diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_add_batch_dim_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_add_batch_dim_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..a86ea943ffbbf2081b18aaf6a6e639e73e869d12 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_add_batch_dim_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 _add_batch_dim { + using schema = at::Tensor (const at::Tensor &, int64_t, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_add_batch_dim") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_add_batch_dim(Tensor self, int batch_dim, int level) -> Tensor") + static at::Tensor call(const at::Tensor & self, int64_t batch_dim, int64_t level); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t batch_dim, int64_t level); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Char.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Char.h new file mode 100644 index 0000000000000000000000000000000000000000..01fc2e40b9996c6694e7297d6d5c6dcff9ee02b9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Char.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_Char(Tensor self, bool non_blocking=False) -> Tensor +inline at::Tensor _cast_Char(const at::Tensor & self, bool non_blocking=false) { + return at::_ops::_cast_Char::call(self, non_blocking); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Int_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Int_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..51c1bb0907985a1c71c9812d89609d69a10c5bb4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Int_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 _cast_Int(const at::Tensor & self, bool non_blocking=false); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_coalesced_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_coalesced_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..0cbc36d94773262cb4a84a8e66d73cc9bb6f16e6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_coalesced_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _coalesced_ { + using schema = at::Tensor & (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::_coalesced_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_coalesced_(Tensor(a!) self, bool coalesced) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, bool coalesced); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, bool coalesced); +}; + +struct TORCH_API _coalesced_out { + using schema = at::Tensor & (const at::Tensor &, bool, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_coalesced") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_coalesced.out(Tensor self, bool coalesced, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, bool coalesced, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool coalesced, at::Tensor & out); +}; + +struct TORCH_API _coalesced { + using schema = at::Tensor (const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_coalesced") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_coalesced(Tensor self, bool coalesced) -> Tensor") + static at::Tensor call(const at::Tensor & self, bool coalesced); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool coalesced); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_copy.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_copy.h new file mode 100644 index 0000000000000000000000000000000000000000..b4190997b44bd9dccf8a70704ed201bc9690d0b1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_conj_copy.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_conj_copy(Tensor self) -> Tensor +inline at::Tensor _conj_copy(const at::Tensor & self) { + return at::_ops::_conj_copy::call(self); +} + +// aten::_conj_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _conj_copy_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::_conj_copy_out::call(self, out); +} +// aten::_conj_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _conj_copy_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::_conj_copy_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_copy_from_and_resize_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_copy_from_and_resize_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..173a0558a04211badc4213b7f1cce5d96cb5d48c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_copy_from_and_resize_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _copy_from_and_resize { + 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::_copy_from_and_resize") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_copy_from_and_resize(Tensor self, Tensor dst) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & dst); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & dst); +}; + +struct TORCH_API _copy_from_and_resize_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::_copy_from_and_resize") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_copy_from_and_resize.out(Tensor self, Tensor dst, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & dst, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & dst, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..4132ad7d1ec55f6898c632fd4db51cd7743a0f70 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn_backward_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 void _cudnn_rnn_backward_out_symint(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); +TORCH_API ::std::tuple> _cudnn_rnn_backward(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, int64_t hidden_size, int64_t proj_size, int64_t num_layers, bool batch_first, double dropout, bool train, bool bidirectional, at::IntArrayRef batch_sizes, const c10::optional & dropout_state, const at::Tensor & reserve, ::std::array output_mask); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_abs.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_abs.h new file mode 100644 index 0000000000000000000000000000000000000000..d32a492b20587ec24a1b3021c6def522ec24449b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_abs.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_foreach_abs(Tensor[] self) -> Tensor[] +inline ::std::vector _foreach_abs(at::TensorList self) { + return at::_ops::_foreach_abs::call(self); +} + +// aten::_foreach_abs_(Tensor(a!)[] self) -> () +inline void _foreach_abs_(at::TensorList self) { + return at::_ops::_foreach_abs_::call(self); +} + +// aten::_foreach_abs.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_abs_out(at::TensorList out, at::TensorList self) { + return at::_ops::_foreach_abs_out::call(self, out); +} +// aten::_foreach_abs.out(Tensor[] self, *, Tensor(a!)[] out) -> () +inline void _foreach_abs_outf(at::TensorList self, at::TensorList out) { + return at::_ops::_foreach_abs_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sign_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sign_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..772b04f3a7c758c27a441be322388b6a633ab93f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sign_cuda_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::vector _foreach_sign(at::TensorList self); +TORCH_API void _foreach_sign_(at::TensorList self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_dropout_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_dropout_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ce96b7837e0c7f7b854cbcfc270b5a3d2069c974 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_dropout_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 _fused_dropout_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & self, double p, c10::optional generator=c10::nullopt); +TORCH_API ::std::tuple _fused_dropout_outf(const at::Tensor & self, double p, c10::optional generator, at::Tensor & out0, at::Tensor & out1); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_index_put_impl_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_index_put_impl_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e39d0ed738ff2854a8bd7e226ec6bcb5d90838e0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_index_put_impl_cpu_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor & _index_put_impl_(at::Tensor & self, const c10::List> & indices, const at::Tensor & values, bool accumulate=false, bool unsafe=false); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_neg_view_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_neg_view_native.h new file mode 100644 index 0000000000000000000000000000000000000000..32cf6972032e77a3f02b39af43dcbe9069f11166 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_neg_view_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 _neg_view(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_alias_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_alias_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c09e7f54ba192b7b8694bdedc5b957c853951fc2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_alias_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 at::Tensor _reshape_alias(const at::Tensor & self, at::IntArrayRef size, at::IntArrayRef stride); +TORCH_API at::Tensor _reshape_alias_symint(const at::Tensor & self, c10::SymIntArrayRef size, c10::SymIntArrayRef stride); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5dbd50277390e97d1a820159f76c8f7e1919ebb1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_slow_conv2d_backward_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _slow_conv2d_backward_grad_input { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, at::Tensor &, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_slow_conv2d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_slow_conv2d_backward.grad_input(Tensor grad_output, Tensor self, Tensor weight, SymInt[2] kernel_size, SymInt[2] stride, SymInt[2] padding, *, Tensor(a!) grad_input, Tensor(b!) grad_weight, Tensor(c!) grad_bias) -> (Tensor(a!), Tensor(b!), Tensor(c!))") + static ::std::tuple call(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, at::Tensor & grad_input, at::Tensor & grad_weight, at::Tensor & grad_bias); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, at::Tensor & grad_input, at::Tensor & grad_weight, at::Tensor & grad_bias); +}; + +struct TORCH_API _slow_conv2d_backward_output_mask { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, ::std::array); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_slow_conv2d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "output_mask") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_slow_conv2d_backward.output_mask(Tensor grad_output, Tensor self, Tensor weight, SymInt[2] kernel_size, SymInt[2] stride, SymInt[2] padding, bool[3] output_mask) -> (Tensor grad_input, Tensor grad_weight, Tensor grad_bias)") + static ::std::tuple call(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, ::std::array output_mask); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, ::std::array output_mask); +}; + +struct TORCH_API _slow_conv2d_backward_output_mask_out { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, ::std::array, at::Tensor &, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_slow_conv2d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "output_mask_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_slow_conv2d_backward.output_mask_out(Tensor grad_output, Tensor self, Tensor weight, SymInt[2] kernel_size, SymInt[2] stride, SymInt[2] padding, bool[3] output_mask, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2) -> (Tensor(a!), Tensor(b!), Tensor(c!))") + static ::std::tuple call(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_bsr_tensor_unsafe.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_bsr_tensor_unsafe.h new file mode 100644 index 0000000000000000000000000000000000000000..a5355c23d1aa7c45dd030408c8be8811604e8374 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_bsr_tensor_unsafe.h @@ -0,0 +1,34 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_sparse_bsr_tensor_unsafe(Tensor crow_indices, Tensor col_indices, Tensor values, int[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor _sparse_bsr_tensor_unsafe(const at::Tensor & crow_indices, const at::Tensor & col_indices, const at::Tensor & values, at::IntArrayRef size, at::TensorOptions options={}) { + return at::_ops::_sparse_bsr_tensor_unsafe::call(crow_indices, col_indices, values, size, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +// aten::_sparse_bsr_tensor_unsafe(Tensor crow_indices, Tensor col_indices, Tensor values, int[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor _sparse_bsr_tensor_unsafe(const at::Tensor & crow_indices, const at::Tensor & col_indices, const at::Tensor & values, at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::_sparse_bsr_tensor_unsafe::call(crow_indices, col_indices, values, size, dtype, layout, device, pin_memory); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_mm_reduce_impl_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_mm_reduce_impl_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..678bf47a06dfd54322d9148e190d760ec7a794d2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_mm_reduce_impl_backward_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple _sparse_mm_reduce_impl_backward_sparse_csr_cpu(const at::Tensor & self, const at::Tensor & grad_out, const at::Tensor & weight, c10::string_view reduce, const at::Tensor & arg_out, ::std::array output_mask); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_semi_structured_linear.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_semi_structured_linear.h new file mode 100644 index 0000000000000000000000000000000000000000..28ac6f555064e1f72b034b6a7741144393d09f71 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_semi_structured_linear.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::_sparse_semi_structured_linear(Tensor input, Tensor weight, Tensor meta, *, Tensor? bias=None, str? activation=None, ScalarType? out_dtype=None) -> Tensor +inline at::Tensor _sparse_semi_structured_linear(const at::Tensor & input, const at::Tensor & weight, const at::Tensor & meta, const c10::optional & bias={}, c10::optional activation=c10::nullopt, c10::optional out_dtype=c10::nullopt) { + return at::_ops::_sparse_semi_structured_linear::call(input, weight, meta, bias, activation, out_dtype); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bicubic2d_aa_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bicubic2d_aa_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..31bd44d3de065408dcf2bc9b19532c39df015eb9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_bicubic2d_aa_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _upsample_bicubic2d_aa_vec { + using schema = at::Tensor (const at::Tensor &, at::OptionalSymIntArrayRef, bool, c10::optional>); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_upsample_bicubic2d_aa") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "vec") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_upsample_bicubic2d_aa.vec(Tensor input, SymInt[]? output_size, bool align_corners, float[]? scale_factors) -> Tensor") + static at::Tensor call(const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, at::OptionalSymIntArrayRef output_size, bool align_corners, c10::optional> scale_factors); +}; + +struct TORCH_API _upsample_bicubic2d_aa_out { + using schema = at::Tensor & (const at::Tensor &, c10::SymIntArrayRef, bool, c10::optional, 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::_upsample_bicubic2d_aa") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_upsample_bicubic2d_aa.out(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); +}; + +struct TORCH_API _upsample_bicubic2d_aa { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef, 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::_upsample_bicubic2d_aa") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_upsample_bicubic2d_aa(Tensor self, SymInt[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_h, c10::optional scales_w); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact2d_backward_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact2d_backward_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9600e8330f3d3730bc119f2c5b1b7c8514ec2f0d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact2d_backward_cpu_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor _upsample_nearest_exact2d_backward(const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor _upsample_nearest_exact2d_backward_symint(const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & _upsample_nearest_exact2d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & _upsample_nearest_exact2d_backward_outf(const at::Tensor & grad_output, at::IntArrayRef output_size, at::IntArrayRef input_size, c10::optional scales_h, c10::optional scales_w, at::Tensor & grad_input); +TORCH_API at::Tensor & _upsample_nearest_exact2d_backward_symint_out(at::Tensor & grad_input, const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & _upsample_nearest_exact2d_backward_symint_outf(const at::Tensor & grad_output, c10::SymIntArrayRef output_size, c10::SymIntArrayRef input_size, c10::optional scales_h, c10::optional scales_w, at::Tensor & grad_input); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_rnn_flatten_weight_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_rnn_flatten_weight_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..866f32f7a9365bdfbfb816d3fdbaa92f7390254c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_rnn_flatten_weight_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API bool _use_cudnn_rnn_flatten_weight(); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool3d_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool3d_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..0eaf1492a857399a66187db290fa8863223fc5fe --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/adaptive_avg_pool3d_backward_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 & adaptive_avg_pool3d_backward_out_cpu(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input); +TORCH_API at::Tensor & adaptive_avg_pool3d_backward_out_cuda(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcdiv.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcdiv.h new file mode 100644 index 0000000000000000000000000000000000000000..e63537dd579cf89e3d257465ce441b2a8e80d7d6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addcdiv.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::addcdiv.out(Tensor self, Tensor tensor1, Tensor tensor2, *, Scalar value=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & addcdiv_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value=1) { + return at::_ops::addcdiv_out::call(self, tensor1, tensor2, value, out); +} +// aten::addcdiv.out(Tensor self, Tensor tensor1, Tensor tensor2, *, Scalar value=1, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & addcdiv_outf(const at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value, at::Tensor & out) { + return at::_ops::addcdiv_out::call(self, tensor1, tensor2, value, out); +} + +// aten::addcdiv(Tensor self, Tensor tensor1, Tensor tensor2, *, Scalar value=1) -> Tensor +inline at::Tensor addcdiv(const at::Tensor & self, const at::Tensor & tensor1, const at::Tensor & tensor2, const at::Scalar & value=1) { + return at::_ops::addcdiv::call(self, tensor1, tensor2, value); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmm_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmm_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..66090de60e2516acab5086dd4dc31623d0ccb85f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmm_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_addmm : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta, const at::Scalar & alpha); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arccos.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arccos.h new file mode 100644 index 0000000000000000000000000000000000000000..4669f4d1ee112147dd9660833422906aabf197ea --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arccos.h @@ -0,0 +1,44 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::arccos(Tensor self) -> Tensor +inline at::Tensor arccos(const at::Tensor & self) { + return at::_ops::arccos::call(self); +} + +// aten::arccos_(Tensor(a!) self) -> Tensor(a!) +inline at::Tensor & arccos_(at::Tensor & self) { + return at::_ops::arccos_::call(self); +} + +// aten::arccos.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & arccos_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::arccos_out::call(self, out); +} +// aten::arccos.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & arccos_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::arccos_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cd042073ea98193f0b0a990c6bb8ee4c8594e6a8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_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 argsort(const at::Tensor & self, bool stable, int64_t dim=-1, bool descending=false); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/as_strided_scatter_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/as_strided_scatter_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0dfad58d9272ad2d40caf908b159651c02ce8d35 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/as_strided_scatter_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor as_strided_scatter(const at::Tensor & self, const at::Tensor & src, at::IntArrayRef size, at::IntArrayRef stride, c10::optional storage_offset=c10::nullopt); +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 compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_and.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_and.h new file mode 100644 index 0000000000000000000000000000000000000000..ca1fcc1d1f19c6ed7031dc90f6bdd0f0f3444de7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_and.h @@ -0,0 +1,67 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::bitwise_and.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_and_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::bitwise_and_Tensor_out::call(self, other, out); +} +// aten::bitwise_and.Tensor_out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_and_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::bitwise_and_Tensor_out::call(self, other, out); +} + +// aten::bitwise_and.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_and_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & other) { + return at::_ops::bitwise_and_Scalar_out::call(self, other, out); +} +// aten::bitwise_and.Scalar_out(Tensor self, Scalar other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_and_outf(const at::Tensor & self, const at::Scalar & other, at::Tensor & out) { + return at::_ops::bitwise_and_Scalar_out::call(self, other, out); +} + +// aten::bitwise_and.Scalar(Tensor self, Scalar other) -> Tensor +inline at::Tensor bitwise_and(const at::Tensor & self, const at::Scalar & other) { + return at::_ops::bitwise_and_Scalar::call(self, other); +} + +// aten::bitwise_and.Scalar_Tensor(Scalar self, Tensor other) -> Tensor +inline at::Tensor bitwise_and(const at::Scalar & self, const at::Tensor & other) { + return at::_ops::bitwise_and_Scalar_Tensor::call(self, other); +} + +// aten::bitwise_and.Tensor(Tensor self, Tensor other) -> Tensor +inline at::Tensor bitwise_and(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::bitwise_and_Tensor::call(self, other); +} + +// aten::bitwise_and.Scalar_Tensor_out(Scalar self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_and_out(at::Tensor & out, const at::Scalar & self, const at::Tensor & other) { + return at::_ops::bitwise_and_Scalar_Tensor_out::call(self, other, out); +} +// aten::bitwise_and.Scalar_Tensor_out(Scalar self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & bitwise_and_outf(const at::Scalar & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::bitwise_and_Scalar_Tensor_out::call(self, other, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cartesian_prod_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cartesian_prod_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b9b0a906b48140bc85096510d026a00203538490 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cartesian_prod_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 cartesian_prod(at::TensorList tensors); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chain_matmul_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chain_matmul_native.h new file mode 100644 index 0000000000000000000000000000000000000000..360e68aa3056d2dfab5daaf8256324c20eb7208c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chain_matmul_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 chain_matmul(at::TensorList matrices); +TORCH_API at::Tensor & chain_matmul_out(at::TensorList matrices, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conj_physical_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conj_physical_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..88b83d7df31e9579506d4275a838801410e1304b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conj_physical_ops.h @@ -0,0 +1,50 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API conj_physical { + 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::conj_physical") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "conj_physical(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 conj_physical_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::conj_physical") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "conj_physical.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +struct TORCH_API conj_physical_ { + using schema = at::Tensor & (at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::conj_physical_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "conj_physical_(Tensor(a!) self) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/copy_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/copy_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8822660993a20651df2328825c579cb84e54e992 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/copy_compositeexplicitautograd_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 compositeexplicitautograd { + +TORCH_API at::Tensor & copy_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & src, bool non_blocking=false); +TORCH_API at::Tensor & copy_outf(const at::Tensor & self, const at::Tensor & src, bool non_blocking, at::Tensor & out); +TORCH_API at::Tensor & copy_(at::Tensor & self, const at::Tensor & src, bool non_blocking=false); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..7cd9a68b04c5742dc9898462c0be0b2e461b5976 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cudnn_convolution_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_convolution { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymInt, bool, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cudnn_convolution") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cudnn_convolution(Tensor self, Tensor weight, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups, bool benchmark, bool deterministic, bool allow_tf32) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, bool benchmark, bool deterministic, bool allow_tf32); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, bool benchmark, bool deterministic, bool allow_tf32); +}; + +struct TORCH_API cudnn_convolution_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymInt, bool, bool, bool, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cudnn_convolution") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cudnn_convolution.out(Tensor self, Tensor weight, SymInt[] padding, SymInt[] stride, SymInt[] dilation, SymInt groups, bool benchmark, bool deterministic, bool allow_tf32, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, bool benchmark, bool deterministic, bool allow_tf32, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef padding, c10::SymIntArrayRef stride, c10::SymIntArrayRef dilation, c10::SymInt groups, bool benchmark, bool deterministic, bool allow_tf32, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummax_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummax_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1aa5f0ca9344e05a1c5afa77b29d1941fa3bee6e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummax_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 cummax(const at::Tensor & self, at::Dimname dim); +TORCH_API ::std::tuple cummax_out(at::Tensor & values, at::Tensor & indices, const at::Tensor & self, at::Dimname dim); +TORCH_API ::std::tuple cummax_outf(const at::Tensor & self, at::Dimname dim, at::Tensor & values, at::Tensor & indices); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummaxmin_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummaxmin_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8bd02b3094cb7f0d2b5f3a25593ddff718c7bf54 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummaxmin_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 cummaxmin_backward(const at::Tensor & grad, const at::Tensor & input, const at::Tensor & indices, int64_t dim); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/detach_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/detach_native.h new file mode 100644 index 0000000000000000000000000000000000000000..7f877ae458e6b21e96535244ad27d100f6d93cc9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/detach_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 detach(const at::Tensor & self); +TORCH_API at::Tensor & detach_(at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty.h new file mode 100644 index 0000000000000000000000000000000000000000..b0b31eba0e0e08a98735d3bd88fa8993835ad9d5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty.h @@ -0,0 +1,131 @@ +#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::empty.names(int[] size, *, Dimname[]? names, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor +inline at::Tensor empty(at::IntArrayRef size, c10::optional names, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_names::call(size, names, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt(), c10::impl::check_tensor_options_and_extract_memory_format(options, memory_format)); +} +// aten::empty.names(int[] size, *, Dimname[]? names, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor +inline at::Tensor empty(at::IntArrayRef size, c10::optional names, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format) { + return at::_ops::empty_names::call(size, names, dtype, layout, device, pin_memory, memory_format); +} + +// aten::empty.memory_format(SymInt[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor +inline at::Tensor empty(at::IntArrayRef size, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_memory_format::call(c10::fromIntArrayRefSlow(size), c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt(), c10::impl::check_tensor_options_and_extract_memory_format(options, memory_format)); +} +namespace symint { + template ::value>> + at::Tensor empty(at::IntArrayRef size, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_memory_format::call(c10::fromIntArrayRefSlow(size), c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt(), c10::impl::check_tensor_options_and_extract_memory_format(options, memory_format)); + } +} + +// aten::empty.memory_format(SymInt[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor +inline at::Tensor empty(at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format) { + return at::_ops::empty_memory_format::call(c10::fromIntArrayRefSlow(size), dtype, layout, device, pin_memory, memory_format); +} +namespace symint { + template ::value>> + at::Tensor empty(at::IntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format) { + return at::_ops::empty_memory_format::call(c10::fromIntArrayRefSlow(size), dtype, layout, device, pin_memory, memory_format); + } +} + +// aten::empty.memory_format(SymInt[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor +inline at::Tensor empty_symint(c10::SymIntArrayRef size, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_memory_format::call(size, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt(), c10::impl::check_tensor_options_and_extract_memory_format(options, memory_format)); +} +namespace symint { + template ::value>> + at::Tensor empty(c10::SymIntArrayRef size, at::TensorOptions options={}, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_memory_format::call(size, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt(), c10::impl::check_tensor_options_and_extract_memory_format(options, memory_format)); + } +} + +// aten::empty.memory_format(SymInt[] size, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None, MemoryFormat? memory_format=None) -> Tensor +inline at::Tensor empty_symint(c10::SymIntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format) { + return at::_ops::empty_memory_format::call(size, dtype, layout, device, pin_memory, memory_format); +} +namespace symint { + template ::value>> + at::Tensor empty(c10::SymIntArrayRef size, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory, c10::optional memory_format) { + return at::_ops::empty_memory_format::call(size, dtype, layout, device, pin_memory, memory_format); + } +} + +// aten::empty.out(SymInt[] size, *, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_out(at::Tensor & out, at::IntArrayRef size, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_out::call(c10::fromIntArrayRefSlow(size), memory_format, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_out(at::Tensor & out, at::IntArrayRef size, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_out::call(c10::fromIntArrayRefSlow(size), memory_format, out); + } +} + +// aten::empty.out(SymInt[] size, *, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_outf(at::IntArrayRef size, c10::optional memory_format, at::Tensor & out) { + return at::_ops::empty_out::call(c10::fromIntArrayRefSlow(size), memory_format, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_outf(at::IntArrayRef size, c10::optional memory_format, at::Tensor & out) { + return at::_ops::empty_out::call(c10::fromIntArrayRefSlow(size), memory_format, out); + } +} + +// aten::empty.out(SymInt[] size, *, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_symint_out(at::Tensor & out, c10::SymIntArrayRef size, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_out::call(size, memory_format, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_out(at::Tensor & out, c10::SymIntArrayRef size, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_out::call(size, memory_format, out); + } +} + +// aten::empty.out(SymInt[] size, *, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_symint_outf(c10::SymIntArrayRef size, c10::optional memory_format, at::Tensor & out) { + return at::_ops::empty_out::call(size, memory_format, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_outf(c10::SymIntArrayRef size, c10::optional memory_format, at::Tensor & out) { + return at::_ops::empty_out::call(size, memory_format, out); + } +} + +// aten::empty.names_out(int[] size, *, Dimname[]? names, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_out(at::Tensor & out, at::IntArrayRef size, c10::optional names, c10::optional memory_format=c10::nullopt) { + return at::_ops::empty_names_out::call(size, names, memory_format, out); +} +// aten::empty.names_out(int[] size, *, Dimname[]? names, MemoryFormat? memory_format=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_outf(at::IntArrayRef size, c10::optional names, c10::optional memory_format, at::Tensor & out) { + return at::_ops::empty_names_out::call(size, names, memory_format, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_permuted.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_permuted.h new file mode 100644 index 0000000000000000000000000000000000000000..3cfcefab9fb735aa327111a773741c1f6696ff90 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_permuted.h @@ -0,0 +1,113 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::empty_permuted(SymInt[] size, int[] physical_layout, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_permuted(at::IntArrayRef size, at::IntArrayRef physical_layout, at::TensorOptions options={}) { + return at::_ops::empty_permuted::call(c10::fromIntArrayRefSlow(size), physical_layout, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +namespace symint { + template ::value>> + at::Tensor empty_permuted(at::IntArrayRef size, at::IntArrayRef physical_layout, at::TensorOptions options={}) { + return at::_ops::empty_permuted::call(c10::fromIntArrayRefSlow(size), physical_layout, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); + } +} + +// aten::empty_permuted(SymInt[] size, int[] physical_layout, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_permuted(at::IntArrayRef size, at::IntArrayRef physical_layout, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_permuted::call(c10::fromIntArrayRefSlow(size), physical_layout, dtype, layout, device, pin_memory); +} +namespace symint { + template ::value>> + at::Tensor empty_permuted(at::IntArrayRef size, at::IntArrayRef physical_layout, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_permuted::call(c10::fromIntArrayRefSlow(size), physical_layout, dtype, layout, device, pin_memory); + } +} + +// aten::empty_permuted(SymInt[] size, int[] physical_layout, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_permuted_symint(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, at::TensorOptions options={}) { + return at::_ops::empty_permuted::call(size, physical_layout, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +namespace symint { + template ::value>> + at::Tensor empty_permuted(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, at::TensorOptions options={}) { + return at::_ops::empty_permuted::call(size, physical_layout, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); + } +} + +// aten::empty_permuted(SymInt[] size, int[] physical_layout, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_permuted_symint(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_permuted::call(size, physical_layout, dtype, layout, device, pin_memory); +} +namespace symint { + template ::value>> + at::Tensor empty_permuted(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_permuted::call(size, physical_layout, dtype, layout, device, pin_memory); + } +} + +// aten::empty_permuted.out(SymInt[] size, int[] physical_layout, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_permuted_out(at::Tensor & out, at::IntArrayRef size, at::IntArrayRef physical_layout) { + return at::_ops::empty_permuted_out::call(c10::fromIntArrayRefSlow(size), physical_layout, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_permuted_out(at::Tensor & out, at::IntArrayRef size, at::IntArrayRef physical_layout) { + return at::_ops::empty_permuted_out::call(c10::fromIntArrayRefSlow(size), physical_layout, out); + } +} + +// aten::empty_permuted.out(SymInt[] size, int[] physical_layout, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_permuted_outf(at::IntArrayRef size, at::IntArrayRef physical_layout, at::Tensor & out) { + return at::_ops::empty_permuted_out::call(c10::fromIntArrayRefSlow(size), physical_layout, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_permuted_outf(at::IntArrayRef size, at::IntArrayRef physical_layout, at::Tensor & out) { + return at::_ops::empty_permuted_out::call(c10::fromIntArrayRefSlow(size), physical_layout, out); + } +} + +// aten::empty_permuted.out(SymInt[] size, int[] physical_layout, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_permuted_symint_out(at::Tensor & out, c10::SymIntArrayRef size, at::IntArrayRef physical_layout) { + return at::_ops::empty_permuted_out::call(size, physical_layout, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_permuted_out(at::Tensor & out, c10::SymIntArrayRef size, at::IntArrayRef physical_layout) { + return at::_ops::empty_permuted_out::call(size, physical_layout, out); + } +} + +// aten::empty_permuted.out(SymInt[] size, int[] physical_layout, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_permuted_symint_outf(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, at::Tensor & out) { + return at::_ops::empty_permuted_out::call(size, physical_layout, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_permuted_outf(c10::SymIntArrayRef size, at::IntArrayRef physical_layout, at::Tensor & out) { + return at::_ops::empty_permuted_out::call(size, physical_layout, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_irfft2_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_irfft2_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f805c2400c56f44272cde7fdd75e4de9b7df4086 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_irfft2_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 fft_irfft2(const at::Tensor & self, at::OptionalIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor fft_irfft2_symint(const at::Tensor & self, at::OptionalSymIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_irfft2_out(at::Tensor & out, const at::Tensor & self, at::OptionalIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_irfft2_outf(const at::Tensor & self, at::OptionalIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out); +TORCH_API at::Tensor & fft_irfft2_symint_out(at::Tensor & out, const at::Tensor & self, at::OptionalSymIntArrayRef s=c10::nullopt, at::IntArrayRef dim={-2,-1}, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_irfft2_symint_outf(const at::Tensor & self, at::OptionalSymIntArrayRef s, at::IntArrayRef dim, c10::optional norm, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d.h new file mode 100644 index 0000000000000000000000000000000000000000..9920ae95de1a2a99860b3369526c6dae3ccf189c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fractional_max_pool3d.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::fractional_max_pool3d.output(Tensor self, int[3] kernel_size, int[3] output_size, Tensor random_samples, *, Tensor(a!) output, Tensor(b!) indices) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple fractional_max_pool3d_out(at::Tensor & output, at::Tensor & indices, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples) { + return at::_ops::fractional_max_pool3d_output::call(self, kernel_size, output_size, random_samples, output, indices); +} +// aten::fractional_max_pool3d.output(Tensor self, int[3] kernel_size, int[3] output_size, Tensor random_samples, *, Tensor(a!) output, Tensor(b!) indices) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple fractional_max_pool3d_outf(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples, at::Tensor & output, at::Tensor & indices) { + return at::_ops::fractional_max_pool3d_output::call(self, kernel_size, output_size, random_samples, output, indices); +} + +// aten::fractional_max_pool3d(Tensor self, int[3] kernel_size, int[3] output_size, Tensor random_samples) -> (Tensor, Tensor) +inline ::std::tuple fractional_max_pool3d(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef output_size, const at::Tensor & random_samples) { + return at::_ops::fractional_max_pool3d::call(self, kernel_size, output_size, random_samples); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fused_moving_avg_obs_fake_quant_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fused_moving_avg_obs_fake_quant_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..e3f434e64830e4609e7c6915e4fdd6c7bd0b7580 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fused_moving_avg_obs_fake_quant_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 fused_moving_avg_obs_fake_quant { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, at::Tensor &, at::Tensor &, at::Tensor &, at::Tensor &, double, int64_t, int64_t, int64_t, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::fused_moving_avg_obs_fake_quant") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "fused_moving_avg_obs_fake_quant(Tensor self, Tensor observer_on, Tensor fake_quant_on, Tensor(a!) running_min, Tensor(b!) running_max, Tensor(c!) scale, Tensor(d!) zero_point, float averaging_const, int quant_min, int quant_max, int ch_axis, bool per_row_fake_quant=False, bool symmetric_quant=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & observer_on, const at::Tensor & fake_quant_on, at::Tensor & running_min, at::Tensor & running_max, at::Tensor & scale, at::Tensor & zero_point, double averaging_const, int64_t quant_min, int64_t quant_max, int64_t ch_axis, bool per_row_fake_quant, bool symmetric_quant); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & observer_on, const at::Tensor & fake_quant_on, at::Tensor & running_min, at::Tensor & running_max, at::Tensor & scale, at::Tensor & zero_point, double averaging_const, int64_t quant_min, int64_t quant_max, int64_t ch_axis, bool per_row_fake_quant, bool symmetric_quant); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5db9649cfbaf4f7a67d857d120ac866408b9bf1b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_backward_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 glu_backward(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim); +TORCH_API at::Tensor & glu_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, int64_t dim); +TORCH_API at::Tensor & glu_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, int64_t dim, at::Tensor & grad_input); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..6455a6cee6b06135ac38ff201b2b5c6d06edda89 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & grid_sampler_3d_out(at::Tensor & out, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners); +TORCH_API at::Tensor & grid_sampler_3d_outf(const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gru_cell_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gru_cell_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..24777c6952927f7b3856beee681ff6d9e5c15982 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gru_cell_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 gru_cell(const at::Tensor & input, const at::Tensor & hx, const at::Tensor & w_ih, const at::Tensor & w_hh, const c10::optional & b_ih={}, const c10::optional & b_hh={}); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardtanh_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardtanh_native.h new file mode 100644 index 0000000000000000000000000000000000000000..dc657d281487398bc6fb2cc896266eed1271de6e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardtanh_native.h @@ -0,0 +1,26 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor hardtanh(const at::Tensor & self, const at::Scalar & min_val=-1, const at::Scalar & max_val=1); +TORCH_API at::Tensor & hardtanh_out(const at::Tensor & self, const at::Scalar & min_val, const at::Scalar & max_val, at::Tensor & out); +TORCH_API at::Tensor & hardtanh_(at::Tensor & self, const at::Scalar & min_val=-1, const at::Scalar & max_val=1); +TORCH_API at::Tensor hardtanh_quantized_cpu(const at::Tensor & self, const at::Scalar & min_val=-1, const at::Scalar & max_val=1); +TORCH_API at::Tensor & hardtanh_out_quantized_cpu(const at::Tensor & self, const at::Scalar & min_val, const at::Scalar & max_val, at::Tensor & out); +TORCH_API at::Tensor & hardtanh_quantized_cpu_(at::Tensor & self, const at::Scalar & min_val=-1, const at::Scalar & max_val=1); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_copy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_copy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..950ddc5ffa8a174799ec617ae10372aafd0fc9bf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_copy_ops.h @@ -0,0 +1,72 @@ +#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 index_copy_out { + using schema = at::Tensor & (const at::Tensor &, int64_t, 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::index_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "index_copy.out(Tensor self, int dim, Tensor index, Tensor source, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source, at::Tensor & out); +}; + +struct TORCH_API index_copy_ { + using schema = at::Tensor & (at::Tensor &, int64_t, 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::index_copy_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "index_copy_(Tensor(a!) self, int dim, Tensor index, Tensor source) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source); +}; + +struct TORCH_API index_copy { + using schema = at::Tensor (const at::Tensor &, int64_t, 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::index_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "index_copy(Tensor self, int dim, Tensor index, Tensor source) -> Tensor") + static at::Tensor call(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source); +}; + +struct TORCH_API index_copy__dimname { + using schema = at::Tensor & (at::Tensor &, at::Dimname, 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::index_copy_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dimname") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "index_copy_.dimname(Tensor(a!) self, Dimname dim, Tensor index, Tensor source) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, at::Dimname dim, const at::Tensor & index, const at::Tensor & source); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, at::Dimname dim, const at::Tensor & index, const at::Tensor & source); +}; + +struct TORCH_API index_copy_dimname { + using schema = at::Tensor (const at::Tensor &, at::Dimname, 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::index_copy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dimname") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "index_copy.dimname(Tensor self, Dimname dim, Tensor index, Tensor source) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::Dimname dim, const at::Tensor & index, const at::Tensor & source); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Dimname dim, const at::Tensor & index, const at::Tensor & source); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isin.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isin.h new file mode 100644 index 0000000000000000000000000000000000000000..068b8641c91d70525fdda2bf7e7574b85bc7d9ab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isin.h @@ -0,0 +1,67 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::isin.Tensor_Tensor_out(Tensor elements, Tensor test_elements, *, bool assume_unique=False, bool invert=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isin_out(at::Tensor & out, const at::Tensor & elements, const at::Tensor & test_elements, bool assume_unique=false, bool invert=false) { + return at::_ops::isin_Tensor_Tensor_out::call(elements, test_elements, assume_unique, invert, out); +} +// aten::isin.Tensor_Tensor_out(Tensor elements, Tensor test_elements, *, bool assume_unique=False, bool invert=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isin_outf(const at::Tensor & elements, const at::Tensor & test_elements, bool assume_unique, bool invert, at::Tensor & out) { + return at::_ops::isin_Tensor_Tensor_out::call(elements, test_elements, assume_unique, invert, out); +} + +// aten::isin.Tensor_Tensor(Tensor elements, Tensor test_elements, *, bool assume_unique=False, bool invert=False) -> Tensor +inline at::Tensor isin(const at::Tensor & elements, const at::Tensor & test_elements, bool assume_unique=false, bool invert=false) { + return at::_ops::isin_Tensor_Tensor::call(elements, test_elements, assume_unique, invert); +} + +// aten::isin.Tensor_Scalar_out(Tensor elements, Scalar test_element, *, bool assume_unique=False, bool invert=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isin_out(at::Tensor & out, const at::Tensor & elements, const at::Scalar & test_element, bool assume_unique=false, bool invert=false) { + return at::_ops::isin_Tensor_Scalar_out::call(elements, test_element, assume_unique, invert, out); +} +// aten::isin.Tensor_Scalar_out(Tensor elements, Scalar test_element, *, bool assume_unique=False, bool invert=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isin_outf(const at::Tensor & elements, const at::Scalar & test_element, bool assume_unique, bool invert, at::Tensor & out) { + return at::_ops::isin_Tensor_Scalar_out::call(elements, test_element, assume_unique, invert, out); +} + +// aten::isin.Tensor_Scalar(Tensor elements, Scalar test_element, *, bool assume_unique=False, bool invert=False) -> Tensor +inline at::Tensor isin(const at::Tensor & elements, const at::Scalar & test_element, bool assume_unique=false, bool invert=false) { + return at::_ops::isin_Tensor_Scalar::call(elements, test_element, assume_unique, invert); +} + +// aten::isin.Scalar_Tensor_out(Scalar element, Tensor test_elements, *, bool assume_unique=False, bool invert=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isin_out(at::Tensor & out, const at::Scalar & element, const at::Tensor & test_elements, bool assume_unique=false, bool invert=false) { + return at::_ops::isin_Scalar_Tensor_out::call(element, test_elements, assume_unique, invert, out); +} +// aten::isin.Scalar_Tensor_out(Scalar element, Tensor test_elements, *, bool assume_unique=False, bool invert=False, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isin_outf(const at::Scalar & element, const at::Tensor & test_elements, bool assume_unique, bool invert, at::Tensor & out) { + return at::_ops::isin_Scalar_Tensor_out::call(element, test_elements, assume_unique, invert, out); +} + +// aten::isin.Scalar_Tensor(Scalar element, Tensor test_elements, *, bool assume_unique=False, bool invert=False) -> Tensor +inline at::Tensor isin(const at::Scalar & element, const at::Tensor & test_elements, bool assume_unique=false, bool invert=false) { + return at::_ops::isin_Scalar_Tensor::call(element, test_elements, assume_unique, invert); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isin_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isin_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..fcbf2a10d38a8181774357e3d3d92e2bb508f8c9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isin_compositeexplicitautogradnonfunctional_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 compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor isin(const at::Tensor & elements, const at::Tensor & test_elements, bool assume_unique=false, bool invert=false); +TORCH_API at::Tensor isin(const at::Tensor & elements, const at::Scalar & test_element, bool assume_unique=false, bool invert=false); +TORCH_API at::Tensor isin(const at::Scalar & element, const at::Tensor & test_elements, bool assume_unique=false, bool invert=false); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isposinf_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isposinf_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b40d121d4e8baff929717269d4d145fab1f748cf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isposinf_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor isposinf(const at::Tensor & self); +TORCH_API at::Tensor & isposinf_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & isposinf_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/istft_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/istft_native.h new file mode 100644 index 0000000000000000000000000000000000000000..4931168ea609ed8437ae1d6b3b1b72802c32ae37 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/istft_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 istft(const at::Tensor & self, int64_t n_fft, c10::optional hop_length=c10::nullopt, c10::optional win_length=c10::nullopt, const c10::optional & window={}, bool center=true, bool normalized=false, c10::optional onesided=c10::nullopt, c10::optional length=c10::nullopt, bool return_complex=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lcm_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lcm_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0082471d2ec99184c21f874f7bfcff3e0d6c9867 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lcm_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 lcm(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & lcm_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & lcm_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & lcm_(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/linalg_tensorinv_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_tensorinv_native.h new file mode 100644 index 0000000000000000000000000000000000000000..f9b90dd08988f112132f24d9723c62605e032662 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_tensorinv_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor linalg_tensorinv(const at::Tensor & self, int64_t ind=2); +TORCH_API at::Tensor & linalg_tensorinv_out(const at::Tensor & self, int64_t ind, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_sigmoid_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_sigmoid_native.h new file mode 100644 index 0000000000000000000000000000000000000000..2eb95092126f43659903613bd4eb9821e1916aff --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_sigmoid_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 log_sigmoid(const at::Tensor & self); +TORCH_API at::Tensor & log_sigmoid_out(const at::Tensor & self, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_backward_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_backward_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a1159b5c8ad75de8f4e9f98d3ccadb49b490b483 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logit_backward_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor logit_backward(const at::Tensor & grad_output, const at::Tensor & self, c10::optional eps=c10::nullopt); +TORCH_API at::Tensor & logit_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, c10::optional eps=c10::nullopt); +TORCH_API at::Tensor & logit_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, c10::optional eps, at::Tensor & grad_input); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..467b39492e0dd5a5d2ffedacca3047a9d13e2857 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/masked_scatter_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 masked_scatter_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::masked_scatter_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "masked_scatter_backward(Tensor grad_output, Tensor mask, SymInt[] sizes) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & mask, c10::SymIntArrayRef sizes); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & mask, c10::SymIntArrayRef sizes); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matrix_power.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matrix_power.h new file mode 100644 index 0000000000000000000000000000000000000000..105474cc7ef68ea1df675416704835135f095a43 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matrix_power.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::matrix_power(Tensor self, int n) -> Tensor +inline at::Tensor matrix_power(const at::Tensor & self, int64_t n) { + return at::_ops::matrix_power::call(self, n); +} + +// aten::matrix_power.out(Tensor self, int n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & matrix_power_out(at::Tensor & out, const at::Tensor & self, int64_t n) { + return at::_ops::matrix_power_out::call(self, n, out); +} +// aten::matrix_power.out(Tensor self, int n, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & matrix_power_outf(const at::Tensor & self, int64_t n, at::Tensor & out) { + return at::_ops::matrix_power_out::call(self, n, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mul_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mul_native.h new file mode 100644 index 0000000000000000000000000000000000000000..025d3882c981acdcb6cc1588c8b9e513e085d79b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mul_native.h @@ -0,0 +1,43 @@ +#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_mul_out : public at::meta::structured_mul_Tensor { +void impl(const at::Tensor & self, const at::Tensor & other, const at::Tensor & out); +}; +TORCH_API at::Tensor NestedTensor_mul_Tensor(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & NestedTensor_mul__Tensor(at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor mul_sparse(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & mul_out_sparse_cpu(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & mul_sparse_(at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & mul_out_sparse_cuda(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor mul_sparse_csr(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & mul_out_sparse_csr(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & mul_sparse_csr_(at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor mkldnn_mul(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & mkldnn_mul_out(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & mkldnn_mul_(at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor mul_zerotensor(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor mul(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & mul_Scalar_out(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +TORCH_API at::Tensor & mul_(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor NestedTensor_mul_Scalar(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & NestedTensor_mul__Scalar(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor mul_scalar_sparse_csr(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & mul__scalar_sparse_csr(at::Tensor & self, const at::Scalar & other); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_layer_norm_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_layer_norm_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..87e7de159a773b419decbf4fc7c1769c088f8162 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_layer_norm_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 native_layer_norm { + using schema = ::std::tuple (const at::Tensor &, c10::SymIntArrayRef, const c10::optional &, const c10::optional &, double); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::native_layer_norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "native_layer_norm(Tensor input, SymInt[] normalized_shape, Tensor? weight, Tensor? bias, float eps) -> (Tensor, Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & input, c10::SymIntArrayRef normalized_shape, const c10::optional & weight, const c10::optional & bias, double eps); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, c10::SymIntArrayRef normalized_shape, const c10::optional & weight, const c10::optional & bias, double eps); +}; + +struct TORCH_API native_layer_norm_out { + using schema = ::std::tuple (const at::Tensor &, c10::SymIntArrayRef, const c10::optional &, const c10::optional &, double, at::Tensor &, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::native_layer_norm") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "native_layer_norm.out(Tensor input, SymInt[] normalized_shape, Tensor? weight, Tensor? bias, float eps, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2) -> (Tensor(a!), Tensor(b!), Tensor(c!))") + static ::std::tuple call(const at::Tensor & input, c10::SymIntArrayRef normalized_shape, const c10::optional & weight, const c10::optional & bias, double eps, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & input, c10::SymIntArrayRef normalized_shape, const c10::optional & weight, const c10::optional & bias, double eps, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/output_nr_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/output_nr_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..650446095923bd6bf0dad40028aa066b65a582ab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/output_nr_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 output_nr { + using schema = int64_t (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::output_nr") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "output_nr(Tensor self) -> int") + static int64_t call(const at::Tensor & self); + static int64_t 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/pad_sequence_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_sequence_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..d5e328923eaaea776dec918a69af7bdff91bc850 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pad_sequence_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 pad_sequence { + using schema = at::Tensor (at::TensorList, bool, double); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::pad_sequence") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "pad_sequence(Tensor[] sequences, bool batch_first=False, float padding_value=0.0) -> Tensor") + static at::Tensor call(at::TensorList sequences, bool batch_first, double padding_value); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList sequences, bool batch_first, double padding_value); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/permute_copy.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/permute_copy.h new file mode 100644 index 0000000000000000000000000000000000000000..5bb2a24787d6c5a0fb04f57f0f6480c0f76c2c3f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/permute_copy.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::permute_copy(Tensor self, int[] dims) -> Tensor +inline at::Tensor permute_copy(const at::Tensor & self, at::IntArrayRef dims) { + return at::_ops::permute_copy::call(self, dims); +} + +// aten::permute_copy.out(Tensor self, int[] dims, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & permute_copy_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef dims) { + return at::_ops::permute_copy_out::call(self, dims, out); +} +// aten::permute_copy.out(Tensor self, int[] dims, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & permute_copy_outf(const at::Tensor & self, at::IntArrayRef dims, at::Tensor & out) { + return at::_ops::permute_copy_out::call(self, dims, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/prod_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/prod_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e7370f0250146d02782d73cdf3300c9293184c8a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/prod_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 prod(const at::Tensor & self, int64_t dim, 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/q_per_channel_axis_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_per_channel_axis_native.h new file mode 100644 index 0000000000000000000000000000000000000000..8b053651d163059d12c1a1fd2ca8c8ef0c4b1fd3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_per_channel_axis_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 int64_t q_per_channel_axis(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad3d_backward_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad3d_backward_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f2e65de4a991db4c1132b8c85307311a0a013f1e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad3d_backward_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor reflection_pad3d_backward(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding); +TORCH_API at::Tensor reflection_pad3d_backward_symint(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..608763284f8db350b9677e6e5ebb6e401fd1cca2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/replication_pad3d_backward_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 replication_pad3d_backward(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding); +TORCH_API at::Tensor replication_pad3d_backward_symint(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding); +TORCH_API at::Tensor & replication_pad3d_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding); +TORCH_API at::Tensor & replication_pad3d_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef padding, at::Tensor & grad_input); +TORCH_API at::Tensor & replication_pad3d_backward_symint_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding); +TORCH_API at::Tensor & replication_pad3d_backward_symint_outf(const at::Tensor & grad_output, const at::Tensor & self, c10::SymIntArrayRef padding, at::Tensor & grad_input); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reshape_as.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reshape_as.h new file mode 100644 index 0000000000000000000000000000000000000000..f91d4233ef60aef89b5985106adaed66120d6267 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reshape_as.h @@ -0,0 +1,26 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reshape_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reshape_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5989910f0ee4b47197c4ba09c559627852e453f4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reshape_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API reshape { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::reshape") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "reshape(Tensor(a) self, SymInt[] shape) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef shape); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef shape); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/resize_as_sparse_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/resize_as_sparse_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..468897e957bb1ebcff5d66863de0b29543ca4fd2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/resize_as_sparse_compositeexplicitautograd_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 compositeexplicitautograd { + +TORCH_API at::Tensor resize_as_sparse(const at::Tensor & self, const at::Tensor & the_template); +TORCH_API const at::Tensor & resize_as_sparse_out(const at::Tensor & out, const at::Tensor & self, const at::Tensor & the_template); +TORCH_API const at::Tensor & resize_as_sparse_outf(const at::Tensor & self, const at::Tensor & the_template, const at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/result_type_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/result_type_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..88b3b769d246f5f2f30e10b1b4a5ad4fc8c30512 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/result_type_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 result_type_Tensor { + using schema = at::ScalarType (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::result_type") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "result_type.Tensor(Tensor tensor, Tensor other) -> ScalarType") + static at::ScalarType call(const at::Tensor & tensor, const at::Tensor & other); + static at::ScalarType redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & tensor, const at::Tensor & other); +}; + +struct TORCH_API result_type_Scalar { + using schema = at::ScalarType (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::result_type") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "result_type.Scalar(Tensor tensor, Scalar other) -> ScalarType") + static at::ScalarType call(const at::Tensor & tensor, const at::Scalar & other); + static at::ScalarType redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & tensor, const at::Scalar & other); +}; + +struct TORCH_API result_type_Scalar_Tensor { + using schema = at::ScalarType (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::result_type") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "result_type.Scalar_Tensor(Scalar scalar, Tensor tensor) -> ScalarType") + static at::ScalarType call(const at::Scalar & scalar, const at::Tensor & tensor); + static at::ScalarType redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & scalar, const at::Tensor & tensor); +}; + +struct TORCH_API result_type_Scalar_Scalar { + using schema = at::ScalarType (const at::Scalar &, const at::Scalar &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::result_type") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "result_type.Scalar_Scalar(Scalar scalar1, Scalar scalar2) -> ScalarType") + static at::ScalarType call(const at::Scalar & scalar1, const at::Scalar & scalar2); + static at::ScalarType redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & scalar1, const at::Scalar & scalar2); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/segment_reduce_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/segment_reduce_native.h new file mode 100644 index 0000000000000000000000000000000000000000..49fa3d1d59ef131e919900d3016140c89174c9ab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/segment_reduce_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 & segment_reduce_out(const at::Tensor & data, c10::string_view reduce, const c10::optional & lengths, const c10::optional & indices, const c10::optional & offsets, int64_t axis, bool unsafe, const c10::optional & initial, at::Tensor & out); +TORCH_API at::Tensor segment_reduce_kernel(const at::Tensor & data, c10::string_view reduce, const c10::optional & lengths={}, const c10::optional & indices={}, const c10::optional & offsets={}, int64_t axis=0, bool unsafe=false, const c10::optional & initial=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/signbit_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/signbit_native.h new file mode 100644 index 0000000000000000000000000000000000000000..aa8f97a2775952ccc86a4693d02a87e459449634 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/signbit_native.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_signbit_out : public at::meta::structured_signbit { +void impl(const at::Tensor & self, const at::Tensor & out); +}; +TORCH_API at::Tensor signbit_sparse(const at::Tensor & self); +TORCH_API at::Tensor & signbit_sparse_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor signbit_sparse_csr(const at::Tensor & self); +TORCH_API at::Tensor & signbit_sparse_csr_out(const at::Tensor & self, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfcx.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfcx.h new file mode 100644 index 0000000000000000000000000000000000000000..060001e9e0f53f44690e65d09858c8f3c77e6850 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfcx.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::special_erfcx(Tensor self) -> Tensor +inline at::Tensor special_erfcx(const at::Tensor & self) { + return at::_ops::special_erfcx::call(self); +} + +// aten::special_erfcx.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_erfcx_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::special_erfcx_out::call(self, out); +} +// aten::special_erfcx.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_erfcx_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::special_erfcx_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_i0e_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_i0e_native.h new file mode 100644 index 0000000000000000000000000000000000000000..763c65eadc98156fde7ae315c5353dd9737fdb67 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_i0e_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_special_i0e_out : public at::meta::structured_special_i0e { +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/sym_storage_offset.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sym_storage_offset.h new file mode 100644 index 0000000000000000000000000000000000000000..2ce04dfaec1d7b22676e83d931c2c27386a3cac8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sym_storage_offset.h @@ -0,0 +1,30 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::sym_storage_offset(Tensor self) -> SymInt +inline c10::SymInt __dispatch_sym_storage_offset(const at::Tensor & self) { + return at::_ops::sym_storage_offset::call(self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5a22c9c71441ac2cfb17298e96ddf6d95d1efd9f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_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 unfold { + using schema = at::Tensor (const at::Tensor &, 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::unfold") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "unfold(Tensor(a) self, int dimension, int size, int step) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, int64_t dimension, int64_t size, int64_t step); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dimension, int64_t size, int64_t step); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsqueeze_copy.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsqueeze_copy.h new file mode 100644 index 0000000000000000000000000000000000000000..69869b1051b4e9d97d01a9c1e6f21eb5027a359c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unsqueeze_copy.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::unsqueeze_copy(Tensor self, int dim) -> Tensor +inline at::Tensor unsqueeze_copy(const at::Tensor & self, int64_t dim) { + return at::_ops::unsqueeze_copy::call(self, dim); +} + +// aten::unsqueeze_copy.out(Tensor self, int dim, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & unsqueeze_copy_out(at::Tensor & out, const at::Tensor & self, int64_t dim) { + return at::_ops::unsqueeze_copy_out::call(self, dim, out); +} +// aten::unsqueeze_copy.out(Tensor self, int dim, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & unsqueeze_copy_outf(const at::Tensor & self, int64_t dim, at::Tensor & out) { + return at::_ops::unsqueeze_copy_out::call(self, dim, out); +} + +}