diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Float.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Float.h new file mode 100644 index 0000000000000000000000000000000000000000..7e47953e8db9858de743b27649def4e79109e1ed --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Float.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::_cast_Float(Tensor self, bool non_blocking=False) -> Tensor +inline at::Tensor _cast_Float(const at::Tensor & self, bool non_blocking=false) { + return at::_ops::_cast_Float::call(self, non_blocking); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_coalesce.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_coalesce.h new file mode 100644 index 0000000000000000000000000000000000000000..ebbea6a6868a214dc83f0d86c5c28f039c62d63d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_coalesce.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::_coalesce(Tensor self) -> Tensor +inline at::Tensor _coalesce(const at::Tensor & self) { + return at::_ops::_coalesce::call(self); +} + +// aten::_coalesce.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _coalesce_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::_coalesce_out::call(self, out); +} +// aten::_coalesce.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _coalesce_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::_coalesce_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..18400a07c430f224173fd3197230d7d479b9db23 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _cudnn_rnn_backward { + using schema = ::std::tuple> (const at::Tensor &, at::TensorList, int64_t, const at::Tensor &, const at::Tensor &, const c10::optional &, const at::Tensor &, const c10::optional &, const c10::optional &, const c10::optional &, int64_t, c10::SymInt, c10::SymInt, int64_t, bool, double, bool, bool, c10::SymIntArrayRef, const c10::optional &, const at::Tensor &, ::std::array); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cudnn_rnn_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cudnn_rnn_backward(Tensor input, Tensor[] weight, int weight_stride0, Tensor weight_buf, Tensor hx, Tensor? cx, Tensor output, Tensor? grad_output, Tensor? grad_hy, Tensor? grad_cy, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state, Tensor reserve, bool[4] output_mask) -> (Tensor, Tensor, Tensor, Tensor[])") + static ::std::tuple> call(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const at::Tensor & weight_buf, const at::Tensor & hx, const c10::optional & cx, const at::Tensor & output, const c10::optional & grad_output, const c10::optional & grad_hy, const c10::optional & grad_cy, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, double dropout, bool train, bool bidirectional, c10::SymIntArrayRef batch_sizes, const c10::optional & dropout_state, const at::Tensor & reserve, ::std::array output_mask); + static ::std::tuple> redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const at::Tensor & weight_buf, const at::Tensor & hx, const c10::optional & cx, const at::Tensor & output, const c10::optional & grad_output, const c10::optional & grad_hy, const c10::optional & grad_cy, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, double dropout, bool train, bool bidirectional, c10::SymIntArrayRef batch_sizes, const c10::optional & dropout_state, const at::Tensor & reserve, ::std::array output_mask); +}; + +struct TORCH_API _cudnn_rnn_backward_out { + using schema = void (const at::Tensor &, at::TensorList, int64_t, const at::Tensor &, const at::Tensor &, const c10::optional &, const at::Tensor &, const c10::optional &, const c10::optional &, const c10::optional &, int64_t, c10::SymInt, c10::SymInt, int64_t, bool, double, bool, bool, c10::SymIntArrayRef, const c10::optional &, const at::Tensor &, ::std::array, at::Tensor &, at::Tensor &, at::Tensor &, at::TensorList); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cudnn_rnn_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cudnn_rnn_backward.out(Tensor input, Tensor[] weight, int weight_stride0, Tensor weight_buf, Tensor hx, Tensor? cx, Tensor output, Tensor? grad_output, Tensor? grad_hy, Tensor? grad_cy, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state, Tensor reserve, bool[4] output_mask, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!)[] out3) -> ()") + static void call(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const at::Tensor & weight_buf, const at::Tensor & hx, const c10::optional & cx, const at::Tensor & output, const c10::optional & grad_output, const c10::optional & grad_hy, const c10::optional & grad_cy, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, double dropout, bool train, bool bidirectional, c10::SymIntArrayRef batch_sizes, const c10::optional & dropout_state, const at::Tensor & reserve, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::TensorList out3); + static void redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const at::Tensor & weight_buf, const at::Tensor & hx, const c10::optional & cx, const at::Tensor & output, const c10::optional & grad_output, const c10::optional & grad_hy, const c10::optional & grad_cy, int64_t mode, c10::SymInt hidden_size, c10::SymInt proj_size, int64_t num_layers, bool batch_first, double dropout, bool train, bool bidirectional, c10::SymIntArrayRef batch_sizes, const c10::optional & dropout_state, const at::Tensor & reserve, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::TensorList out3); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fill_mem_eff_dropout_mask_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fill_mem_eff_dropout_mask_native.h new file mode 100644 index 0000000000000000000000000000000000000000..5d3a525d7b2de1784f2e850d08778b8cd69edbe0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fill_mem_eff_dropout_mask_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 & _fill_mem_eff_dropout_mask_(at::Tensor & self, double dropout_p, int64_t seed, int64_t offset); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_addcmul.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_addcmul.h new file mode 100644 index 0000000000000000000000000000000000000000..234bf10f3954bee176a675486d429ca6a2d137bf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_addcmul.h @@ -0,0 +1,82 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_foreach_addcmul.Scalar(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar value=1) -> Tensor[] +inline ::std::vector _foreach_addcmul(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Scalar & value=1) { + return at::_ops::_foreach_addcmul_Scalar::call(self, tensor1, tensor2, value); +} + +// aten::_foreach_addcmul.ScalarList(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar[] scalars) -> Tensor[] +inline ::std::vector _foreach_addcmul(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, at::ArrayRef scalars) { + return at::_ops::_foreach_addcmul_ScalarList::call(self, tensor1, tensor2, scalars); +} + +// aten::_foreach_addcmul.Tensor(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Tensor scalars) -> Tensor[] +inline ::std::vector _foreach_addcmul(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Tensor & scalars) { + return at::_ops::_foreach_addcmul_Tensor::call(self, tensor1, tensor2, scalars); +} + +// aten::_foreach_addcmul_.Scalar(Tensor(a!)[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar value=1) -> () +inline void _foreach_addcmul_(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Scalar & value=1) { + return at::_ops::_foreach_addcmul__Scalar::call(self, tensor1, tensor2, value); +} + +// aten::_foreach_addcmul_.ScalarList(Tensor(a!)[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar[] scalars) -> () +inline void _foreach_addcmul_(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, at::ArrayRef scalars) { + return at::_ops::_foreach_addcmul__ScalarList::call(self, tensor1, tensor2, scalars); +} + +// aten::_foreach_addcmul_.Tensor(Tensor(a!)[] self, Tensor[] tensor1, Tensor[] tensor2, Tensor scalars) -> () +inline void _foreach_addcmul_(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Tensor & scalars) { + return at::_ops::_foreach_addcmul__Tensor::call(self, tensor1, tensor2, scalars); +} + +// aten::_foreach_addcmul.Scalar_out(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar value=1, *, Tensor(a!)[] out) -> () +inline void _foreach_addcmul_out(at::TensorList out, at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Scalar & value=1) { + return at::_ops::_foreach_addcmul_Scalar_out::call(self, tensor1, tensor2, value, out); +} +// aten::_foreach_addcmul.Scalar_out(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar value=1, *, Tensor(a!)[] out) -> () +inline void _foreach_addcmul_outf(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Scalar & value, at::TensorList out) { + return at::_ops::_foreach_addcmul_Scalar_out::call(self, tensor1, tensor2, value, out); +} + +// aten::_foreach_addcmul.ScalarList_out(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar[] scalars, *, Tensor(a!)[] out) -> () +inline void _foreach_addcmul_out(at::TensorList out, at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, at::ArrayRef scalars) { + return at::_ops::_foreach_addcmul_ScalarList_out::call(self, tensor1, tensor2, scalars, out); +} +// aten::_foreach_addcmul.ScalarList_out(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Scalar[] scalars, *, Tensor(a!)[] out) -> () +inline void _foreach_addcmul_outf(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, at::ArrayRef scalars, at::TensorList out) { + return at::_ops::_foreach_addcmul_ScalarList_out::call(self, tensor1, tensor2, scalars, out); +} + +// aten::_foreach_addcmul.Tensor_out(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Tensor scalars, *, Tensor(a!)[] out) -> () +inline void _foreach_addcmul_out(at::TensorList out, at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Tensor & scalars) { + return at::_ops::_foreach_addcmul_Tensor_out::call(self, tensor1, tensor2, scalars, out); +} +// aten::_foreach_addcmul.Tensor_out(Tensor[] self, Tensor[] tensor1, Tensor[] tensor2, Tensor scalars, *, Tensor(a!)[] out) -> () +inline void _foreach_addcmul_outf(at::TensorList self, at::TensorList tensor1, at::TensorList tensor2, const at::Tensor & scalars, at::TensorList out) { + return at::_ops::_foreach_addcmul_Tensor_out::call(self, tensor1, tensor2, scalars, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b335370d27a94653e11e83b7e18d11327b7c73aa --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log_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_log(at::TensorList self); +TORCH_API void _foreach_log_(at::TensorList self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_indices_copy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_indices_copy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b11a28b62b27864a3173e625a703fe46de49c22f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_indices_copy_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _indices_copy { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_indices_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_indices_copy(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API _indices_copy_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_indices_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_indices_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_per_tensor_quantized_tensor_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_per_tensor_quantized_tensor_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..c817e7547dbbccd3e6c165f24cb25583e4e1c406 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_make_per_tensor_quantized_tensor_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 _make_per_tensor_quantized_tensor { + using schema = at::Tensor (const at::Tensor &, 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::_make_per_tensor_quantized_tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_make_per_tensor_quantized_tensor(Tensor self, float scale, int zero_point) -> Tensor") + static at::Tensor call(const at::Tensor & self, double scale, int64_t zero_point); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, double scale, int64_t zero_point); +}; + +struct TORCH_API _make_per_tensor_quantized_tensor_out { + using schema = at::Tensor & (const at::Tensor &, 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::_make_per_tensor_quantized_tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_make_per_tensor_quantized_tensor.out(Tensor self, float scale, int zero_point, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, double scale, int64_t zero_point, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, double scale, int64_t zero_point, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_select_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_select_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..e286d32b192b3e577eb5d6e3521e493e53b6d0ff --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_select_backward.h @@ -0,0 +1,47 @@ +#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::_nested_select_backward(Tensor grad_output, Tensor self, int dim, SymInt index) -> Tensor +inline at::Tensor _nested_select_backward(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim, int64_t index) { + return at::_ops::_nested_select_backward::call(grad_output, self, dim, index); +} +namespace symint { + template ::value>> + at::Tensor _nested_select_backward(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim, int64_t index) { + return at::_ops::_nested_select_backward::call(grad_output, self, dim, index); + } +} + +// aten::_nested_select_backward(Tensor grad_output, Tensor self, int dim, SymInt index) -> Tensor +inline at::Tensor _nested_select_backward_symint(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim, c10::SymInt index) { + return at::_ops::_nested_select_backward::call(grad_output, self, dim, index); +} +namespace symint { + template ::value>> + at::Tensor _nested_select_backward(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim, c10::SymInt index) { + return at::_ops::_nested_select_backward::call(grad_output, self, dim, index); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_softmax_backward_data_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_softmax_backward_data_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7e712e737214b47605d0bf81c8810e019652274a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_softmax_backward_data_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 _softmax_backward_data(const at::Tensor & grad_output, const at::Tensor & output, int64_t dim, at::ScalarType input_dtype); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_stack_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_stack_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..98e3e4f963772389c2d0837c953540994d6c0f03 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_stack_cpu_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 cpu { + +TORCH_API at::Tensor _stack(at::TensorList tensors, int64_t dim=0); +TORCH_API at::Tensor & _stack_out(at::Tensor & out, at::TensorList tensors, int64_t dim=0); +TORCH_API at::Tensor & _stack_outf(at::TensorList tensors, int64_t dim, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..37896513bdea080fb91181de9432586330c07be7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_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_fused_lstm_cell_backward { + using schema = ::std::tuple (const c10::optional &, const c10::optional &, 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::_thnn_fused_lstm_cell_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_thnn_fused_lstm_cell_backward(Tensor? grad_hy, Tensor? grad_cy, Tensor cx, Tensor cy, Tensor workspace, bool has_bias) -> (Tensor, Tensor, Tensor, Tensor, Tensor)") + static ::std::tuple call(const c10::optional & grad_hy, const c10::optional & grad_cy, const at::Tensor & cx, const at::Tensor & cy, const at::Tensor & workspace, bool has_bias); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const c10::optional & grad_hy, const c10::optional & grad_cy, const at::Tensor & cx, const at::Tensor & cy, const at::Tensor & workspace, bool has_bias); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b185005ad90d47fd48126d47d694dd5b1e6c7339 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_lstm_cell_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::tuple _thnn_fused_lstm_cell(const at::Tensor & input_gates, const at::Tensor & hidden_gates, const at::Tensor & cx, const c10::optional & input_bias={}, const c10::optional & hidden_bias={}); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_ctc_loss_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_ctc_loss_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7bb65a27d711ef410200c7db9b481638453d22ae --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_ctc_loss_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 _use_cudnn_ctc_loss { + using schema = bool (const at::Tensor &, const at::Tensor &, at::IntArrayRef, at::IntArrayRef, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_use_cudnn_ctc_loss") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_use_cudnn_ctc_loss(Tensor log_probs, Tensor targets, int[] input_lengths, int[] target_lengths, int blank) -> bool") + static bool call(const at::Tensor & log_probs, const at::Tensor & targets, at::IntArrayRef input_lengths, at::IntArrayRef target_lengths, int64_t blank); + static bool redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & log_probs, const at::Tensor & targets, at::IntArrayRef input_lengths, at::IntArrayRef target_lengths, int64_t blank); +}; + +struct TORCH_API _use_cudnn_ctc_loss_Tensor { + using schema = bool (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::_use_cudnn_ctc_loss") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_use_cudnn_ctc_loss.Tensor(Tensor log_probs, Tensor targets, Tensor input_lengths, Tensor target_lengths, int blank) -> bool") + static bool call(const at::Tensor & log_probs, const at::Tensor & targets, const at::Tensor & input_lengths, const at::Tensor & target_lengths, int64_t blank); + static bool redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & log_probs, const at::Tensor & targets, const at::Tensor & input_lengths, const at::Tensor & target_lengths, int64_t blank); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool2d.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool2d.h new file mode 100644 index 0000000000000000000000000000000000000000..0262f50a9e043812acb6946b1442f855f3035685 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool2d.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::adaptive_avg_pool2d.out(Tensor self, SymInt[2] output_size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & adaptive_avg_pool2d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d_out::call(self, c10::fromIntArrayRefSlow(output_size), out); +} +namespace symint { + template ::value>> + at::Tensor & adaptive_avg_pool2d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d_out::call(self, c10::fromIntArrayRefSlow(output_size), out); + } +} + +// aten::adaptive_avg_pool2d.out(Tensor self, SymInt[2] output_size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & adaptive_avg_pool2d_outf(const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out) { + return at::_ops::adaptive_avg_pool2d_out::call(self, c10::fromIntArrayRefSlow(output_size), out); +} +namespace symint { + template ::value>> + at::Tensor & adaptive_avg_pool2d_outf(const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out) { + return at::_ops::adaptive_avg_pool2d_out::call(self, c10::fromIntArrayRefSlow(output_size), out); + } +} + +// aten::adaptive_avg_pool2d.out(Tensor self, SymInt[2] output_size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & adaptive_avg_pool2d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d_out::call(self, output_size, out); +} +namespace symint { + template ::value>> + at::Tensor & adaptive_avg_pool2d_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d_out::call(self, output_size, out); + } +} + +// aten::adaptive_avg_pool2d.out(Tensor self, SymInt[2] output_size, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & adaptive_avg_pool2d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, at::Tensor & out) { + return at::_ops::adaptive_avg_pool2d_out::call(self, output_size, out); +} +namespace symint { + template ::value>> + at::Tensor & adaptive_avg_pool2d_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, at::Tensor & out) { + return at::_ops::adaptive_avg_pool2d_out::call(self, output_size, out); + } +} + +// aten::adaptive_avg_pool2d(Tensor self, SymInt[2] output_size) -> Tensor +inline at::Tensor adaptive_avg_pool2d(const at::Tensor & self, at::IntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d::call(self, c10::fromIntArrayRefSlow(output_size)); +} +namespace symint { + template ::value>> + at::Tensor adaptive_avg_pool2d(const at::Tensor & self, at::IntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d::call(self, c10::fromIntArrayRefSlow(output_size)); + } +} + +// aten::adaptive_avg_pool2d(Tensor self, SymInt[2] output_size) -> Tensor +inline at::Tensor adaptive_avg_pool2d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d::call(self, output_size); +} +namespace symint { + template ::value>> + at::Tensor adaptive_avg_pool2d(const at::Tensor & self, c10::SymIntArrayRef output_size) { + return at::_ops::adaptive_avg_pool2d::call(self, output_size); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool3d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool3d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c0fbf736ce6ee0d45daa5bb2f5ef13161eadbd0a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool3d_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 adaptive_avg_pool3d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size); +TORCH_API at::Tensor & adaptive_avg_pool3d_out_cpu(const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out); +TORCH_API at::Tensor & adaptive_avg_pool3d_out_cuda(const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out); +TORCH_API at::Tensor & adaptive_avg_pool3d_out_quantized_cpu(const at::Tensor & self, at::IntArrayRef output_size, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/allclose_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/allclose_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cdf19a48de854e67197387681749d9121174e44c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/allclose_compositeexplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API bool allclose(const at::Tensor & self, const at::Tensor & other, double rtol=1e-05, double atol=1e-08, bool equal_nan=false); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/and_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/and_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..0eee8491cf475d2abe798a5c091cbb5a180b6ac1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/and_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 __and___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::__and__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__and__.Scalar(Tensor self, Scalar other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API __and___Tensor { + using schema = at::Tensor (const 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::__and__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__and__.Tensor(Tensor self, Tensor other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other); +}; + +struct TORCH_API __iand___Scalar { + using schema = at::Tensor & (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::__iand__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__iand__.Scalar(Tensor(a!) self, Scalar other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Scalar & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API __iand___Tensor { + using schema = at::Tensor & (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::__iand__") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "__iand__.Tensor(Tensor(a!) self, Tensor other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Tensor & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Tensor & other); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/angle.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/angle.h new file mode 100644 index 0000000000000000000000000000000000000000..cdabb6835b60e569db680903e41df05286861cbf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/angle.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::angle(Tensor self) -> Tensor +inline at::Tensor angle(const at::Tensor & self) { + return at::_ops::angle::call(self); +} + +// aten::angle.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & angle_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::angle_out::call(self, out); +} +// aten::angle.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & angle_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::angle_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/as_strided_scatter_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/as_strided_scatter_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b8231436159ad9ab4fd8420175adb12e67a27cf2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/as_strided_scatter_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 & as_strided_scatter_out_symint(const at::Tensor & self, const at::Tensor & src, c10::SymIntArrayRef size, c10::SymIntArrayRef stride, c10::optional storage_offset, at::Tensor & out); +TORCH_API at::Tensor as_strided_scatter_symint(const at::Tensor & self, const at::Tensor & src, c10::SymIntArrayRef size, c10::SymIntArrayRef stride, c10::optional storage_offset=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bartlett_window_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bartlett_window_native.h new file mode 100644 index 0000000000000000000000000000000000000000..badf1f7b0b650ee78ab27aa20a0e1afcff49251c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bartlett_window_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 bartlett_window(int64_t window_length, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +TORCH_API at::Tensor & bartlett_window_out(int64_t window_length, at::Tensor & out); +TORCH_API at::Tensor bartlett_window(int64_t window_length, bool periodic, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +TORCH_API at::Tensor & bartlett_window_periodic_out(int64_t window_length, bool periodic, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_right_shift_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_right_shift_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7b88ef6ab663c0b9525ce6db84f95609bbcb587f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_right_shift_meta_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor bitwise_right_shift(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_right_shift_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_right_shift_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & bitwise_right_shift_(at::Tensor & self, const at::Tensor & other); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/concatenate_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/concatenate_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..396d7ce2b976abcc67f9ed78c4c9beb5ea16ab59 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/concatenate_compositeimplicitautograd_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 compositeimplicitautograd { + +TORCH_API at::Tensor concatenate(at::TensorList tensors, int64_t dim=0); +TORCH_API at::Tensor & concatenate_out(at::Tensor & out, at::TensorList tensors, int64_t dim=0); +TORCH_API at::Tensor & concatenate_outf(at::TensorList tensors, int64_t dim, at::Tensor & out); +TORCH_API at::Tensor concatenate(at::TensorList tensors, at::Dimname dim); +TORCH_API at::Tensor & concatenate_out(at::Tensor & out, at::TensorList tensors, at::Dimname dim); +TORCH_API at::Tensor & concatenate_outf(at::TensorList tensors, at::Dimname dim, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/data_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/data_native.h new file mode 100644 index 0000000000000000000000000000000000000000..02c8430efe7bc377cf72c3ebff92d7dcb3456929 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/data_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 data(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..869f138b1194711cbb7599d97d2900b5daaa7239 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API diagonal_backward { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, int64_t, int64_t, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::diagonal_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "diagonal_backward(Tensor grad_output, SymInt[] input_sizes, int offset, int dim1, int dim2) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2); +}; + +struct TORCH_API diagonal_backward_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, int64_t, int64_t, int64_t, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::diagonal_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "diagonal_backward.out(Tensor grad_output, SymInt[] input_sizes, int offset, int dim1, int dim2, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t offset, int64_t dim1, int64_t dim2, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0ff6b74ff5324aee3b16ba2f3c5704971b07be2a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/diagonal_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 diagonal(const at::Tensor & self, at::Dimname outdim, at::Dimname dim1, at::Dimname dim2, int64_t offset=0); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/erfc_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/erfc_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..b028371fb9fbc97389199ee2442abf3fe92e22f3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/erfc_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_erfc : 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/full_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/full_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5a8a5a06a78573884dc4de447a89bde23b3d63ec --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/full_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 full_names { + using schema = at::Tensor (at::IntArrayRef, const at::Scalar &, 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::full") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "full.names(int[] size, Scalar fill_value, *, Dimname[]? names, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(at::IntArrayRef size, const at::Scalar & fill_value, c10::optional names, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, at::IntArrayRef size, const at::Scalar & fill_value, c10::optional names, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API full { + using schema = at::Tensor (c10::SymIntArrayRef, const at::Scalar &, 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::full") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "full(SymInt[] size, Scalar fill_value, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(c10::SymIntArrayRef size, const at::Scalar & fill_value, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, c10::SymIntArrayRef size, const at::Scalar & fill_value, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API full_out { + using schema = at::Tensor & (c10::SymIntArrayRef, 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::full") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "full.out(SymInt[] size, Scalar fill_value, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(c10::SymIntArrayRef size, const at::Scalar & fill_value, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, c10::SymIntArrayRef size, const at::Scalar & fill_value, at::Tensor & out); +}; + +struct TORCH_API full_names_out { + using schema = at::Tensor & (at::IntArrayRef, const at::Scalar &, 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::full") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "full.names_out(int[] size, Scalar fill_value, *, Dimname[]? names, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(at::IntArrayRef size, const at::Scalar & fill_value, c10::optional names, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::IntArrayRef size, const at::Scalar & fill_value, c10::optional names, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler.h new file mode 100644 index 0000000000000000000000000000000000000000..0309d3f821a7d79ef361a514edaa13c68c792e8e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler.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::grid_sampler(Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners) -> Tensor +inline at::Tensor grid_sampler(const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners) { + return at::_ops::grid_sampler::call(input, grid, interpolation_mode, padding_mode, align_corners); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_2d_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_2d_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..08a081cf3e29cec098d535a1f8564cb092fd79e9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_2d_backward_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 ::std::tuple grid_sampler_2d_backward_out(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1); +TORCH_API ::std::tuple grid_sampler_2d_backward_cpu(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask); +TORCH_API ::std::tuple grid_sampler_2d_backward_cuda(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..343023d64d5d21d7536eef5954d62fd9a0240a35 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::tuple grid_sampler_3d_backward(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogram_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogram_native.h new file mode 100644 index 0000000000000000000000000000000000000000..71fbf4fa8a2ad04a91610a07eadd13c0d760da59 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/histogram_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::tuple histogram(const at::Tensor & self, const at::Tensor & bins, const c10::optional & weight={}, bool density=false); +TORCH_API ::std::tuple histogram_out(const at::Tensor & self, const at::Tensor & bins, const c10::optional & weight, bool density, at::Tensor & hist, at::Tensor & bin_edges); +TORCH_API ::std::tuple histogram(const at::Tensor & self, int64_t bins=100, c10::optional> range=c10::nullopt, const c10::optional & weight={}, bool density=false); +TORCH_API ::std::tuple histogram_out(const at::Tensor & self, int64_t bins, c10::optional> range, const c10::optional & weight, bool density, at::Tensor & hist, at::Tensor & bin_edges); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..d4b18b30cfb9ac685a4191037147f0442d499044 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_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 instance_norm { + using schema = at::Tensor (const at::Tensor &, const c10::optional &, const c10::optional &, const c10::optional &, const c10::optional &, bool, double, double, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::instance_norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "instance_norm(Tensor input, Tensor? weight, Tensor? bias, Tensor? running_mean, Tensor? running_var, bool use_input_stats, float momentum, float eps, bool cudnn_enabled) -> Tensor") + static at::Tensor call(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const c10::optional & running_mean, const c10::optional & running_var, bool use_input_stats, double momentum, double eps, bool cudnn_enabled); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const c10::optional & running_mean, const c10::optional & running_var, bool use_input_stats, double momentum, double eps, bool cudnn_enabled); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_nonzero_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_nonzero_native.h new file mode 100644 index 0000000000000000000000000000000000000000..4aa71bb97dee0b3a15c86c3638ecd8c5ce03dd79 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_nonzero_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 bool is_nonzero(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_vulkan_available_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_vulkan_available_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..07ed34586debb6dca3a0d3189a87b75e69491707 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_vulkan_available_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_vulkan_available { + using schema = bool (); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::is_vulkan_available") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "is_vulkan_available() -> bool") + static bool call(); + static bool redispatch(c10::DispatchKeySet dispatchKeySet); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/layer_norm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/layer_norm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..98d4969d1c6390edbda9382a74414df84b523539 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/layer_norm_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 layer_norm { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, const c10::optional &, const c10::optional &, double, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::layer_norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "layer_norm(Tensor input, SymInt[] normalized_shape, Tensor? weight=None, Tensor? bias=None, float eps=1e-05, bool cudnn_enable=True) -> Tensor") + static at::Tensor call(const at::Tensor & input, c10::SymIntArrayRef normalized_shape, const c10::optional & weight, const c10::optional & bias, double eps, bool cudnn_enable); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, c10::SymIntArrayRef normalized_shape, const c10::optional & weight, const c10::optional & bias, double eps, bool cudnn_enable); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4444ea869374a42f7347c6a30ef6509177313fd6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lerp_cuda_dispatch.h @@ -0,0 +1,30 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor lerp(const at::Tensor & self, const at::Tensor & end, const at::Scalar & weight); +TORCH_API at::Tensor & lerp_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & end, const at::Scalar & weight); +TORCH_API at::Tensor & lerp_outf(const at::Tensor & self, const at::Tensor & end, const at::Scalar & weight, at::Tensor & out); +TORCH_API at::Tensor & lerp_(at::Tensor & self, const at::Tensor & end, const at::Scalar & weight); +TORCH_API at::Tensor lerp(const at::Tensor & self, const at::Tensor & end, const at::Tensor & weight); +TORCH_API at::Tensor & lerp_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & end, const at::Tensor & weight); +TORCH_API at::Tensor & lerp_outf(const at::Tensor & self, const at::Tensor & end, const at::Tensor & weight, at::Tensor & out); +TORCH_API at::Tensor & lerp_(at::Tensor & self, const at::Tensor & end, const at::Tensor & weight); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cholesky_ex_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cholesky_ex_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..597eb6e7ceacf69e44ecb822adb50311ae0c1d7b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cholesky_ex_cpu_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 cpu { + +TORCH_API ::std::tuple linalg_cholesky_ex(const at::Tensor & self, bool upper=false, bool check_errors=false); +TORCH_API ::std::tuple linalg_cholesky_ex_out(at::Tensor & L, at::Tensor & info, const at::Tensor & self, bool upper=false, bool check_errors=false); +TORCH_API ::std::tuple linalg_cholesky_ex_outf(const at::Tensor & self, bool upper, bool check_errors, at::Tensor & L, at::Tensor & info); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigh_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigh_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..00ee1cf75f0bf9d2d4357eed26def19470dc8f38 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigh_compositeimplicitautograd_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 compositeimplicitautograd { + +TORCH_API ::std::tuple linalg_eigh(const at::Tensor & self, c10::string_view UPLO="L"); +TORCH_API ::std::tuple linalg_eigh_out(at::Tensor & eigvals, at::Tensor & eigvecs, const at::Tensor & self, c10::string_view UPLO="L"); +TORCH_API ::std::tuple linalg_eigh_outf(const at::Tensor & self, c10::string_view UPLO, at::Tensor & eigvals, at::Tensor & eigvecs); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_solve_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_solve_native.h new file mode 100644 index 0000000000000000000000000000000000000000..4e4195c83ac435051d55bf92aa4880bbf801ff50 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_solve_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_linalg_ldl_solve_out : public at::meta::structured_linalg_ldl_solve { +void impl(const at::Tensor & LD, const at::Tensor & pivots, const at::Tensor & B, bool hermitian, 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_lu_factor_ex_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_ex_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f1386c061174e068cc35eb79d540532a9d4c6c6e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_ex_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::tuple linalg_lu_factor_ex(const at::Tensor & A, bool pivot=true, bool check_errors=false); +TORCH_API ::std::tuple linalg_lu_factor_ex_out(at::Tensor & LU, at::Tensor & pivots, at::Tensor & info, const at::Tensor & A, bool pivot=true, bool check_errors=false); +TORCH_API ::std::tuple linalg_lu_factor_ex_outf(const at::Tensor & A, bool pivot, bool check_errors, at::Tensor & LU, at::Tensor & pivots, at::Tensor & info); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..ca856a13fe23a3e381bce9aa16b07a581827a20a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_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 linalg_lu_factor { + using schema = ::std::tuple (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::linalg_lu_factor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_lu_factor(Tensor A, *, bool pivot=True) -> (Tensor LU, Tensor pivots)") + static ::std::tuple call(const at::Tensor & A, bool pivot); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & A, bool pivot); +}; + +struct TORCH_API linalg_lu_factor_out { + using schema = ::std::tuple (const at::Tensor &, bool, 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::linalg_lu_factor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_lu_factor.out(Tensor A, *, bool pivot=True, Tensor(a!) LU, Tensor(b!) pivots) -> (Tensor(a!) LU, Tensor(b!) pivots)") + static ::std::tuple call(const at::Tensor & A, bool pivot, at::Tensor & LU, at::Tensor & pivots); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & A, bool pivot, at::Tensor & LU, at::Tensor & pivots); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vector_norm_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vector_norm_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c20a43b2364f687ba688e9147d36a0aaacf63c60 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vector_norm_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 linalg_vector_norm(const at::Tensor & self, const at::Scalar & ord=2, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logspace_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logspace_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..c05ebcdf235d50a4493927b212cfd460fbce5d89 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logspace_ops.h @@ -0,0 +1,105 @@ +#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 logspace { + using schema = at::Tensor (const at::Scalar &, const at::Scalar &, int64_t, double, 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::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace(Scalar start, Scalar end, int steps, float base=10.0, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(const at::Scalar & start, const at::Scalar & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & start, const at::Scalar & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API logspace_Tensor_Tensor { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, int64_t, double, 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::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace.Tensor_Tensor(Tensor start, Tensor end, int steps, float base=10.0, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(const at::Tensor & start, const at::Tensor & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & start, const at::Tensor & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API logspace_Tensor_Scalar { + using schema = at::Tensor (const at::Tensor &, const at::Scalar &, int64_t, double, 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::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace.Tensor_Scalar(Tensor start, Scalar end, int steps, float base=10.0, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(const at::Tensor & start, const at::Scalar & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & start, const at::Scalar & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API logspace_Scalar_Tensor { + using schema = at::Tensor (const at::Scalar &, const at::Tensor &, int64_t, double, 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::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace.Scalar_Tensor(Scalar start, Tensor end, int steps, float base=10.0, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor") + static at::Tensor call(const at::Scalar & start, const at::Tensor & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & start, const at::Tensor & end, int64_t steps, double base, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +}; + +struct TORCH_API logspace_out { + using schema = at::Tensor & (const at::Scalar &, const at::Scalar &, int64_t, double, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace.out(Scalar start, Scalar end, int steps, float base=10.0, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Scalar & start, const at::Scalar & end, int64_t steps, double base, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & start, const at::Scalar & end, int64_t steps, double base, at::Tensor & out); +}; + +struct TORCH_API logspace_Tensor_Tensor_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, int64_t, double, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace.Tensor_Tensor_out(Tensor start, Tensor end, int steps, float base=10.0, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & start, const at::Tensor & end, int64_t steps, double base, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & start, const at::Tensor & end, int64_t steps, double base, at::Tensor & out); +}; + +struct TORCH_API logspace_Tensor_Scalar_out { + using schema = at::Tensor & (const at::Tensor &, const at::Scalar &, int64_t, double, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_Scalar_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace.Tensor_Scalar_out(Tensor start, Scalar end, int steps, float base=10.0, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & start, const at::Scalar & end, int64_t steps, double base, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & start, const at::Scalar & end, int64_t steps, double base, at::Tensor & out); +}; + +struct TORCH_API logspace_Scalar_Tensor_out { + using schema = at::Tensor & (const at::Scalar &, const at::Tensor &, int64_t, double, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::logspace") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "logspace.Scalar_Tensor_out(Scalar start, Tensor end, int steps, float base=10.0, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Scalar & start, const at::Tensor & end, int64_t steps, double base, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & start, const at::Tensor & end, int64_t steps, double base, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lshift.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lshift.h new file mode 100644 index 0000000000000000000000000000000000000000..4ab063a59e7eaadcbe5ce5c52fff3360f76a5cf5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lshift.h @@ -0,0 +1,53 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::__lshift__.Scalar(Tensor self, Scalar other) -> Tensor +inline at::Tensor __lshift__(const at::Tensor & self, const at::Scalar & other) { + return at::_ops::__lshift___Scalar::call(self, other); +} + +// aten::__lshift__.Tensor(Tensor self, Tensor other) -> Tensor +inline at::Tensor __lshift__(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::__lshift___Tensor::call(self, other); +} + +// aten::__lshift__.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & __lshift___out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other) { + return at::_ops::__lshift___Scalar_out::call(self, other, out); +} +// aten::__lshift__.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & __lshift___outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out) { + return at::_ops::__lshift___Scalar_out::call(self, other, out); +} + +// aten::__lshift__.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & __lshift___out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::__lshift___Tensor_out::call(self, other, out); +} +// aten::__lshift__.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & __lshift___outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::__lshift___Tensor_out::call(self, other, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a9a642218aaff628ab37261d9493ddd607d36e28 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lstm_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 ::std::tuple lstm(const at::Tensor & input, at::TensorList hx, at::TensorList params, bool has_biases, int64_t num_layers, double dropout, bool train, bool bidirectional, bool batch_first); +TORCH_API ::std::tuple lstm(const at::Tensor & data, const at::Tensor & batch_sizes, at::TensorList hx, at::TensorList params, bool has_biases, int64_t num_layers, double dropout, bool train, bool bidirectional); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..979c887268865659ac2e1833c9711b8cd1794954 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_meta.h @@ -0,0 +1,39 @@ +#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_max_dim : public at::impl::MetaBase { + + template + struct TORCH_API precompute_out { + + precompute_out set_dim(int64_t value) { + static_assert(DIM == false, "dim already set"); + precompute_out ret; +ret.dim = value; +return ret; + } + + int64_t dim; + }; + using meta_return_ty = precompute_out ; + meta_return_ty meta(const at::Tensor & self, int64_t dim, bool keepdim); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f5ccf388e5c9806a4babb04273bab8c65a836607 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_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 at::Tensor max_unpool3d(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API at::Tensor max_unpool3d_symint(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API 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); +TORCH_API 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); +TORCH_API 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); +TORCH_API 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); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/minimum_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/minimum_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..6bba249cec6f5b699071724076bb0666935fda48 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/minimum_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 minimum { + using schema = at::Tensor (const 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::minimum") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "minimum(Tensor self, Tensor other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other); +}; + +struct TORCH_API minimum_out { + using schema = at::Tensor & (const 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::minimum") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "minimum.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_convolution_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_convolution_native.h new file mode 100644 index 0000000000000000000000000000000000000000..1a159a2629d96c3758024dd20a8d4328b1d4d94d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/miopen_convolution_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 & miopen_convolution_out_symint(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, bool benchmark, bool deterministic, at::Tensor & out); +TORCH_API at::Tensor miopen_convolution(const at::Tensor & self, const at::Tensor & weight, const c10::optional & bias, at::IntArrayRef padding, at::IntArrayRef stride, at::IntArrayRef dilation, int64_t groups, bool benchmark, bool deterministic); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mish_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mish_native.h new file mode 100644 index 0000000000000000000000000000000000000000..eaa436bfbcd5658131655b4de497cfc5c35734fa --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mish_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_mish_out : public at::meta::structured_mish { +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/mode_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mode_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..53021626912e8a87044af031ffeaec02e6e69037 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mode_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 mode_out(at::Tensor & values, at::Tensor & indices, const at::Tensor & self, int64_t dim=-1, bool keepdim=false); +TORCH_API ::std::tuple mode_outf(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & values, at::Tensor & indices); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/normal_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/normal_native.h new file mode 100644 index 0000000000000000000000000000000000000000..003ec71f62360b5a1e24f28ee7b34adbca164db6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/normal_native.h @@ -0,0 +1,40 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor normal_functional(const at::Tensor & self, double mean=0, double std=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_out(const at::Tensor & self, double mean, double std, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor & normal_(at::Tensor & self, double mean=0, double std=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_nested_(at::Tensor & self, double mean=0, double std=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_sparse_csr_(at::Tensor & self, double mean=0, double std=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_meta_(at::Tensor & self, double mean=0, double std=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor normal(const at::Tensor & mean, double std=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_out(const at::Tensor & mean, double std, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor normal_meta(const at::Tensor & mean, double std=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_out_meta(const at::Tensor & mean, double std, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor normal(double mean, const at::Tensor & std, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_out(double mean, const at::Tensor & std, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor normal_meta(double mean, const at::Tensor & std, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_out_meta(double mean, const at::Tensor & std, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor normal(const at::Tensor & mean, const at::Tensor & std, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_out(const at::Tensor & mean, const at::Tensor & std, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor normal_meta(const at::Tensor & mean, const at::Tensor & std, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & normal_out_meta(const at::Tensor & mean, const at::Tensor & std, c10::optional generator, at::Tensor & out); +TORCH_API at::Tensor normal(double mean, double std, at::IntArrayRef size, c10::optional generator=c10::nullopt, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +TORCH_API at::Tensor & normal_out(double mean, double std, at::IntArrayRef size, c10::optional generator, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/not_equal_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/not_equal_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..74d33fc47c6855b17860fba79d80ea6bceaa95f7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/not_equal_ops.h @@ -0,0 +1,83 @@ +#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 not_equal_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::not_equal") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "not_equal.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +}; + +struct TORCH_API not_equal_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::not_equal") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "not_equal.Scalar(Tensor self, Scalar other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API not_equal_Tensor_out { + using schema = at::Tensor & (const 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::not_equal") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "not_equal.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +}; + +struct TORCH_API not_equal_Tensor { + using schema = at::Tensor (const 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::not_equal") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "not_equal.Tensor(Tensor self, Tensor other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other); +}; + +struct TORCH_API not_equal__Scalar { + using schema = at::Tensor & (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::not_equal_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "not_equal_.Scalar(Tensor(a!) self, Scalar other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Scalar & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API not_equal__Tensor { + using schema = at::Tensor & (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::not_equal_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "not_equal_.Tensor(Tensor(a!) self, Tensor other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Tensor & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Tensor & other); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/range_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/range_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..77e98257def78cb0657b1ae6ede7e8c08b0a3c5c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/range_meta_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 meta { + +TORCH_API at::Tensor & range_out(at::Tensor & out, const at::Scalar & start, const at::Scalar & end, const at::Scalar & step); +TORCH_API at::Tensor & range_outf(const at::Scalar & start, const at::Scalar & end, const at::Scalar & step, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad2d_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad2d_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..16a5b8377df319a25a29307b8d878b97dd1aa1af --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad2d_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API reflection_pad2d_backward_grad_input { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::reflection_pad2d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "reflection_pad2d_backward.grad_input(Tensor grad_output, Tensor self, SymInt[4] padding, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding, at::Tensor & grad_input); +}; + +struct TORCH_API reflection_pad2d_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::reflection_pad2d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "reflection_pad2d_backward(Tensor grad_output, Tensor self, SymInt[4] padding) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_add_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_add_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3ddab01670d0799bb3b858b056f1d39cfe855759 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/scatter_add_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 scatter_add(const at::Tensor & self, at::Dimname dim, const at::Tensor & index, const at::Tensor & src); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f58ebc53bc74b0ce6739cf925d4c4ffe578d32dd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_meta_dispatch.h @@ -0,0 +1,27 @@ +#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 & set_(at::Tensor & self, at::Storage source); +TORCH_API at::Tensor & set_(at::Tensor & self, at::Storage source, int64_t storage_offset, at::IntArrayRef size, at::IntArrayRef stride={}); +TORCH_API at::Tensor & set__symint(at::Tensor & self, at::Storage source, c10::SymInt storage_offset, c10::SymIntArrayRef size, c10::SymIntArrayRef stride={}); +TORCH_API at::Tensor & set_(at::Tensor & self, const at::Tensor & source); +TORCH_API at::Tensor & set_(at::Tensor & self); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..e290400adfda920d65a7dce32b06700144766610 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward.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::silu_backward.grad_input(Tensor grad_output, Tensor self, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & silu_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self) { + return at::_ops::silu_backward_grad_input::call(grad_output, self, grad_input); +} +// aten::silu_backward.grad_input(Tensor grad_output, Tensor self, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & silu_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input) { + return at::_ops::silu_backward_grad_input::call(grad_output, self, grad_input); +} + +// aten::silu_backward(Tensor grad_output, Tensor self) -> Tensor +inline at::Tensor silu_backward(const at::Tensor & grad_output, const at::Tensor & self) { + return at::_ops::silu_backward::call(grad_output, self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinc_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinc_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..fb29448070f8236a7714864cb707b6b254475943 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinc_meta_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor sinc(const at::Tensor & self); +TORCH_API at::Tensor & sinc_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & sinc_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & sinc_(at::Tensor & self); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/soft_margin_loss_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/soft_margin_loss_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..109d354ac1566e67be6ece483d7fe65fee9de58e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/soft_margin_loss_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 soft_margin_loss_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, int64_t, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::soft_margin_loss") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "soft_margin_loss.out(Tensor self, Tensor target, int reduction=Mean, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & target, int64_t reduction, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & target, int64_t reduction, at::Tensor & out); +}; + +struct TORCH_API soft_margin_loss { + using schema = 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::soft_margin_loss") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "soft_margin_loss(Tensor self, Tensor target, int reduction=Mean) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & target, int64_t reduction); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & target, int64_t reduction); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sort_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sort_native.h new file mode 100644 index 0000000000000000000000000000000000000000..9a9165fbbea7fe6e036e4d5ff742f6d2117aed47 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sort_native.h @@ -0,0 +1,30 @@ +#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 ::std::tuple sort(const at::Tensor & self, int64_t dim=-1, bool descending=false); +TORCH_API ::std::tuple sort_out(const at::Tensor & self, int64_t dim, bool descending, at::Tensor & values, at::Tensor & indices); +struct TORCH_API structured_sort_stable_out : public at::meta::structured_sort_stable { +void impl(const at::Tensor & self, c10::optional stable, int64_t dim, bool descending, const at::Tensor & values, const at::Tensor & indices); +}; +TORCH_API ::std::tuple sort_quantized_cpu_stable(const at::Tensor & self, c10::optional stable, int64_t dim=-1, bool descending=false); +TORCH_API ::std::tuple sort(const at::Tensor & self, at::Dimname dim, bool descending=false); +TORCH_API ::std::tuple sort_out(const at::Tensor & self, at::Dimname dim, bool descending, at::Tensor & values, at::Tensor & indices); +TORCH_API ::std::tuple sort(const at::Tensor & self, c10::optional stable, at::Dimname dim, bool descending=false); +TORCH_API ::std::tuple sort_out(const at::Tensor & self, c10::optional stable, at::Dimname dim, bool descending, at::Tensor & values, at::Tensor & indices); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_coo_tensor_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_coo_tensor_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cf974e1e223a6d7fca1209094ae140e718491dc2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sparse_coo_tensor_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 sparse_coo_tensor(at::IntArrayRef size, at::TensorOptions options); +TORCH_API at::Tensor sparse_coo_tensor(at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory); +TORCH_API at::Tensor & sparse_coo_tensor_out(at::Tensor & out, at::IntArrayRef size); +TORCH_API at::Tensor & sparse_coo_tensor_outf(at::IntArrayRef size, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2bcaadf8490c1aadefeafde40f9342965646e76e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_bessel_j0_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 special_bessel_j0(const at::Tensor & self); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..285bf9da62f17d1404681e45e4c2dba3d071bf46 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_v_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 special_chebyshev_polynomial_v(const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_out(at::Tensor & out, const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_outf(const at::Scalar & x, const at::Tensor & n, at::Tensor & out); +TORCH_API at::Tensor special_chebyshev_polynomial_v(const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_out(at::Tensor & out, const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_v_outf(const at::Tensor & x, const at::Scalar & n, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_h_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_h_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..434fb83fb492f190c4ba85b19f44c19f69ad1433 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_h_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 special_hermite_polynomial_h(const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_hermite_polynomial_h_out(at::Tensor & out, const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_hermite_polynomial_h_outf(const at::Scalar & x, const at::Tensor & n, at::Tensor & out); +TORCH_API at::Tensor special_hermite_polynomial_h(const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_hermite_polynomial_h_out(at::Tensor & out, const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_hermite_polynomial_h_outf(const at::Tensor & x, const at::Scalar & n, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_legendre_polynomial_p_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_legendre_polynomial_p_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..79db3964d4cc831551a4f44a00a07493b2a66881 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_legendre_polynomial_p_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor special_legendre_polynomial_p(const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_legendre_polynomial_p_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_legendre_polynomial_p_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e169b04ca6da38adaee1311f5dac61e8777b529d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor special_spherical_bessel_j0(const at::Tensor & x); +TORCH_API at::Tensor & special_spherical_bessel_j0_out(at::Tensor & out, const at::Tensor & x); +TORCH_API at::Tensor & special_spherical_bessel_j0_outf(const at::Tensor & x, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/split.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/split.h new file mode 100644 index 0000000000000000000000000000000000000000..887106b0d5f56ed39bb0ee1ee92f76768d56dbc0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/split.h @@ -0,0 +1,69 @@ +#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::split.Tensor(Tensor(a -> *) self, SymInt split_size, int dim=0) -> Tensor(a)[] +inline ::std::vector split(const at::Tensor & self, int64_t split_size, int64_t dim=0) { + return at::_ops::split_Tensor::call(self, split_size, dim); +} +namespace symint { + template ::value>> + ::std::vector split(const at::Tensor & self, int64_t split_size, int64_t dim=0) { + return at::_ops::split_Tensor::call(self, split_size, dim); + } +} + +// aten::split.Tensor(Tensor(a -> *) self, SymInt split_size, int dim=0) -> Tensor(a)[] +inline ::std::vector split_symint(const at::Tensor & self, c10::SymInt split_size, int64_t dim=0) { + return at::_ops::split_Tensor::call(self, split_size, dim); +} +namespace symint { + template ::value>> + ::std::vector split(const at::Tensor & self, c10::SymInt split_size, int64_t dim=0) { + return at::_ops::split_Tensor::call(self, split_size, dim); + } +} + +// aten::split.sizes(Tensor(a -> *) self, SymInt[] split_size, int dim=0) -> Tensor(a)[] +inline ::std::vector split(const at::Tensor & self, at::IntArrayRef split_size, int64_t dim=0) { + return at::_ops::split_sizes::call(self, c10::fromIntArrayRefSlow(split_size), dim); +} +namespace symint { + template ::value>> + ::std::vector split(const at::Tensor & self, at::IntArrayRef split_size, int64_t dim=0) { + return at::_ops::split_sizes::call(self, c10::fromIntArrayRefSlow(split_size), dim); + } +} + +// aten::split.sizes(Tensor(a -> *) self, SymInt[] split_size, int dim=0) -> Tensor(a)[] +inline ::std::vector split_symint(const at::Tensor & self, c10::SymIntArrayRef split_size, int64_t dim=0) { + return at::_ops::split_sizes::call(self, split_size, dim); +} +namespace symint { + template ::value>> + ::std::vector split(const at::Tensor & self, c10::SymIntArrayRef split_size, int64_t dim=0) { + return at::_ops::split_sizes::call(self, split_size, dim); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/stft_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/stft_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..bc89fd02c6ff051fd2d00c5e1a2df0104b3f5d47 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/stft_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 stft { + using schema = at::Tensor (const at::Tensor &, int64_t, c10::optional, c10::optional, const c10::optional &, bool, 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::stft") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "stft(Tensor self, int n_fft, int? hop_length=None, int? win_length=None, Tensor? window=None, bool normalized=False, bool? onesided=None, bool? return_complex=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, int64_t n_fft, c10::optional hop_length, c10::optional win_length, const c10::optional & window, bool normalized, c10::optional onesided, c10::optional return_complex); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t n_fft, c10::optional hop_length, c10::optional win_length, const c10::optional & window, bool normalized, c10::optional onesided, c10::optional return_complex); +}; + +struct TORCH_API stft_center { + using schema = at::Tensor (const at::Tensor &, int64_t, c10::optional, c10::optional, const c10::optional &, bool, c10::string_view, bool, 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::stft") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "center") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "stft.center(Tensor self, int n_fft, int? hop_length=None, int? win_length=None, Tensor? window=None, bool center=True, str pad_mode=\"reflect\", bool normalized=False, bool? onesided=None, bool? return_complex=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, int64_t n_fft, c10::optional hop_length, c10::optional win_length, const c10::optional & window, bool center, c10::string_view pad_mode, bool normalized, c10::optional onesided, c10::optional return_complex); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t n_fft, c10::optional hop_length, c10::optional win_length, const c10::optional & window, bool center, c10::string_view pad_mode, bool normalized, c10::optional onesided, c10::optional return_complex); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tile_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tile_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..6250051a85f66bca949f5fec9ac975f20724910c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tile_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 tile { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::tile") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "tile(Tensor self, SymInt[] dims) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef dims); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef dims); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d5426688910e880db1a6f7104a8be9b52abf0b5a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/to_dense_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 to_dense_backward(const at::Tensor & grad, const at::Tensor & input, c10::optional masked_grad=c10::nullopt); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..79ef868b9e7808ad0c0a83e9dc210cdf1d39c8ed --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_cuda_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor unfold(const at::Tensor & self, int64_t dimension, int64_t size, int64_t step); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..8384a56e8c98bfa30107659257cb814b68dbb82e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_real_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 view_as_real { + 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::view_as_real") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "view_as_real(Tensor(a) self) -> Tensor(a)") + 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/xlogy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xlogy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..ca01874bf8e98da0aa9555bef423f950cf15746c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/xlogy_ops.h @@ -0,0 +1,105 @@ +#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 xlogy_Tensor { + using schema = at::Tensor (const 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::xlogy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy.Tensor(Tensor self, Tensor other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other); +}; + +struct TORCH_API xlogy_Scalar_Self { + using schema = at::Tensor (const at::Scalar &, 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::xlogy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Self") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy.Scalar_Self(Scalar self, Tensor other) -> Tensor") + static at::Tensor call(const at::Scalar & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & self, const at::Tensor & other); +}; + +struct TORCH_API xlogy_Scalar_Other { + 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::xlogy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Other") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy.Scalar_Other(Tensor self, Scalar other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API xlogy__Tensor { + using schema = at::Tensor & (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::xlogy_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy_.Tensor(Tensor(a!) self, Tensor other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Tensor & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Tensor & other); +}; + +struct TORCH_API xlogy__Scalar_Other { + using schema = at::Tensor & (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::xlogy_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Other") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy_.Scalar_Other(Tensor(a!) self, Scalar other) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, const at::Scalar & other); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, const at::Scalar & other); +}; + +struct TORCH_API xlogy_OutTensor { + using schema = at::Tensor & (const 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::xlogy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "OutTensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy.OutTensor(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +}; + +struct TORCH_API xlogy_OutScalar_Self { + using schema = at::Tensor & (const at::Scalar &, 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::xlogy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "OutScalar_Self") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy.OutScalar_Self(Scalar self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Scalar & self, const at::Tensor & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & self, const at::Tensor & other, at::Tensor & out); +}; + +struct TORCH_API xlogy_OutScalar_Other { + 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::xlogy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "OutScalar_Other") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "xlogy.OutScalar_Other(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +}; + +}} // namespace at::_ops