0); +TORCH_API ::std::vector unsafe_split_with_sizes_symint(const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim=0); +TORCH_API void unsafe_split_with_sizes_out(at::TensorList out, const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim=0); +TORCH_API void unsafe_split_with_sizes_outf(const at::Tensor & self, at::IntArrayRef split_sizes, int64_t dim, at::TensorList out); +TORCH_API void unsafe_split_with_sizes_symint_out(at::TensorList out, const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim=0); +TORCH_API void unsafe_split_with_sizes_symint_outf(const at::Tensor & self, c10::SymIntArrayRef split_sizes, int64_t dim, at::TensorList out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bicubic2d_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bicubic2d_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..183d084e51e8355e1b413662f6a745acd8b6278e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_bicubic2d_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 upsample_bicubic2d(const at::Tensor & input, at::OptionalIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); +TORCH_API at::Tensor upsample_bicubic2d_symint(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest3d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest3d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a01f5a07bb326120c958362cecbc3ffb52080312 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_nearest3d_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 +#include + +namespace at { +namespace native { +TORCH_API at::Tensor upsample_nearest3d(const at::Tensor & input, at::OptionalIntArrayRef output_size, c10::optional> scale_factors); +struct TORCH_API structured_upsample_nearest3d_out_cpu : public at::meta::structured_upsample_nearest3d { +void impl(const at::Tensor & self, at::ArrayRef output_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +struct TORCH_API structured_upsample_nearest3d_out_cuda : public at::meta::structured_upsample_nearest3d { +void impl(const at::Tensor & self, at::ArrayRef output_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, const at::Tensor & out); +}; +TORCH_API at::Tensor upsample_nearest3d_quantized_cpu(const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +} // namespace native +} // namespace at