diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b97da5d16ea6c57aa37937f4980305377292dbb8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_assert_scalar_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 _assert_scalar { + using schema = void (const at::Scalar &, c10::string_view); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_assert_scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_assert_scalar(Scalar self, str assert_msg) -> ()") + static void call(const at::Scalar & self, c10::string_view assert_msg); + static void redispatch(c10::DispatchKeySet dispatchKeySet, const at::Scalar & self, c10::string_view assert_msg); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Byte_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Byte_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..641a371ea186c40cf734240bcbf12c598d562c45 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Byte_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 _cast_Byte { + 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::_cast_Byte") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cast_Byte(Tensor self, bool non_blocking=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, bool non_blocking); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool non_blocking); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cdist_forward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cdist_forward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b10449cc72d23227ee6adbc86a34e74eabe882e7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cdist_forward_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 _cdist_forward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, double, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cdist_forward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cdist_forward(Tensor x1, Tensor x2, float p, int? compute_mode) -> Tensor") + static at::Tensor call(const at::Tensor & x1, const at::Tensor & x2, double p, c10::optional compute_mode); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x1, const at::Tensor & x2, double p, c10::optional compute_mode); +}; + +struct TORCH_API _cdist_forward_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, double, c10::optional, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_cdist_forward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_cdist_forward.out(Tensor x1, Tensor x2, float p, int? compute_mode, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & x1, const at::Tensor & x2, double p, c10::optional compute_mode, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x1, const at::Tensor & x2, double p, c10::optional compute_mode, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_weight_to_int4pack_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_weight_to_int4pack_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..14df73b867581d86492a36a9154747711d7d952f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convert_weight_to_int4pack_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 _convert_weight_to_int4pack(const at::Tensor & self, int64_t innerKTiles); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn.h new file mode 100644 index 0000000000000000000000000000000000000000..076ee0eb3d5a2b6cdf9c8154093c4fe46e4c9990 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cudnn_rnn.h @@ -0,0 +1,91 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_cudnn_rnn(Tensor input, Tensor[] weight, int weight_stride0, Tensor? weight_buf, Tensor hx, Tensor? cx, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state) -> (Tensor, Tensor, Tensor, Tensor, Tensor) +inline ::std::tuple _cudnn_rnn(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, c10::fromIntArrayRefSlow(batch_sizes), dropout_state); +} +namespace symint { + template ::value>> + ::std::tuple _cudnn_rnn(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, c10::fromIntArrayRefSlow(batch_sizes), dropout_state); + } +} + +// aten::_cudnn_rnn(Tensor input, Tensor[] weight, int weight_stride0, Tensor? weight_buf, Tensor hx, Tensor? cx, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state) -> (Tensor, Tensor, Tensor, Tensor, Tensor) +inline ::std::tuple _cudnn_rnn_symint(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, batch_sizes, dropout_state); +} +namespace symint { + template ::value>> + ::std::tuple _cudnn_rnn(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, batch_sizes, dropout_state); + } +} + +// aten::_cudnn_rnn.out(Tensor input, Tensor[] weight, int weight_stride0, Tensor? weight_buf, Tensor hx, Tensor? cx, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3, Tensor(e!) out4) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!), Tensor(e!)) +inline ::std::tuple _cudnn_rnn_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4, const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, c10::fromIntArrayRefSlow(batch_sizes), dropout_state, out0, out1, out2, out3, out4); +} +namespace symint { + template ::value>> + ::std::tuple _cudnn_rnn_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4, const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, c10::fromIntArrayRefSlow(batch_sizes), dropout_state, out0, out1, out2, out3, out4); + } +} + +// aten::_cudnn_rnn.out(Tensor input, Tensor[] weight, int weight_stride0, Tensor? weight_buf, Tensor hx, Tensor? cx, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3, Tensor(e!) out4) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!), Tensor(e!)) +inline ::std::tuple _cudnn_rnn_outf(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, c10::fromIntArrayRefSlow(batch_sizes), dropout_state, out0, out1, out2, out3, out4); +} +namespace symint { + template ::value>> + ::std::tuple _cudnn_rnn_outf(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, c10::fromIntArrayRefSlow(batch_sizes), dropout_state, out0, out1, out2, out3, out4); + } +} + +// aten::_cudnn_rnn.out(Tensor input, Tensor[] weight, int weight_stride0, Tensor? weight_buf, Tensor hx, Tensor? cx, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3, Tensor(e!) out4) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!), Tensor(e!)) +inline ::std::tuple _cudnn_rnn_symint_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4, const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, batch_sizes, dropout_state, out0, out1, out2, out3, out4); +} +namespace symint { + template ::value>> + ::std::tuple _cudnn_rnn_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4, const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, batch_sizes, dropout_state, out0, out1, out2, out3, out4); + } +} + +// aten::_cudnn_rnn.out(Tensor input, Tensor[] weight, int weight_stride0, Tensor? weight_buf, Tensor hx, Tensor? cx, int mode, SymInt hidden_size, SymInt proj_size, int num_layers, bool batch_first, float dropout, bool train, bool bidirectional, SymInt[] batch_sizes, Tensor? dropout_state, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3, Tensor(e!) out4) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!), Tensor(e!)) +inline ::std::tuple _cudnn_rnn_symint_outf(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, batch_sizes, dropout_state, out0, out1, out2, out3, out4); +} +namespace symint { + template ::value>> + ::std::tuple _cudnn_rnn_outf(const at::Tensor & input, at::TensorList weight, int64_t weight_stride0, const c10::optional & weight_buf, const at::Tensor & hx, const c10::optional & cx, 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, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, at::Tensor & out4) { + return at::_ops::_cudnn_rnn_out::call(input, weight, weight_stride0, weight_buf, hx, cx, mode, hidden_size, proj_size, num_layers, batch_first, dropout, train, bidirectional, batch_sizes, dropout_state, out0, out1, out2, out3, out4); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_dim_arange.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_dim_arange.h new file mode 100644 index 0000000000000000000000000000000000000000..f0b55d220d60dbbf6b117a1691241deb44874fe2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_dim_arange.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::_dim_arange(Tensor like, int dim) -> Tensor +inline at::Tensor _dim_arange(const at::Tensor & like, int64_t dim) { + return at::_ops::_dim_arange::call(like, dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_learnable_per_channel_affine_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_learnable_per_channel_affine_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..dc8494ef3b1449843abe714aa2064f8fa15ef8f1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fake_quantize_learnable_per_channel_affine_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 _fake_quantize_learnable_per_channel_affine(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, int64_t quant_min, int64_t quant_max, double grad_factor=1.0); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sinh_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sinh_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c1f0e48745f003a9f5365baa54fd24eeb375098d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_sinh_cpu_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API ::std::vector _foreach_sinh(at::TensorList self); +TORCH_API void _foreach_sinh_(at::TensorList self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_masked_softmax_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_masked_softmax_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..df11b0092912751e633872f750ccccef3f7ea6e5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_masked_softmax_backward.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_masked_softmax_backward(Tensor grad_output, Tensor output, Tensor mask, int? dim=None) -> Tensor +inline at::Tensor _masked_softmax_backward(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & mask, c10::optional dim=c10::nullopt) { + return at::_ops::_masked_softmax_backward::call(grad_output, output, mask, dim); +} + +// aten::_masked_softmax_backward.out(Tensor grad_output, Tensor output, Tensor mask, int? dim=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _masked_softmax_backward_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & mask, c10::optional dim=c10::nullopt) { + return at::_ops::_masked_softmax_backward_out::call(grad_output, output, mask, dim, out); +} +// aten::_masked_softmax_backward.out(Tensor grad_output, Tensor output, Tensor mask, int? dim=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _masked_softmax_backward_outf(const at::Tensor & grad_output, const at::Tensor & output, const at::Tensor & mask, c10::optional dim, at::Tensor & out) { + return at::_ops::_masked_softmax_backward_out::call(grad_output, output, mask, dim, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_get_lengths.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_get_lengths.h new file mode 100644 index 0000000000000000000000000000000000000000..db3a4dc72e30b9817337637a6f27383fc8067606 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_get_lengths.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::_nested_get_lengths(Tensor self) -> Tensor +inline at::Tensor _nested_get_lengths(const at::Tensor & self) { + return at::_ops::_nested_get_lengths::call(self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_get_values_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_get_values_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..bc5704467b52eab568f32da67be8b841fa21427c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_get_values_ops.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _nested_get_values { + 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::_nested_get_values") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_get_values(Tensor(a) self) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_packed_sequence_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_packed_sequence_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..15098948b51d7878750cae34deb926a8f71752c1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_packed_sequence_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API ::std::tuple _pad_packed_sequence(const at::Tensor & data, const at::Tensor & batch_sizes, bool batch_first, const at::Scalar & padding_value, int64_t total_length); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pin_memory_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pin_memory_native.h new file mode 100644 index 0000000000000000000000000000000000000000..1aa883f6682ccf181a8dbe048f25888c38782a8b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pin_memory_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor & _pin_memory_out(const at::Tensor & self, c10::optional device, at::Tensor & out); +TORCH_API at::Tensor _pin_memory_cuda(const at::Tensor & self, c10::optional device=c10::nullopt); +TORCH_API at::Tensor _pin_memory_nested(const at::Tensor & self, c10::optional device=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_copy.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_copy.h new file mode 100644 index 0000000000000000000000000000000000000000..58df5f06892d8e4e784d4d59a197dda98b40c1dc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_reshape_copy.h @@ -0,0 +1,47 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_reshape_copy(Tensor self, SymInt[] size) -> Tensor +inline at::Tensor _reshape_copy(const at::Tensor & self, at::IntArrayRef size) { + return at::_ops::_reshape_copy::call(self, c10::fromIntArrayRefSlow(size)); +} +namespace symint { + template ::value>> + at::Tensor _reshape_copy(const at::Tensor & self, at::IntArrayRef size) { + return at::_ops::_reshape_copy::call(self, c10::fromIntArrayRefSlow(size)); + } +} + +// aten::_reshape_copy(Tensor self, SymInt[] size) -> Tensor +inline at::Tensor _reshape_copy_symint(const at::Tensor & self, c10::SymIntArrayRef size) { + return at::_ops::_reshape_copy::call(self, size); +} +namespace symint { + template ::value>> + at::Tensor _reshape_copy(const at::Tensor & self, c10::SymIntArrayRef size) { + return at::_ops::_reshape_copy::call(self, size); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_rowwise_prune_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_rowwise_prune_native.h new file mode 100644 index 0000000000000000000000000000000000000000..3fb2b24304f214becc6718d9c457b975d9953a2e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_rowwise_prune_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 _rowwise_prune(const at::Tensor & weight, const at::Tensor & mask, at::ScalarType compressed_indices_dtype); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_rowwise_prune_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_rowwise_prune_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b9996b919a40c75266c9bdfe0f1c637bb4a24e47 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_rowwise_prune_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 _rowwise_prune { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, at::ScalarType); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_rowwise_prune") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_rowwise_prune(Tensor weight, Tensor mask, ScalarType compressed_indices_dtype) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & weight, const at::Tensor & mask, at::ScalarType compressed_indices_dtype); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & weight, const at::Tensor & mask, at::ScalarType compressed_indices_dtype); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_flash_attention_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_flash_attention_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..a7130019366087af497a9d1dde6b4b50552b48ee --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_dot_product_flash_attention_backward.h @@ -0,0 +1,47 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_scaled_dot_product_flash_attention_backward(Tensor grad_out, Tensor query, Tensor key, Tensor value, Tensor out, Tensor logsumexp, Tensor cum_seq_q, Tensor cum_seq_k, SymInt max_q, SymInt max_k, float dropout_p, bool is_causal, Tensor philox_seed, Tensor philox_offset, *, float? scale=None) -> (Tensor grad_query, Tensor grad_key, Tensor grad_value) +inline ::std::tuple _scaled_dot_product_flash_attention_backward(const at::Tensor & grad_out, const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const at::Tensor & out, const at::Tensor & logsumexp, const at::Tensor & cum_seq_q, const at::Tensor & cum_seq_k, int64_t max_q, int64_t max_k, double dropout_p, bool is_causal, const at::Tensor & philox_seed, const at::Tensor & philox_offset, c10::optional scale=c10::nullopt) { + return at::_ops::_scaled_dot_product_flash_attention_backward::call(grad_out, query, key, value, out, logsumexp, cum_seq_q, cum_seq_k, max_q, max_k, dropout_p, is_causal, philox_seed, philox_offset, scale); +} +namespace symint { + template ::value>> + ::std::tuple _scaled_dot_product_flash_attention_backward(const at::Tensor & grad_out, const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const at::Tensor & out, const at::Tensor & logsumexp, const at::Tensor & cum_seq_q, const at::Tensor & cum_seq_k, int64_t max_q, int64_t max_k, double dropout_p, bool is_causal, const at::Tensor & philox_seed, const at::Tensor & philox_offset, c10::optional scale=c10::nullopt) { + return at::_ops::_scaled_dot_product_flash_attention_backward::call(grad_out, query, key, value, out, logsumexp, cum_seq_q, cum_seq_k, max_q, max_k, dropout_p, is_causal, philox_seed, philox_offset, scale); + } +} + +// aten::_scaled_dot_product_flash_attention_backward(Tensor grad_out, Tensor query, Tensor key, Tensor value, Tensor out, Tensor logsumexp, Tensor cum_seq_q, Tensor cum_seq_k, SymInt max_q, SymInt max_k, float dropout_p, bool is_causal, Tensor philox_seed, Tensor philox_offset, *, float? scale=None) -> (Tensor grad_query, Tensor grad_key, Tensor grad_value) +inline ::std::tuple _scaled_dot_product_flash_attention_backward_symint(const at::Tensor & grad_out, const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const at::Tensor & out, const at::Tensor & logsumexp, const at::Tensor & cum_seq_q, const at::Tensor & cum_seq_k, c10::SymInt max_q, c10::SymInt max_k, double dropout_p, bool is_causal, const at::Tensor & philox_seed, const at::Tensor & philox_offset, c10::optional scale=c10::nullopt) { + return at::_ops::_scaled_dot_product_flash_attention_backward::call(grad_out, query, key, value, out, logsumexp, cum_seq_q, cum_seq_k, max_q, max_k, dropout_p, is_causal, philox_seed, philox_offset, scale); +} +namespace symint { + template ::value>> + ::std::tuple _scaled_dot_product_flash_attention_backward(const at::Tensor & grad_out, const at::Tensor & query, const at::Tensor & key, const at::Tensor & value, const at::Tensor & out, const at::Tensor & logsumexp, const at::Tensor & cum_seq_q, const at::Tensor & cum_seq_k, c10::SymInt max_q, c10::SymInt max_k, double dropout_p, bool is_causal, const at::Tensor & philox_seed, const at::Tensor & philox_offset, c10::optional scale=c10::nullopt) { + return at::_ops::_scaled_dot_product_flash_attention_backward::call(grad_out, query, key, value, out, logsumexp, cum_seq_q, cum_seq_k, max_q, max_k, dropout_p, is_causal, philox_seed, philox_offset, scale); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_spdiags_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_spdiags_native.h new file mode 100644 index 0000000000000000000000000000000000000000..2b094ab1ddf8183e3f902c4d9bbd55acb9682de8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_spdiags_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 & _spdiags_out(const at::Tensor & diagonals, const at::Tensor & offsets, at::IntArrayRef shape, c10::optional layout, at::Tensor & out); +TORCH_API at::Tensor spdiags(const at::Tensor & diagonals, const at::Tensor & offsets, at::IntArrayRef shape, c10::optional layout=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addr_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addr_native.h new file mode 100644 index 0000000000000000000000000000000000000000..7740fc800c3e5a9f3eacd32a4647ffee461cf5f1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addr_native.h @@ -0,0 +1,25 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor math_addr(const at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta=1, const at::Scalar & alpha=1); +TORCH_API at::Tensor & math_addr_out(const at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta, const at::Scalar & alpha, at::Tensor & out); +TORCH_API at::Tensor & addr_(at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta=1, const at::Scalar & alpha=1); +TORCH_API at::Tensor addr(const at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta=1, const at::Scalar & alpha=1); +TORCH_API at::Tensor & addr_out(const at::Tensor & self, const at::Tensor & vec1, const at::Tensor & vec2, const at::Scalar & beta, const at::Scalar & alpha, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atleast_1d_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atleast_1d_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ec584ce60f0ff0938de5c63119911c862253ef4d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atleast_1d_compositeimplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor atleast_1d(const at::Tensor & self); +TORCH_API ::std::vector atleast_1d(at::TensorList tensors); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_or_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_or_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d9d6a6494bfa59432661e638f3774a2118985287 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_or_cuda_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor bitwise_or(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_or_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_or_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & bitwise_or_(at::Tensor & self, const at::Tensor & other); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_xor_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_xor_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a3b2cd3cae43c69fcc3d4abe8d2f92d09c20d9d0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/bitwise_xor_cpu_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor bitwise_xor(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_xor_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & bitwise_xor_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & bitwise_xor_(at::Tensor & self, const at::Tensor & other); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cauchy_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cauchy_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a5562df3361baf619994e16f49b9eef316c8abe9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cauchy_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 cauchy(const at::Tensor & self, double median=0, double sigma=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & cauchy_out(at::Tensor & out, const at::Tensor & self, double median=0, double sigma=1, c10::optional generator=c10::nullopt); +TORCH_API at::Tensor & cauchy_outf(const at::Tensor & self, double median, double sigma, c10::optional generator, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ccol_indices_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ccol_indices_native.h new file mode 100644 index 0000000000000000000000000000000000000000..573ecde04db05f34f4b683bbc70652239a636ebf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ccol_indices_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 ccol_indices_default(const at::Tensor & self); +TORCH_API at::Tensor ccol_indices_sparse_csr(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..86e69da0fe82f3e354c34d186d04b41ca64fd350 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/clamp_cpu_dispatch.h @@ -0,0 +1,30 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor clamp(const at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor & clamp_out(at::Tensor & out, const at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor & clamp_outf(const at::Tensor & self, const c10::optional & min, const c10::optional & max, at::Tensor & out); +TORCH_API at::Tensor & clamp_(at::Tensor & self, const c10::optional & min, const c10::optional & max=c10::nullopt); +TORCH_API at::Tensor clamp(const at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); +TORCH_API at::Tensor & clamp_out(at::Tensor & out, const at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); +TORCH_API at::Tensor & clamp_outf(const at::Tensor & self, const c10::optional & min, const c10::optional & max, at::Tensor & out); +TORCH_API at::Tensor & clamp_(at::Tensor & self, const c10::optional & min={}, const c10::optional & max={}); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cos_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cos_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..16bf9233c1daeef3db4864f43d60175023d0953d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cos_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 cos(const at::Tensor & self); +TORCH_API at::Tensor & cos_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & cos_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & cos_(at::Tensor & self); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/equal.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/equal.h new file mode 100644 index 0000000000000000000000000000000000000000..8e2eb3f5c371f5a95d7be6033071dd5b3e75a2fd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/equal.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::equal(Tensor self, Tensor other) -> bool +inline bool equal(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::equal::call(self, other); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_native.h new file mode 100644 index 0000000000000000000000000000000000000000..8f851525b37153864fdbdb784a5ffef545477700 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/expm1_native.h @@ -0,0 +1,29 @@ +#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_expm1_out : public at::meta::structured_expm1 { +void impl(const at::Tensor & self, const at::Tensor & out); +}; +TORCH_API at::Tensor expm1_sparse(const at::Tensor & self); +TORCH_API at::Tensor & expm1_sparse_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & expm1_sparse_(at::Tensor & self); +TORCH_API at::Tensor expm1_sparse_csr(const at::Tensor & self); +TORCH_API at::Tensor & expm1_sparse_csr_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & expm1_sparse_csr_(at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ifft_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ifft_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ed2e51ce6e0fd95ca511a6e266846e96aaff79ad --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fft_ifft_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_ifft(const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor fft_ifft_symint(const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_ifft_out(at::Tensor & out, const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_ifft_outf(const at::Tensor & self, c10::optional n, int64_t dim, c10::optional norm, at::Tensor & out); +TORCH_API at::Tensor & fft_ifft_symint_out(at::Tensor & out, const at::Tensor & self, c10::optional n=c10::nullopt, int64_t dim=-1, c10::optional norm=c10::nullopt); +TORCH_API at::Tensor & fft_ifft_symint_outf(const at::Tensor & self, c10::optional n, int64_t 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/flip_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/flip_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..eb8d45444e268ab33c8d32d73d98721a7ebb7635 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/flip_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 flip { + using schema = at::Tensor (const at::Tensor &, at::IntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::flip") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "flip(Tensor self, int[] dims) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::IntArrayRef dims); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef dims); +}; + +struct TORCH_API flip_out { + using schema = at::Tensor & (const at::Tensor &, at::IntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::flip") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "flip.out(Tensor self, int[] dims, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::IntArrayRef dims, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef dims, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/frobenius_norm_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/frobenius_norm_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5ad00b4311a2fadc2c4f5fcfd5223ea427d41fa1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/frobenius_norm_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 at::Tensor frobenius_norm(const at::Tensor & self, at::IntArrayRef dim, bool keepdim=false); +TORCH_API at::Tensor & frobenius_norm_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef dim, bool keepdim=false); +TORCH_API at::Tensor & frobenius_norm_outf(const at::Tensor & self, at::IntArrayRef dim, bool keepdim, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..1e4ae606b28e3053eda5e549dbf291d68c2174ca --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_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 gather_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, int64_t, 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::gather_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "gather_backward(Tensor grad, Tensor self, int dim, Tensor index, bool sparse_grad) -> Tensor") + static at::Tensor call(const at::Tensor & grad, const at::Tensor & self, int64_t dim, const at::Tensor & index, bool sparse_grad); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad, const at::Tensor & self, int64_t dim, const at::Tensor & index, bool sparse_grad); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardswish_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardswish_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d4793bce95907be7bab651ba176c568b5ed02e1e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardswish_cpu_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor hardswish(const at::Tensor & self); +TORCH_API at::Tensor & hardswish_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & hardswish_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & hardswish_(at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss.h new file mode 100644 index 0000000000000000000000000000000000000000..5c04c55c5bacd39990913282d0802d5fbb74b7a1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss.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::huber_loss.out(Tensor self, Tensor target, int reduction=Mean, float delta=1.0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & huber_loss_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & target, int64_t reduction=at::Reduction::Mean, double delta=1.0) { + return at::_ops::huber_loss_out::call(self, target, reduction, delta, out); +} +// aten::huber_loss.out(Tensor self, Tensor target, int reduction=Mean, float delta=1.0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & huber_loss_outf(const at::Tensor & self, const at::Tensor & target, int64_t reduction, double delta, at::Tensor & out) { + return at::_ops::huber_loss_out::call(self, target, reduction, delta, out); +} + +// aten::huber_loss(Tensor self, Tensor target, int reduction=Mean, float delta=1.0) -> Tensor +inline at::Tensor huber_loss(const at::Tensor & self, const at::Tensor & target, int64_t reduction=at::Reduction::Mean, double delta=1.0) { + return at::_ops::huber_loss::call(self, target, reduction, delta); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igamma_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igamma_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..8b8b3afc2f1f5d95c8dc5e7814c1a8b5e50ac9f7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igamma_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_igamma : public TensorIteratorBase { + + + void meta(const at::Tensor & self, const at::Tensor & other); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_copy_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_copy_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f3c852ed8eb41ef9a3d24690b0d41a599430fa45 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/index_copy_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 index_copy(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source); +TORCH_API at::Tensor & index_copy_out(at::Tensor & out, const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source); +TORCH_API at::Tensor & index_copy_outf(const at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source, at::Tensor & out); +TORCH_API at::Tensor & index_copy_(at::Tensor & self, int64_t dim, const at::Tensor & index, const at::Tensor & source); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3fbc282ab518dc9d8348d5042c79e3a6ad580cad --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_cuda_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor leaky_relu(const at::Tensor & self, const at::Scalar & negative_slope=0.01); +TORCH_API at::Tensor & leaky_relu_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & negative_slope=0.01); +TORCH_API at::Tensor & leaky_relu_outf(const at::Tensor & self, const at::Scalar & negative_slope, at::Tensor & out); +TORCH_API at::Tensor & leaky_relu_(at::Tensor & self, const at::Scalar & negative_slope=0.01); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lift_fresh_copy.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lift_fresh_copy.h new file mode 100644 index 0000000000000000000000000000000000000000..b33086e5a1c5d0d89f4e11bdc285f5eb98e75ee1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/lift_fresh_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::lift_fresh_copy(Tensor self) -> Tensor +inline at::Tensor lift_fresh_copy(const at::Tensor & self) { + return at::_ops::lift_fresh_copy::call(self); +} + +// aten::lift_fresh_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & lift_fresh_copy_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::lift_fresh_copy_out::call(self, out); +} +// aten::lift_fresh_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & lift_fresh_copy_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::lift_fresh_copy_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cond_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cond_native.h new file mode 100644 index 0000000000000000000000000000000000000000..2df3c211d5c9074c6b6bf76ae78f8bc068c58f94 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_cond_native.h @@ -0,0 +1,24 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor linalg_cond(const at::Tensor & self, const c10::optional & p=c10::nullopt); +TORCH_API at::Tensor & linalg_cond_out(const at::Tensor & self, const c10::optional & p, at::Tensor & out); +TORCH_API at::Tensor linalg_cond(const at::Tensor & self, c10::string_view p); +TORCH_API at::Tensor & linalg_cond_out(const at::Tensor & self, c10::string_view p, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigvalsh.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigvalsh.h new file mode 100644 index 0000000000000000000000000000000000000000..e5ba455f87acbdcb4c3b44a90f057759b7ffa5af --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_eigvalsh.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::linalg_eigvalsh(Tensor self, str UPLO="L") -> Tensor +inline at::Tensor linalg_eigvalsh(const at::Tensor & self, c10::string_view UPLO="L") { + return at::_ops::linalg_eigvalsh::call(self, UPLO); +} + +// aten::linalg_eigvalsh.out(Tensor self, str UPLO="L", *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_eigvalsh_out(at::Tensor & out, const at::Tensor & self, c10::string_view UPLO="L") { + return at::_ops::linalg_eigvalsh_out::call(self, UPLO, out); +} +// aten::linalg_eigvalsh.out(Tensor self, str UPLO="L", *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_eigvalsh_outf(const at::Tensor & self, c10::string_view UPLO, at::Tensor & out) { + return at::_ops::linalg_eigvalsh_out::call(self, UPLO, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e06853c7cd10ba29e532f96be0e71d2765c4d6e7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_factor_compositeimplicitautograd_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API ::std::tuple linalg_lu_factor(const at::Tensor & A, bool pivot=true); +TORCH_API ::std::tuple linalg_lu_factor_out(at::Tensor & LU, at::Tensor & pivots, const at::Tensor & A, bool pivot=true); +TORCH_API ::std::tuple linalg_lu_factor_outf(const at::Tensor & A, bool pivot, at::Tensor & LU, at::Tensor & pivots); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b56d85b93666fca706e614c4f58f609d728e8311 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_solve_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 at::Tensor linalg_solve(const at::Tensor & A, const at::Tensor & B, bool left=true); +TORCH_API at::Tensor & linalg_solve_out(at::Tensor & out, const at::Tensor & A, const at::Tensor & B, bool left=true); +TORCH_API at::Tensor & linalg_solve_outf(const at::Tensor & A, const at::Tensor & B, bool left, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vecdot_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vecdot_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..fe92df1a38926e7f15fb0f2ab606326f16eef5cd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vecdot_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API linalg_vecdot { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::linalg_vecdot") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_vecdot(Tensor x, Tensor y, *, int dim=-1) -> Tensor") + static at::Tensor call(const at::Tensor & x, const at::Tensor & y, int64_t dim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x, const at::Tensor & y, int64_t dim); +}; + +struct TORCH_API linalg_vecdot_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, int64_t, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::linalg_vecdot") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "linalg_vecdot.out(Tensor x, Tensor y, *, int dim=-1, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & x, const at::Tensor & y, int64_t dim, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & x, const at::Tensor & y, int64_t dim, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log2_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log2_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..902a17815d49cba9aca582a067a35e8d6e6ab38e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log2_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 log2 { + 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::log2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "log2(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 log2_ { + 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::log2_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "log2_(Tensor(a!) self) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self); +}; + +struct TORCH_API log2_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::log2") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "log2.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matmul_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matmul_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..066a940d2fe6a8338d6e0ff1c52fd1c6962eb9e5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/matmul_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 matmul { + 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::matmul") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "matmul(Tensor self, Tensor other) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & other); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other); +}; + +struct TORCH_API matmul_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::matmul") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "matmul.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mode_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mode_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..bde301cc371ac8c109799990542656f18b6b3d98 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mode_cpu_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API ::std::tuple mode(const at::Tensor & self, int64_t dim=-1, bool keepdim=false); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss_forward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss_forward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..1d00b1584906c347aed0edfe40accd01f634b393 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss_forward_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 multilabel_margin_loss_forward_output { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, int64_t, 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::multilabel_margin_loss_forward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "output") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "multilabel_margin_loss_forward.output(Tensor self, Tensor target, int reduction, *, Tensor(a!) output, Tensor(b!) is_target) -> (Tensor(a!), Tensor(b!))") + static ::std::tuple call(const at::Tensor & self, const at::Tensor & target, int64_t reduction, at::Tensor & output, at::Tensor & is_target); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & target, int64_t reduction, at::Tensor & output, at::Tensor & is_target); +}; + +struct TORCH_API multilabel_margin_loss_forward { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::multilabel_margin_loss_forward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "multilabel_margin_loss_forward(Tensor self, Tensor target, int reduction) -> (Tensor output, Tensor is_target)") + static ::std::tuple call(const at::Tensor & self, const at::Tensor & target, int64_t reduction); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & target, int64_t reduction); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmedian_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmedian_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..5cb13443a4949c8269ba481b2ea94bd24abb6648 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nanmedian_cpu_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor nanmedian(const at::Tensor & self); +TORCH_API ::std::tuple nanmedian_out(at::Tensor & values, at::Tensor & indices, const at::Tensor & self, int64_t dim, bool keepdim=false); +TORCH_API ::std::tuple nanmedian_outf(const at::Tensor & self, int64_t dim, bool keepdim, at::Tensor & values, at::Tensor & indices); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/negative_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/negative_native.h new file mode 100644 index 0000000000000000000000000000000000000000..116d853c013af0f418f9c200e7fbd60120306ee8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/negative_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor negative(const at::Tensor & self); +TORCH_API at::Tensor & negative_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & negative_(at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_forward_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_forward_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c1dea428cbaec8467e3d3fc780c5c8cb614d937e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_forward_meta_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 meta { + +TORCH_API ::std::tuple nll_loss_forward(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index); +TORCH_API ::std::tuple nll_loss_forward_symint(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index); +TORCH_API ::std::tuple nll_loss_forward_out(at::Tensor & output, at::Tensor & total_weight, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index); +TORCH_API ::std::tuple nll_loss_forward_outf(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, at::Tensor & output, at::Tensor & total_weight); +TORCH_API ::std::tuple nll_loss_forward_symint_out(at::Tensor & output, at::Tensor & total_weight, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index); +TORCH_API ::std::tuple nll_loss_forward_symint_outf(const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, at::Tensor & output, at::Tensor & total_weight); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/permute_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/permute_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..ee1b863dd039c66397d389328d123d093b63596c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/permute_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 permute { + using schema = at::Tensor (const at::Tensor &, at::IntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::permute") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "permute(Tensor(a) self, int[] dims) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, at::IntArrayRef dims); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef dims); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/resize_as_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/resize_as_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..15a9cc87f8a2155a47eb8c6611bfdf85454cc376 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/resize_as_compositeexplicitautograd_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor resize_as(const at::Tensor & self, const at::Tensor & the_template, c10::optional memory_format=c10::nullopt); +TORCH_API const at::Tensor & resize_as_out(const at::Tensor & out, const at::Tensor & self, const at::Tensor & the_template, c10::optional memory_format=c10::nullopt); +TORCH_API const at::Tensor & resize_as_outf(const at::Tensor & self, const at::Tensor & the_template, c10::optional memory_format, const at::Tensor & out); +TORCH_API const at::Tensor & resize_as_(const at::Tensor & self, const at::Tensor & the_template, c10::optional memory_format=c10::nullopt); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/row_indices_copy_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/row_indices_copy_native.h new file mode 100644 index 0000000000000000000000000000000000000000..7dd0f1ad8f6e65c6e258bfa9f7d9d1c22f0e2841 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/row_indices_copy_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor & row_indices_copy_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor row_indices_copy(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sgn_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sgn_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2e021d72923e3f2d6510dfd2c38f6bb3b66ab42f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sgn_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 sgn(const at::Tensor & self); +TORCH_API at::Tensor & sgn_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & sgn_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & sgn_(at::Tensor & self); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sign_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sign_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d97da238b6870f524914553bd83d323dbfa55a16 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sign_cpu_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor sign(const at::Tensor & self); +TORCH_API at::Tensor & sign_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & sign_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & sign_(at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sin_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sin_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2ffca294221ef2c712e4d57eb1cbc9582946c748 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sin_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 sin(const at::Tensor & self); +TORCH_API at::Tensor & sin_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & sin_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & sin_(at::Tensor & self); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slogdet.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slogdet.h new file mode 100644 index 0000000000000000000000000000000000000000..daabfb8d2c75f52b71b175344830f54d15f21c3c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slogdet.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::slogdet(Tensor self) -> (Tensor sign, Tensor logabsdet) +inline ::std::tuple slogdet(const at::Tensor & self) { + return at::_ops::slogdet::call(self); +} + +// aten::slogdet.out(Tensor self, *, Tensor(a!) sign, Tensor(b!) logabsdet) -> (Tensor(a!) sign, Tensor(b!) logabsdet) +inline ::std::tuple slogdet_out(at::Tensor & sign, at::Tensor & logabsdet, const at::Tensor & self) { + return at::_ops::slogdet_out::call(self, sign, logabsdet); +} +// aten::slogdet.out(Tensor self, *, Tensor(a!) sign, Tensor(b!) logabsdet) -> (Tensor(a!) sign, Tensor(b!) logabsdet) +inline ::std::tuple slogdet_outf(const at::Tensor & self, at::Tensor & sign, at::Tensor & logabsdet) { + return at::_ops::slogdet_out::call(self, sign, logabsdet); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slow_conv_transpose2d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slow_conv_transpose2d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..1f387b974ebc9a2ccddd2d74b2695cc48bfe2793 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slow_conv_transpose2d_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 slow_conv_transpose2d_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, const c10::optional &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::slow_conv_transpose2d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "slow_conv_transpose2d.out(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias=None, SymInt[2] stride=1, SymInt[2] padding=0, SymInt[2] output_padding=0, SymInt[2] dilation=1, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef dilation, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef dilation, at::Tensor & out); +}; + +struct TORCH_API slow_conv_transpose2d { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, const c10::optional &, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::slow_conv_transpose2d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "slow_conv_transpose2d(Tensor self, Tensor weight, SymInt[2] kernel_size, Tensor? bias=None, SymInt[2] stride=1, SymInt[2] padding=0, SymInt[2] output_padding=0, SymInt[2] dilation=1) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef dilation); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & weight, c10::SymIntArrayRef kernel_size, const c10::optional & bias, c10::SymIntArrayRef stride, c10::SymIntArrayRef padding, c10::SymIntArrayRef output_padding, c10::SymIntArrayRef dilation); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_backward_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_backward_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b31cf7d0ed110f9532c2ef00d857f79075a06d2b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/smooth_l1_loss_backward_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 & smooth_l1_loss_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double beta); +TORCH_API at::Tensor & smooth_l1_loss_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double beta, at::Tensor & grad_input); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erf_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erf_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..34da262406840e4ff06e1bb0dc8ee2aeb6d1e668 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erf_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 special_erf { + 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::special_erf") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_erf(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 special_erf_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::special_erf") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_erf.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfc_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfc_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..c28db5e36748318010c5cda2d4f7c1d67e6af0c9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfc_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 special_erfc { + 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::special_erfc") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_erfc(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 special_erfc_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::special_erfc") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_erfc.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sqrt_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sqrt_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ff00aaa2c54ea729e7115e4febd79b130801ac2a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sqrt_cuda_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor sqrt(const at::Tensor & self); +TORCH_API at::Tensor & sqrt_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & sqrt_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & sqrt_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sum_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sum_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a7354a2b4db32afea9e4de1c748329f7503ae74d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sum_cpu_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor sum(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & sum_out(at::Tensor & out, const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim=false, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & sum_outf(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_along_dim.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_along_dim.h new file mode 100644 index 0000000000000000000000000000000000000000..7ff0573769aaed9e2ff98857c3f7a41d2844e98e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_along_dim.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::take_along_dim.out(Tensor self, Tensor indices, int? dim=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & take_along_dim_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, c10::optional dim=c10::nullopt) { + return at::_ops::take_along_dim_out::call(self, indices, dim, out); +} +// aten::take_along_dim.out(Tensor self, Tensor indices, int? dim=None, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & take_along_dim_outf(const at::Tensor & self, const at::Tensor & indices, c10::optional dim, at::Tensor & out) { + return at::_ops::take_along_dim_out::call(self, indices, dim, out); +} + +// aten::take_along_dim(Tensor self, Tensor indices, int? dim=None) -> Tensor +inline at::Tensor take_along_dim(const at::Tensor & self, const at::Tensor & indices, c10::optional dim=c10::nullopt) { + return at::_ops::take_along_dim::call(self, indices, dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..1a01be8a37682b3b42f4b9dc58c0783e82005f40 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_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_tanh : public TensorIteratorBase { + + + void meta(const at::Tensor & self); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/topk_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/topk_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..fe9167f80f33edb9dc1d897e0a2053a6eee6deee --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/topk_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 ::std::tuple topk(const at::Tensor & self, int64_t k, int64_t dim=-1, bool largest=true, bool sorted=true); +TORCH_API ::std::tuple topk_symint(const at::Tensor & self, c10::SymInt k, int64_t dim=-1, bool largest=true, bool sorted=true); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/triplet_margin_loss_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/triplet_margin_loss_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1e55bb6fc7c2369c4bd2fd380be128d99dc61be2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/triplet_margin_loss_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 triplet_margin_loss(const at::Tensor & anchor, const at::Tensor & positive, const at::Tensor & negative, double margin=1.0, double p=2, double eps=1e-06, bool swap=false, int64_t reduction=at::Reduction::Mean); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/trunc_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/trunc_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..e78f131e58fec111068aa42095c6bbcc219d2370 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/trunc_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_trunc : public TensorIteratorBase { + + + void meta(const at::Tensor & self); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unflatten_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unflatten_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..c383679a6e438e308b5709b2c36f0483e5c6b1bd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unflatten_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 unflatten_int { + using schema = at::Tensor (const at::Tensor &, int64_t, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::unflatten") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "int") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "unflatten.int(Tensor(a) self, int dim, SymInt[] sizes) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, int64_t dim, c10::SymIntArrayRef sizes); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, c10::SymIntArrayRef sizes); +}; + +struct TORCH_API unflatten_Dimname { + using schema = at::Tensor (const at::Tensor &, at::Dimname, c10::SymIntArrayRef, at::DimnameList); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::unflatten") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Dimname") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "unflatten.Dimname(Tensor(a) self, Dimname dim, SymInt[] sizes, Dimname[] names) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, at::Dimname dim, c10::SymIntArrayRef sizes, at::DimnameList names); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Dimname dim, c10::SymIntArrayRef sizes, at::DimnameList names); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_linear1d_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_linear1d_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2e63c568895f557ebdbc349c036af244251e4ddf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_linear1d_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_linear1d(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor upsample_linear1d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor & upsample_linear1d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor & upsample_linear1d_outf(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales, at::Tensor & out); +TORCH_API at::Tensor & upsample_linear1d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales=c10::nullopt); +TORCH_API at::Tensor & upsample_linear1d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..aff8419a7157e56037b2c777366e3e021eed67c2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/upsample_trilinear3d_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 upsample_trilinear3d(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor upsample_trilinear3d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & upsample_trilinear3d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & upsample_trilinear3d_outf(const at::Tensor & self, at::IntArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); +TORCH_API at::Tensor & upsample_trilinear3d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & upsample_trilinear3d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, bool align_corners, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/var_mean_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/var_mean_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f061f9a90548001c084be4a578524544e7e6558a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/var_mean_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 var_mean_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, const c10::optional & correction=c10::nullopt, bool keepdim=false); +TORCH_API ::std::tuple var_mean_outf(const at::Tensor & self, at::OptionalIntArrayRef dim, const c10::optional & correction, bool keepdim, 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/view_as_complex_copy.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_copy.h new file mode 100644 index 0000000000000000000000000000000000000000..a668388c1bc79d2969a513978b3be51ca4a3ee0a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_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::view_as_complex_copy(Tensor self) -> Tensor +inline at::Tensor view_as_complex_copy(const at::Tensor & self) { + return at::_ops::view_as_complex_copy::call(self); +} + +// aten::view_as_complex_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & view_as_complex_copy_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::view_as_complex_copy_out::call(self, out); +} +// aten::view_as_complex_copy.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & view_as_complex_copy_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::view_as_complex_copy_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_copy_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_copy_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9c1fac4b58f54721fccdd1678cf1a57067388a4a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_copy_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 view_as_complex_copy(const at::Tensor & self); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b867f9f4f550b2bbb12b9b494a27af850fc87c46 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/view_as_complex_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 view_as_complex(const at::Tensor & self); + +} // namespace cpu +} // namespace at