diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Double.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Double.h new file mode 100644 index 0000000000000000000000000000000000000000..d80d2043e36bb2d2bf3743b4f5cacf5ff91a263a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Double.h @@ -0,0 +1,30 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_cast_Double(Tensor self, bool non_blocking=False) -> Tensor +inline at::Tensor _cast_Double(const at::Tensor & self, bool non_blocking=false) { + return at::_ops::_cast_Double::call(self, non_blocking); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cholesky_solve_helper.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cholesky_solve_helper.h new file mode 100644 index 0000000000000000000000000000000000000000..811beb2d74d6b7415a76fee90b3082b79c2d63a5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cholesky_solve_helper.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::_cholesky_solve_helper(Tensor self, Tensor A, bool upper) -> Tensor +inline at::Tensor _cholesky_solve_helper(const at::Tensor & self, const at::Tensor & A, bool upper) { + return at::_ops::_cholesky_solve_helper::call(self, A, upper); +} + +// aten::_cholesky_solve_helper.out(Tensor self, Tensor A, bool upper, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _cholesky_solve_helper_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & A, bool upper) { + return at::_ops::_cholesky_solve_helper_out::call(self, A, upper, out); +} +// aten::_cholesky_solve_helper.out(Tensor self, Tensor A, bool upper, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & _cholesky_solve_helper_outf(const at::Tensor & self, const at::Tensor & A, bool upper, at::Tensor & out) { + return at::_ops::_cholesky_solve_helper_out::call(self, A, upper, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..deaea95755d4fe1e258d15dfeb6e2b5f316bf9a7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_embedding_bag_forward_only_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 _embedding_bag_forward_only { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, bool, int64_t, bool, const c10::optional &, bool, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_embedding_bag_forward_only") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_embedding_bag_forward_only(Tensor weight, Tensor indices, Tensor offsets, bool scale_grad_by_freq=False, int mode=0, bool sparse=False, Tensor? per_sample_weights=None, bool include_last_offset=False, int padding_idx=-1) -> (Tensor, Tensor, Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq, int64_t mode, bool sparse, const c10::optional & per_sample_weights, bool include_last_offset, int64_t padding_idx); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq, int64_t mode, bool sparse, const c10::optional & per_sample_weights, bool include_last_offset, int64_t padding_idx); +}; + +struct TORCH_API _embedding_bag_forward_only_out { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, bool, int64_t, bool, const c10::optional &, bool, int64_t, at::Tensor &, at::Tensor &, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_embedding_bag_forward_only") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_embedding_bag_forward_only.out(Tensor weight, Tensor indices, Tensor offsets, bool scale_grad_by_freq=False, int mode=0, bool sparse=False, Tensor? per_sample_weights=None, bool include_last_offset=False, int padding_idx=-1, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!))") + static ::std::tuple call(const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq, int64_t mode, bool sparse, const c10::optional & per_sample_weights, bool include_last_offset, int64_t padding_idx, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & weight, const at::Tensor & indices, const at::Tensor & offsets, bool scale_grad_by_freq, int64_t mode, bool sparse, const c10::optional & per_sample_weights, bool include_last_offset, int64_t padding_idx, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_acos_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_acos_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3df8eb38caae007b55c38fa214fe8fb426ac5c7f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_acos_cuda_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::vector _foreach_acos(at::TensorList self); +TORCH_API void _foreach_acos_(at::TensorList self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_floor_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_floor_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b87f4ea671785326b61c63e983bf4357c7fc8e5b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_floor_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 void _foreach_floor_out(at::TensorList out, at::TensorList self); +TORCH_API void _foreach_floor_outf(at::TensorList self, at::TensorList out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log10_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log10_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..10dfa7346f215ef3737bb7b577b4ec098908f137 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log10_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_log10(at::TensorList self); +TORCH_API void _foreach_log10_(at::TensorList self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_bin_edges_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_bin_edges_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0fa1dbf19c80e1a4e60db8dbf6a5d957e0881cb0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_bin_edges_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 void _histogramdd_bin_edges_out(at::TensorList out, const at::Tensor & self, at::IntArrayRef bins, c10::optional> range=c10::nullopt, const c10::optional & weight={}, bool density=false); +TORCH_API void _histogramdd_bin_edges_outf(const at::Tensor & self, at::IntArrayRef bins, c10::optional> range, const c10::optional & weight, bool density, at::TensorList out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_tensors_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_tensors_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..bc4a172b23e4e9121b631a6bde1e62101913d55c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_tensors_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 _histogramdd_from_bin_tensors(const at::Tensor & self, at::TensorList bins, const c10::optional & weight={}, bool density=false); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_mask_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_mask_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..04b76176dd9471dc47ce600ac292b388b7a0ee9b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_from_mask_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 _nested_tensor_from_mask { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_nested_tensor_from_mask") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_tensor_from_mask(Tensor t, Tensor mask, bool mask_check=True) -> Tensor") + static at::Tensor call(const at::Tensor & t, const at::Tensor & mask, bool mask_check); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & t, const at::Tensor & mask, bool mask_check); +}; + +struct TORCH_API _nested_tensor_from_mask_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, bool, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_nested_tensor_from_mask") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_tensor_from_mask.out(Tensor t, Tensor mask, bool mask_check=True, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & t, const at::Tensor & mask, bool mask_check, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & t, const at::Tensor & mask, bool mask_check, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_size_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_size_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3c504a0f1708fd668b2f6366accb9817a75e36e9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_nested_tensor_size_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 _nested_tensor_size { + 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_tensor_size") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_tensor_size(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 _nested_tensor_size_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::_nested_tensor_size") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_nested_tensor_size.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/_pack_padded_sequence_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pack_padded_sequence_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..94a9000ced75aba2e3f40d463d08cc5c0c8bb5e3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pack_padded_sequence_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 ::std::tuple _pack_padded_sequence(const at::Tensor & input, const at::Tensor & lengths, bool batch_first); +TORCH_API ::std::tuple _pack_padded_sequence_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & input, const at::Tensor & lengths, bool batch_first); +TORCH_API ::std::tuple _pack_padded_sequence_outf(const at::Tensor & input, const at::Tensor & lengths, bool batch_first, 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/_pad_packed_sequence_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_packed_sequence_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b04f1f42d3849e797a717ede53b9ba0a1103dae7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_packed_sequence_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 _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 native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_mm.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_mm.h new file mode 100644 index 0000000000000000000000000000000000000000..ed618ecdc69b69d8259999a08cbad17d3b30c99d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_mm.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::_scaled_mm(Tensor self, Tensor mat2, *, Tensor? bias=None, ScalarType? out_dtype=None, Tensor? scale_a=None, Tensor? scale_b=None, Tensor? scale_result=None, bool use_fast_accum=False) -> (Tensor, Tensor) +inline ::std::tuple _scaled_mm(const at::Tensor & self, const at::Tensor & mat2, const c10::optional & bias={}, c10::optional out_dtype=c10::nullopt, const c10::optional & scale_a={}, const c10::optional & scale_b={}, const c10::optional & scale_result={}, bool use_fast_accum=false) { + return at::_ops::_scaled_mm::call(self, mat2, bias, out_dtype, scale_a, scale_b, scale_result, use_fast_accum); +} + +// aten::_scaled_mm.out(Tensor self, Tensor mat2, *, Tensor? bias=None, ScalarType? out_dtype=None, Tensor? scale_a=None, Tensor? scale_b=None, Tensor? scale_result=None, bool use_fast_accum=False, Tensor(a!) out, Tensor(b!) out_amax) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple _scaled_mm_out(at::Tensor & out, at::Tensor & out_amax, const at::Tensor & self, const at::Tensor & mat2, const c10::optional & bias={}, c10::optional out_dtype=c10::nullopt, const c10::optional & scale_a={}, const c10::optional & scale_b={}, const c10::optional & scale_result={}, bool use_fast_accum=false) { + return at::_ops::_scaled_mm_out::call(self, mat2, bias, out_dtype, scale_a, scale_b, scale_result, use_fast_accum, out, out_amax); +} +// aten::_scaled_mm.out(Tensor self, Tensor mat2, *, Tensor? bias=None, ScalarType? out_dtype=None, Tensor? scale_a=None, Tensor? scale_b=None, Tensor? scale_result=None, bool use_fast_accum=False, Tensor(a!) out, Tensor(b!) out_amax) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple _scaled_mm_outf(const at::Tensor & self, const at::Tensor & mat2, const c10::optional & bias, c10::optional out_dtype, const c10::optional & scale_a, const c10::optional & scale_b, const c10::optional & scale_result, bool use_fast_accum, at::Tensor & out, at::Tensor & out_amax) { + return at::_ops::_scaled_mm_out::call(self, mat2, bias, out_dtype, scale_a, scale_b, scale_result, use_fast_accum, out, out_amax); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_segment_reduce_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_segment_reduce_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..5d8b15a18c9c63bdfa9032f9bdc3df55205fcfd3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_segment_reduce_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API _segment_reduce_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, c10::string_view, const c10::optional &, const c10::optional &, int64_t, const c10::optional &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_segment_reduce_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_segment_reduce_backward(Tensor grad, Tensor output, Tensor data, str reduce, *, Tensor? lengths=None, Tensor? offsets=None, int axis=0, Scalar? initial=None) -> Tensor") + static at::Tensor call(const at::Tensor & grad, const at::Tensor & output, const at::Tensor & data, c10::string_view reduce, const c10::optional & lengths, const c10::optional & offsets, int64_t axis, const c10::optional & initial); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad, const at::Tensor & output, const at::Tensor & data, c10::string_view reduce, const c10::optional & lengths, const c10::optional & offsets, int64_t axis, const c10::optional & initial); +}; + +struct TORCH_API _segment_reduce_backward_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Tensor &, c10::string_view, const c10::optional &, const c10::optional &, int64_t, const 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::_segment_reduce_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_segment_reduce_backward.out(Tensor grad, Tensor output, Tensor data, str reduce, *, Tensor? lengths=None, Tensor? offsets=None, int axis=0, Scalar? initial=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad, const at::Tensor & output, const at::Tensor & data, c10::string_view reduce, const c10::optional & lengths, const c10::optional & offsets, int64_t axis, const c10::optional & initial, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad, const at::Tensor & output, const at::Tensor & data, c10::string_view reduce, const c10::optional & lengths, const c10::optional & offsets, int64_t axis, const c10::optional & initial, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_softmax_backward_data_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_softmax_backward_data_native.h new file mode 100644 index 0000000000000000000000000000000000000000..bc1b1c947e40ea5f2cbd025c284f3f34f08fe5d0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_softmax_backward_data_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 & _sparse_softmax_backward_data_out(const at::Tensor & grad_output, const at::Tensor & output, int64_t dim, const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor softmax_backward_sparse_cpu(const at::Tensor & grad_output, const at::Tensor & output, int64_t dim, const at::Tensor & self); +TORCH_API at::Tensor softmax_backward_sparse_cuda(const at::Tensor & grad_output, const at::Tensor & output, int64_t dim, const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_parallel_materialize.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_parallel_materialize.h new file mode 100644 index 0000000000000000000000000000000000000000..19def292a9494398c2d8646ab1ce2ed51e660fad --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_parallel_materialize.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::_test_parallel_materialize(Tensor self, int num_parallel, bool skip_first=False) -> Tensor +inline at::Tensor _test_parallel_materialize(const at::Tensor & self, int64_t num_parallel, bool skip_first=false) { + return at::_ops::_test_parallel_materialize::call(self, num_parallel, skip_first); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_string_default_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_string_default_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..97d6f8e304d423c9728fe445951e1b99f5755871 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_string_default_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 _test_string_default { + using schema = at::Tensor (const at::Tensor &, c10::string_view, 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::_test_string_default") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_test_string_default(Tensor dummy, str a=\"\\\"'\\\\\", str b='\"\\'\\\\') -> Tensor") + static at::Tensor call(const at::Tensor & dummy, c10::string_view a, c10::string_view b); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & dummy, c10::string_view a, c10::string_view b); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_cpu_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_cpu_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..f8578fb53b245764feb2713c327637b66784c121 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_cpu_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::vector _to_cpu(at::TensorList tensors); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csc_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csc_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..2531a9f5c9d9cb143f87002f43bf9eb6e3c71214 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csc_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & _to_sparse_csc_out(at::Tensor & out, const at::Tensor & self, c10::optional dense_dim=c10::nullopt); +TORCH_API at::Tensor & _to_sparse_csc_outf(const at::Tensor & self, c10::optional dense_dim, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csc_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csc_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c1d705d46b37c09eaf649306f371ffd46b2a9458 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_to_sparse_csc_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 & _to_sparse_csc_out(const at::Tensor & self, c10::optional dense_dim, at::Tensor & out); +TORCH_API at::Tensor dense_to_sparse_csc(const at::Tensor & self, c10::optional dense_dim=c10::nullopt); +TORCH_API at::Tensor coo_to_sparse_csc(const at::Tensor & self, c10::optional dense_dim=c10::nullopt); +TORCH_API at::Tensor sparse_compressed_to_sparse_csc(const at::Tensor & self, c10::optional dense_dim=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_transformer_encoder_layer_fwd_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_transformer_encoder_layer_fwd_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b50c4004cb24d0cc17e04e608bb1d6438441fab5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_transformer_encoder_layer_fwd_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor & _transformer_encoder_layer_fwd_out(at::Tensor & out, const at::Tensor & src, int64_t embed_dim, int64_t num_heads, const at::Tensor & qkv_weight, const at::Tensor & qkv_bias, const at::Tensor & proj_weight, const at::Tensor & proj_bias, bool use_gelu, bool norm_first, double eps, const at::Tensor & norm_weight_1, const at::Tensor & norm_bias_1, const at::Tensor & norm_weight_2, const at::Tensor & norm_bias_2, const at::Tensor & ffn_weight_1, const at::Tensor & ffn_bias_1, const at::Tensor & ffn_weight_2, const at::Tensor & ffn_bias_2, const c10::optional & mask={}, c10::optional mask_type=c10::nullopt); +TORCH_API at::Tensor & _transformer_encoder_layer_fwd_outf(const at::Tensor & src, int64_t embed_dim, int64_t num_heads, const at::Tensor & qkv_weight, const at::Tensor & qkv_bias, const at::Tensor & proj_weight, const at::Tensor & proj_bias, bool use_gelu, bool norm_first, double eps, const at::Tensor & norm_weight_1, const at::Tensor & norm_bias_1, const at::Tensor & norm_weight_2, const at::Tensor & norm_bias_2, const at::Tensor & ffn_weight_1, const at::Tensor & ffn_bias_1, const at::Tensor & ffn_weight_2, const at::Tensor & ffn_bias_2, const c10::optional & mask, c10::optional mask_type, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_ctc_loss_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_ctc_loss_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ad6d5abfc71a8e55a98d0cd4c1da6ce999413a71 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_ctc_loss_cuda_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API bool _use_cudnn_ctc_loss(const at::Tensor & log_probs, const at::Tensor & targets, at::IntArrayRef input_lengths, at::IntArrayRef target_lengths, int64_t blank); +TORCH_API bool _use_cudnn_ctc_loss(const at::Tensor & log_probs, const at::Tensor & targets, const at::Tensor & input_lengths, const at::Tensor & target_lengths, int64_t blank); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/angle_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/angle_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..675ed3503cb8b85d87939a4cee7e448f766ab08e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/angle_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor angle(const at::Tensor & self); +TORCH_API at::Tensor & angle_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & angle_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arange_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arange_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b216d46c5c12c01792ed16eea3c05f9a72650693 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arange_meta_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor & arange_out(at::Tensor & out, const at::Scalar & start, const at::Scalar & end, const at::Scalar & step); +TORCH_API at::Tensor & arange_outf(const at::Scalar & start, const at::Scalar & end, const at::Scalar & step, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2.h new file mode 100644 index 0000000000000000000000000000000000000000..d2612346820ee3961da75fe36de1021bb40b8140 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/atan2.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::atan2.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & atan2_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other) { + return at::_ops::atan2_out::call(self, other, out); +} +// aten::atan2.out(Tensor self, Tensor other, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & atan2_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out) { + return at::_ops::atan2_out::call(self, other, out); +} + +// aten::atan2(Tensor self, Tensor other) -> Tensor +inline at::Tensor atan2(const at::Tensor & self, const at::Tensor & other) { + return at::_ops::atan2::call(self, other); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..1c9c9b7f890356bdfec6b91bd9eb821a5434d588 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat_ops.h @@ -0,0 +1,61 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API cat { + using schema = at::Tensor (const at::ITensorListRef &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cat") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cat(Tensor[] tensors, int dim=0) -> Tensor") + static at::Tensor call(const at::ITensorListRef & tensors, int64_t dim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::ITensorListRef & tensors, int64_t dim); +}; + +struct TORCH_API cat_out { + using schema = at::Tensor & (const at::ITensorListRef &, 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::cat") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cat.out(Tensor[] tensors, int dim=0, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::ITensorListRef & tensors, int64_t dim, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::ITensorListRef & tensors, int64_t dim, at::Tensor & out); +}; + +struct TORCH_API cat_names { + using schema = at::Tensor (at::TensorList, at::Dimname); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cat") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cat.names(Tensor[] tensors, Dimname dim) -> Tensor") + static at::Tensor call(at::TensorList tensors, at::Dimname dim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList tensors, at::Dimname dim); +}; + +struct TORCH_API cat_names_out { + using schema = at::Tensor & (at::TensorList, at::Dimname, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cat") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "names_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cat.names_out(Tensor[] tensors, Dimname dim, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(at::TensorList tensors, at::Dimname dim, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::TensorList tensors, at::Dimname dim, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cauchy_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cauchy_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..151d77da185702ee87233c6eb248139660216086 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cauchy_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 cauchy_ { + using schema = at::Tensor & (at::Tensor &, double, 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::cauchy_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cauchy_(Tensor(a!) self, float median=0, float sigma=1, *, Generator? generator=None) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self, double median, double sigma, c10::optional generator); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self, double median, double sigma, c10::optional generator); +}; + +struct TORCH_API cauchy_out { + using schema = at::Tensor & (const at::Tensor &, double, 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::cauchy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cauchy.out(Tensor self, float median=0, float sigma=1, *, Generator? generator=None, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, double median, double sigma, c10::optional generator, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, double median, double sigma, c10::optional generator, at::Tensor & out); +}; + +struct TORCH_API cauchy { + using schema = at::Tensor (const at::Tensor &, double, 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::cauchy") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cauchy(Tensor self, float median=0, float sigma=1, *, Generator? generator=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, double median, double sigma, c10::optional generator); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, double median, double sigma, c10::optional generator); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummaxmin_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummaxmin_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3f671adb1560fb7a82940619a8c94b88b05bf610 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cummaxmin_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 cummaxmin_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::cummaxmin_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "cummaxmin_backward(Tensor grad, Tensor input, Tensor indices, int dim) -> Tensor") + static at::Tensor call(const at::Tensor & grad, const at::Tensor & input, const at::Tensor & indices, int64_t dim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad, const at::Tensor & input, const at::Tensor & indices, int64_t dim); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumsum_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumsum_native.h new file mode 100644 index 0000000000000000000000000000000000000000..803c31daeb9e5224fc725258762295f8f6a37bb4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cumsum_native.h @@ -0,0 +1,26 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_cumsum_out : public at::meta::structured_cumsum { +void impl(const at::Tensor & self, int64_t dim, c10::optional dtype, const at::Tensor & out); +}; +TORCH_API at::Tensor cumsum(const at::Tensor & self, at::Dimname dim, c10::optional dtype=c10::nullopt); +TORCH_API at::Tensor & cumsum_out(const at::Tensor & self, at::Dimname dim, c10::optional dtype, at::Tensor & out); +TORCH_API at::Tensor & cumsum_(at::Tensor & self, at::Dimname dim, c10::optional dtype=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/detach_copy_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/detach_copy_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..53153012488ed8e4e1a6868e3e0bc1cfb3d0ca93 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/detach_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 detach_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/empty_strided.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_strided.h new file mode 100644 index 0000000000000000000000000000000000000000..081d6c8b62ba44d0128a85b67a2d9c108f6ec4e1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/empty_strided.h @@ -0,0 +1,113 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::empty_strided(SymInt[] size, SymInt[] stride, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_strided(at::IntArrayRef size, at::IntArrayRef stride, at::TensorOptions options={}) { + return at::_ops::empty_strided::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +namespace symint { + template ::value>> + at::Tensor empty_strided(at::IntArrayRef size, at::IntArrayRef stride, at::TensorOptions options={}) { + return at::_ops::empty_strided::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); + } +} + +// aten::empty_strided(SymInt[] size, SymInt[] stride, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_strided(at::IntArrayRef size, at::IntArrayRef stride, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_strided::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), dtype, layout, device, pin_memory); +} +namespace symint { + template ::value>> + at::Tensor empty_strided(at::IntArrayRef size, at::IntArrayRef stride, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_strided::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), dtype, layout, device, pin_memory); + } +} + +// aten::empty_strided(SymInt[] size, SymInt[] stride, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_strided_symint(c10::SymIntArrayRef size, c10::SymIntArrayRef stride, at::TensorOptions options={}) { + return at::_ops::empty_strided::call(size, stride, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); +} +namespace symint { + template ::value>> + at::Tensor empty_strided(c10::SymIntArrayRef size, c10::SymIntArrayRef stride, at::TensorOptions options={}) { + return at::_ops::empty_strided::call(size, stride, c10::optTypeMetaToScalarType(options.dtype_opt()), options.layout_opt(), options.device_opt(), options.pinned_memory_opt()); + } +} + +// aten::empty_strided(SymInt[] size, SymInt[] stride, *, ScalarType? dtype=None, Layout? layout=None, Device? device=None, bool? pin_memory=None) -> Tensor +inline at::Tensor empty_strided_symint(c10::SymIntArrayRef size, c10::SymIntArrayRef stride, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_strided::call(size, stride, dtype, layout, device, pin_memory); +} +namespace symint { + template ::value>> + at::Tensor empty_strided(c10::SymIntArrayRef size, c10::SymIntArrayRef stride, c10::optional dtype, c10::optional layout, c10::optional device, c10::optional pin_memory) { + return at::_ops::empty_strided::call(size, stride, dtype, layout, device, pin_memory); + } +} + +// aten::empty_strided.out(SymInt[] size, SymInt[] stride, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_strided_out(at::Tensor & out, at::IntArrayRef size, at::IntArrayRef stride) { + return at::_ops::empty_strided_out::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), out); +} +namespace symint { + template ::value>> + at::Tensor & empty_strided_out(at::Tensor & out, at::IntArrayRef size, at::IntArrayRef stride) { + return at::_ops::empty_strided_out::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), out); + } +} + +// aten::empty_strided.out(SymInt[] size, SymInt[] stride, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_strided_outf(at::IntArrayRef size, at::IntArrayRef stride, at::Tensor & out) { + return at::_ops::empty_strided_out::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), out); +} +namespace symint { + template ::value>> + at::Tensor & empty_strided_outf(at::IntArrayRef size, at::IntArrayRef stride, at::Tensor & out) { + return at::_ops::empty_strided_out::call(c10::fromIntArrayRefSlow(size), c10::fromIntArrayRefSlow(stride), out); + } +} + +// aten::empty_strided.out(SymInt[] size, SymInt[] stride, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_strided_symint_out(at::Tensor & out, c10::SymIntArrayRef size, c10::SymIntArrayRef stride) { + return at::_ops::empty_strided_out::call(size, stride, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_strided_out(at::Tensor & out, c10::SymIntArrayRef size, c10::SymIntArrayRef stride) { + return at::_ops::empty_strided_out::call(size, stride, out); + } +} + +// aten::empty_strided.out(SymInt[] size, SymInt[] stride, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & empty_strided_symint_outf(c10::SymIntArrayRef size, c10::SymIntArrayRef stride, at::Tensor & out) { + return at::_ops::empty_strided_out::call(size, stride, out); +} +namespace symint { + template ::value>> + at::Tensor & empty_strided_outf(c10::SymIntArrayRef size, c10::SymIntArrayRef stride, at::Tensor & out) { + return at::_ops::empty_strided_out::call(size, stride, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..28541d74214abc405ba8655c6a0c6f16ac0b3df4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_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 floor(const at::Tensor & self); +TORCH_API at::Tensor & floor_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & floor_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & floor_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_divide_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_divide_native.h new file mode 100644 index 0000000000000000000000000000000000000000..b065f5df5d03361a5055acbfdf678398a4d6d4e2 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/floor_divide_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 + + +namespace at { +namespace native { +TORCH_API at::Tensor floor_divide(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & floor_divide_out(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & floor_divide_(at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor floor_divide_sparse(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & floor_divide_out_sparse_zerodim(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & floor_divide_sparse_(at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor floor_divide(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & floor_divide_Scalar_out(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +TORCH_API at::Tensor & floor_divide_(at::Tensor & self, const at::Scalar & other); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..e939c6bd8d6dbfae24a92ef37fefab90597bcd67 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gather_backward.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::gather_backward(Tensor grad, Tensor self, int dim, Tensor index, bool sparse_grad) -> Tensor +inline at::Tensor gather_backward(const at::Tensor & grad, const at::Tensor & self, int64_t dim, const at::Tensor & index, bool sparse_grad) { + return at::_ops::gather_backward::call(grad, self, dim, index, sparse_grad); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ge_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ge_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ae541f9888e9ee6de2b631a2fcb8d98498db1c06 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/ge_compositeexplicitautogradnonfunctional_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 compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor ge(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & ge_(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor ge(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & ge_(at::Tensor & self, const at::Tensor & other); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_jvp_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_jvp_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..ca9787cfdd0220309bfbe2d4ea679a6803440a94 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/glu_jvp_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 glu_jvp(const at::Tensor & glu, const at::Tensor & x, const at::Tensor & dx, int64_t dim); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardsigmoid_backward_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardsigmoid_backward_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4de83514317b1f429fce7c809a5db850a1f58859 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardsigmoid_backward_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor hardsigmoid_backward(const at::Tensor & grad_output, const at::Tensor & self); +TORCH_API at::Tensor & hardsigmoid_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self); +TORCH_API at::Tensor & hardsigmoid_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hstack_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hstack_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..6e7d4bccbbbb214b5a16b7d9bcddd7ac8aa7ff65 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hstack_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 hstack(at::TensorList tensors); +TORCH_API at::Tensor & hstack_out(at::Tensor & out, at::TensorList tensors); +TORCH_API at::Tensor & hstack_outf(at::TensorList tensors, at::Tensor & out); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..1b4c16b474327c2712d99881a282a553bdf60155 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API huber_loss_backward_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, double, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::huber_loss_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "huber_loss_backward.out(Tensor grad_output, Tensor self, Tensor target, int reduction, float delta, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double delta, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double delta, at::Tensor & grad_input); +}; + +struct TORCH_API huber_loss_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, double); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::huber_loss_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "huber_loss_backward(Tensor grad_output, Tensor self, Tensor target, int reduction, float delta) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double delta); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double delta); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_neg.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_neg.h new file mode 100644 index 0000000000000000000000000000000000000000..f5fa66570c99c8ce555bdde5265126eb4b7503fd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/is_neg.h @@ -0,0 +1,30 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::is_neg(Tensor self) -> bool +inline bool __dispatch_is_neg(const at::Tensor & self) { + return at::_ops::is_neg::call(self); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isneginf.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isneginf.h new file mode 100644 index 0000000000000000000000000000000000000000..a3942058f67c05cbe2dd96ecc9d770af87569804 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isneginf.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::isneginf(Tensor self) -> Tensor +inline at::Tensor isneginf(const at::Tensor & self) { + return at::_ops::isneginf::call(self); +} + +// aten::isneginf.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isneginf_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::isneginf_out::call(self, out); +} +// aten::isneginf.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & isneginf_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::isneginf_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isposinf_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isposinf_native.h new file mode 100644 index 0000000000000000000000000000000000000000..0f458b7f1a2590b2fe24799770d594ed6d779f8f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/isposinf_native.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_isposinf_out : public at::meta::structured_isposinf { +void impl(const at::Tensor & self, const at::Tensor & out); +}; +TORCH_API at::Tensor isposinf_sparse(const at::Tensor & self); +TORCH_API at::Tensor & isposinf_sparse_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor isposinf_sparse_csr(const at::Tensor & self); +TORCH_API at::Tensor & isposinf_sparse_csr_out(const at::Tensor & self, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..551e1851e842e972401ac83b1e57bfc1fe0be40e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_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::leaky_relu_backward.grad_input(Tensor grad_output, Tensor self, Scalar negative_slope, bool self_is_result, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & leaky_relu_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & negative_slope, bool self_is_result) { + return at::_ops::leaky_relu_backward_grad_input::call(grad_output, self, negative_slope, self_is_result, grad_input); +} +// aten::leaky_relu_backward.grad_input(Tensor grad_output, Tensor self, Scalar negative_slope, bool self_is_result, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & leaky_relu_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & negative_slope, bool self_is_result, at::Tensor & grad_input) { + return at::_ops::leaky_relu_backward_grad_input::call(grad_output, self, negative_slope, self_is_result, grad_input); +} + +// aten::leaky_relu_backward(Tensor grad_output, Tensor self, Scalar negative_slope, bool self_is_result) -> Tensor +inline at::Tensor leaky_relu_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & negative_slope, bool self_is_result) { + return at::_ops::leaky_relu_backward::call(grad_output, self, negative_slope, self_is_result); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_solve_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_solve_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d46caca8c21fed8a90c5c3664974d3f1b010e7c4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_ldl_solve_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor linalg_ldl_solve(const at::Tensor & LD, const at::Tensor & pivots, const at::Tensor & B, bool hermitian=false); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_solve_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_solve_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..1c9fc3c9067ac995e6eafe0a9077bf871d331c6a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_lu_solve_meta.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeMetaFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace meta { + +struct TORCH_API structured_linalg_lu_solve : public at::impl::MetaBase { + + + void meta(const at::Tensor & LU, const at::Tensor & pivots, const at::Tensor & B, bool left, bool adjoint); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vander.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vander.h new file mode 100644 index 0000000000000000000000000000000000000000..9ac4ed5d0c45296d42e9037f1e362d1ea5e9dabc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vander.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::linalg_vander(Tensor x, *, SymInt? N=None) -> Tensor +inline at::Tensor linalg_vander(const at::Tensor & x, c10::optional N=c10::nullopt) { + return at::_ops::linalg_vander::call(x, N.has_value() ? c10::make_optional(c10::SymInt(*N)) : c10::nullopt); +} +namespace symint { + template ::value>> + at::Tensor linalg_vander(const at::Tensor & x, c10::optional N=c10::nullopt) { + return at::_ops::linalg_vander::call(x, N.has_value() ? c10::make_optional(c10::SymInt(*N)) : c10::nullopt); + } +} + +// aten::linalg_vander(Tensor x, *, SymInt? N=None) -> Tensor +inline at::Tensor linalg_vander_symint(const at::Tensor & x, c10::optional N=c10::nullopt) { + return at::_ops::linalg_vander::call(x, N); +} +namespace symint { + template ::value>> + at::Tensor linalg_vander(const at::Tensor & x, c10::optional N=c10::nullopt) { + return at::_ops::linalg_vander::call(x, N); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linspace_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linspace_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..cfaf717deb745b3b62bc8f2f8b88f32857b54cef --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linspace_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 & linspace_out(at::Tensor & out, const at::Scalar & start, const at::Scalar & end, int64_t steps); +TORCH_API at::Tensor & linspace_outf(const at::Scalar & start, const at::Scalar & end, int64_t steps, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_sigmoid_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_sigmoid_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..8e341fb599a50be0412c4517f59663ac524538f5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_sigmoid_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::log_sigmoid_backward.grad_input(Tensor grad_output, Tensor self, Tensor buffer, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & log_sigmoid_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & buffer) { + return at::_ops::log_sigmoid_backward_grad_input::call(grad_output, self, buffer, grad_input); +} +// aten::log_sigmoid_backward.grad_input(Tensor grad_output, Tensor self, Tensor buffer, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & log_sigmoid_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & buffer, at::Tensor & grad_input) { + return at::_ops::log_sigmoid_backward_grad_input::call(grad_output, self, buffer, grad_input); +} + +// aten::log_sigmoid_backward(Tensor grad_output, Tensor self, Tensor buffer) -> Tensor +inline at::Tensor log_sigmoid_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & buffer) { + return at::_ops::log_sigmoid_backward::call(grad_output, self, buffer); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_backward_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_backward_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..1d80928e8e32b3eb7dfe4b478502a54371cc55b3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_backward_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor max_pool2d_with_indices_backward(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices); +TORCH_API at::Tensor & max_pool2d_with_indices_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices); +TORCH_API at::Tensor & max_pool2d_with_indices_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, const at::Tensor & indices, at::Tensor & grad_input); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..d90d548483a1c96a86ab8b3e056f14f741a0fde9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool3d_with_indices_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 max_pool3d_with_indices_out { + using schema = ::std::tuple (const at::Tensor &, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, bool, at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::max_pool3d_with_indices") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "max_pool3d_with_indices.out(Tensor self, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False, *, Tensor(a!) out, Tensor(b!) indices) -> (Tensor(a!), Tensor(b!))") + static ::std::tuple call(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out, at::Tensor & indices); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode, at::Tensor & out, at::Tensor & indices); +}; + +struct TORCH_API max_pool3d_with_indices { + using schema = ::std::tuple (const at::Tensor &, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, at::IntArrayRef, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::max_pool3d_with_indices") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "max_pool3d_with_indices(Tensor self, int[3] kernel_size, int[3] stride=[], int[3] padding=0, int[3] dilation=1, bool ceil_mode=False) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::IntArrayRef kernel_size, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool ceil_mode); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..24efbc157c4a474569e90b9c1241265e267d5efd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_cpu_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor max_unpool3d(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API at::Tensor max_unpool3d_symint(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API at::Tensor & max_unpool3d_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API at::Tensor & max_unpool3d_outf(const at::Tensor & self, const at::Tensor & indices, at::IntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out); +TORCH_API at::Tensor & max_unpool3d_symint_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +TORCH_API at::Tensor & max_unpool3d_symint_outf(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_rnn_layer.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_rnn_layer.h new file mode 100644 index 0000000000000000000000000000000000000000..9ef7321e75a6fb59ab97378c8217ceec9757d23f --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_rnn_layer.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::mkldnn_rnn_layer(Tensor input, Tensor weight0, Tensor weight1, Tensor weight2, Tensor weight3, Tensor hx_, Tensor cx_, bool reverse, int[] batch_sizes, int mode, int hidden_size, int num_layers, bool has_biases, bool bidirectional, bool batch_first, bool train) -> (Tensor, Tensor, Tensor, Tensor) +inline ::std::tuple mkldnn_rnn_layer(const at::Tensor & input, const at::Tensor & weight0, const at::Tensor & weight1, const at::Tensor & weight2, const at::Tensor & weight3, const at::Tensor & hx_, const at::Tensor & cx_, bool reverse, at::IntArrayRef batch_sizes, int64_t mode, int64_t hidden_size, int64_t num_layers, bool has_biases, bool bidirectional, bool batch_first, bool train) { + return at::_ops::mkldnn_rnn_layer::call(input, weight0, weight1, weight2, weight3, hx_, cx_, reverse, batch_sizes, mode, hidden_size, num_layers, has_biases, bidirectional, batch_first, train); +} + +// aten::mkldnn_rnn_layer.out(Tensor input, Tensor weight0, Tensor weight1, Tensor weight2, Tensor weight3, Tensor hx_, Tensor cx_, bool reverse, int[] batch_sizes, int mode, int hidden_size, int num_layers, bool has_biases, bool bidirectional, bool batch_first, bool train, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!)) +inline ::std::tuple mkldnn_rnn_layer_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3, const at::Tensor & input, const at::Tensor & weight0, const at::Tensor & weight1, const at::Tensor & weight2, const at::Tensor & weight3, const at::Tensor & hx_, const at::Tensor & cx_, bool reverse, at::IntArrayRef batch_sizes, int64_t mode, int64_t hidden_size, int64_t num_layers, bool has_biases, bool bidirectional, bool batch_first, bool train) { + return at::_ops::mkldnn_rnn_layer_out::call(input, weight0, weight1, weight2, weight3, hx_, cx_, reverse, batch_sizes, mode, hidden_size, num_layers, has_biases, bidirectional, batch_first, train, out0, out1, out2, out3); +} +// aten::mkldnn_rnn_layer.out(Tensor input, Tensor weight0, Tensor weight1, Tensor weight2, Tensor weight3, Tensor hx_, Tensor cx_, bool reverse, int[] batch_sizes, int mode, int hidden_size, int num_layers, bool has_biases, bool bidirectional, bool batch_first, bool train, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2, Tensor(d!) out3) -> (Tensor(a!), Tensor(b!), Tensor(c!), Tensor(d!)) +inline ::std::tuple mkldnn_rnn_layer_outf(const at::Tensor & input, const at::Tensor & weight0, const at::Tensor & weight1, const at::Tensor & weight2, const at::Tensor & weight3, const at::Tensor & hx_, const at::Tensor & cx_, bool reverse, at::IntArrayRef batch_sizes, int64_t mode, int64_t hidden_size, int64_t num_layers, bool has_biases, bool bidirectional, bool batch_first, bool train, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, at::Tensor & out3) { + return at::_ops::mkldnn_rnn_layer_out::call(input, weight0, weight1, weight2, weight3, hx_, cx_, reverse, batch_sizes, mode, hidden_size, num_layers, has_biases, bidirectional, batch_first, train, out0, out1, out2, out3); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multi_margin_loss_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multi_margin_loss_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b1a05725ec879f23ed1e3066666202f93b163901 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multi_margin_loss_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor multi_margin_loss(const at::Tensor & self, const at::Tensor & target, const at::Scalar & p=1, const at::Scalar & margin=1, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean); +TORCH_API at::Tensor & multi_margin_loss_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & target, const at::Scalar & p=1, const at::Scalar & margin=1, const c10::optional & weight={}, int64_t reduction=at::Reduction::Mean); +TORCH_API at::Tensor & multi_margin_loss_outf(const at::Tensor & self, const at::Tensor & target, const at::Scalar & p, const at::Scalar & margin, const c10::optional & weight, int64_t reduction, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss.h new file mode 100644 index 0000000000000000000000000000000000000000..dec21ff2320265d7523dce19822c20fe09584724 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_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::multilabel_margin_loss.out(Tensor self, Tensor target, int reduction=Mean, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & multilabel_margin_loss_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & target, int64_t reduction=at::Reduction::Mean) { + return at::_ops::multilabel_margin_loss_out::call(self, target, reduction, out); +} +// aten::multilabel_margin_loss.out(Tensor self, Tensor target, int reduction=Mean, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & multilabel_margin_loss_outf(const at::Tensor & self, const at::Tensor & target, int64_t reduction, at::Tensor & out) { + return at::_ops::multilabel_margin_loss_out::call(self, target, reduction, out); +} + +// aten::multilabel_margin_loss(Tensor self, Tensor target, int reduction=Mean) -> Tensor +inline at::Tensor multilabel_margin_loss(const at::Tensor & self, const at::Tensor & target, int64_t reduction=at::Reduction::Mean) { + return at::_ops::multilabel_margin_loss::call(self, target, reduction); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_dropout_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_dropout_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..c9cfb3cc5c074eed5468ea60f3243f86fae77788 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_dropout_backward_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API native_dropout_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, double); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::native_dropout_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "native_dropout_backward(Tensor grad_output, Tensor mask, float scale) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & mask, double scale); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & mask, double scale); +}; + +struct TORCH_API native_dropout_backward_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, double, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::native_dropout_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "native_dropout_backward.out(Tensor grad_output, Tensor mask, float scale, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & mask, double scale, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & mask, double scale, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..0d71edfcf48fff6eb711b3000032cd1a62ef7e60 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/nll_loss_backward.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::nll_loss_backward.grad_input(Tensor grad_output, Tensor self, Tensor target, Tensor? weight, int reduction, SymInt ignore_index, Tensor total_weight, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & nll_loss_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & nll_loss_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); + } +} + +// aten::nll_loss_backward.grad_input(Tensor grad_output, Tensor self, Tensor target, Tensor? weight, int reduction, SymInt ignore_index, Tensor total_weight, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & nll_loss_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, const at::Tensor & total_weight, at::Tensor & grad_input) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & nll_loss_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, const at::Tensor & total_weight, at::Tensor & grad_input) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); + } +} + +// aten::nll_loss_backward.grad_input(Tensor grad_output, Tensor self, Tensor target, Tensor? weight, int reduction, SymInt ignore_index, Tensor total_weight, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & nll_loss_backward_symint_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & nll_loss_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); + } +} + +// aten::nll_loss_backward.grad_input(Tensor grad_output, Tensor self, Tensor target, Tensor? weight, int reduction, SymInt ignore_index, Tensor total_weight, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & nll_loss_backward_symint_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, const at::Tensor & total_weight, at::Tensor & grad_input) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); +} +namespace symint { + template ::value>> + at::Tensor & nll_loss_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, const at::Tensor & total_weight, at::Tensor & grad_input) { + return at::_ops::nll_loss_backward_grad_input::call(grad_output, self, target, weight, reduction, ignore_index, total_weight, grad_input); + } +} + +// aten::nll_loss_backward(Tensor grad_output, Tensor self, Tensor target, Tensor? weight, int reduction, SymInt ignore_index, Tensor total_weight) -> Tensor +inline at::Tensor nll_loss_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward::call(grad_output, self, target, weight, reduction, ignore_index, total_weight); +} +namespace symint { + template ::value>> + at::Tensor nll_loss_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, int64_t ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward::call(grad_output, self, target, weight, reduction, ignore_index, total_weight); + } +} + +// aten::nll_loss_backward(Tensor grad_output, Tensor self, Tensor target, Tensor? weight, int reduction, SymInt ignore_index, Tensor total_weight) -> Tensor +inline at::Tensor nll_loss_backward_symint(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward::call(grad_output, self, target, weight, reduction, ignore_index, total_weight); +} +namespace symint { + template ::value>> + at::Tensor nll_loss_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, const c10::optional & weight, int64_t reduction, c10::SymInt ignore_index, const at::Tensor & total_weight) { + return at::_ops::nll_loss_backward::call(grad_output, self, target, weight, reduction, ignore_index, total_weight); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm.h new file mode 100644 index 0000000000000000000000000000000000000000..4cc0837989d8644329741e4fb4123975d405e2fb --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm.h @@ -0,0 +1,109 @@ +#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::norm.ScalarOpt_dtype(Tensor self, Scalar? p, *, ScalarType dtype) -> Tensor +inline at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::ScalarType dtype) { + return at::_ops::norm_ScalarOpt_dtype::call(self, p, dtype); +} + +// aten::norm.Scalar(Tensor self, Scalar p=2) -> Tensor +inline at::Tensor norm(const at::Tensor & self, const at::Scalar & p=2) { + return at::_ops::norm_Scalar::call(self, p); +} + +// aten::norm.ScalarOpt_dim_dtype(Tensor self, Scalar? p, int[1] dim, bool keepdim, *, ScalarType dtype) -> Tensor +inline at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype) { + return at::_ops::norm_ScalarOpt_dim_dtype::call(self, p, dim, keepdim, dtype); +} + +// aten::norm.ScalarOpt_dim(Tensor self, Scalar? p, int[1] dim, bool keepdim=False) -> Tensor +inline at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim=false) { + return at::_ops::norm_ScalarOpt_dim::call(self, p, dim, keepdim); +} + +// aten::norm.dtype_out(Tensor self, Scalar? p, int[1] dim, bool keepdim, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype) { + return at::_ops::norm_dtype_out::call(self, p, dim, keepdim, dtype, out); +} +// aten::norm.dtype_out(Tensor self, Scalar? p, int[1] dim, bool keepdim, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_outf(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype, at::Tensor & out) { + return at::_ops::norm_dtype_out::call(self, p, dim, keepdim, dtype, out); +} + +// aten::norm.out(Tensor self, Scalar? p, int[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim=false) { + return at::_ops::norm_out::call(self, p, dim, keepdim, out); +} +// aten::norm.out(Tensor self, Scalar? p, int[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_outf(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::Tensor & out) { + return at::_ops::norm_out::call(self, p, dim, keepdim, out); +} + +// aten::norm.names_ScalarOpt_dim_dtype(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim, *, ScalarType dtype) -> Tensor +inline at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype) { + return at::_ops::norm_names_ScalarOpt_dim_dtype::call(self, p, dim, keepdim, dtype); +} + +// aten::norm.names_ScalarOpt_dim(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim=False) -> Tensor +inline at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim=false) { + return at::_ops::norm_names_ScalarOpt_dim::call(self, p, dim, keepdim); +} + +// aten::norm.names_dtype_out(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype) { + return at::_ops::norm_names_dtype_out::call(self, p, dim, keepdim, dtype, out); +} +// aten::norm.names_dtype_out(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_outf(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::ScalarType dtype, at::Tensor & out) { + return at::_ops::norm_names_dtype_out::call(self, p, dim, keepdim, dtype, out); +} + +// aten::norm.names_out(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim=false) { + return at::_ops::norm_names_out::call(self, p, dim, keepdim, out); +} +// aten::norm.names_out(Tensor self, Scalar? p, Dimname[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_outf(const at::Tensor & self, const c10::optional & p, at::DimnameList dim, bool keepdim, at::Tensor & out) { + return at::_ops::norm_names_out::call(self, p, dim, keepdim, out); +} + +// aten::norm.ScalarOpt_dtype_out(Tensor self, Scalar? p, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p, at::ScalarType dtype) { + return at::_ops::norm_ScalarOpt_dtype_out::call(self, p, dtype, out); +} +// aten::norm.ScalarOpt_dtype_out(Tensor self, Scalar? p, *, ScalarType dtype, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_outf(const at::Tensor & self, const c10::optional & p, at::ScalarType dtype, at::Tensor & out) { + return at::_ops::norm_ScalarOpt_dtype_out::call(self, p, dtype, out); +} + +// aten::norm.Scalar_out(Tensor self, Scalar p=2, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & p=2) { + return at::_ops::norm_Scalar_out::call(self, p, out); +} +// aten::norm.Scalar_out(Tensor self, Scalar p=2, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & norm_outf(const at::Tensor & self, const at::Scalar & p, at::Tensor & out) { + return at::_ops::norm_Scalar_out::call(self, p, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8b09858283e169c2f4e86d63565572a38ed939ab --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/norm_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 norm(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype); +TORCH_API at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype); +TORCH_API at::Tensor & norm_outf(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::ScalarType dtype, at::Tensor & out); +TORCH_API at::Tensor norm(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim=false); +TORCH_API at::Tensor & norm_out(at::Tensor & out, const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim=false); +TORCH_API at::Tensor & norm_outf(const at::Tensor & self, const c10::optional & p, at::IntArrayRef dim, bool keepdim, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad1d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad1d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..f38c3d48deeeb8c8dc7c80fcf97153fd2d6b214b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/reflection_pad1d_native.h @@ -0,0 +1,27 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_reflection_pad1d_out_cpu : public at::meta::structured_reflection_pad1d { +void impl(const at::Tensor & self, at::ArrayRef padding, const at::Tensor & out); +}; +struct TORCH_API structured_reflection_pad1d_out_cuda : public at::meta::structured_reflection_pad1d { +void impl(const at::Tensor & self, at::ArrayRef padding, const at::Tensor & out); +}; +TORCH_API at::Tensor & reflection_pad1d_out_quantized_cpu(const at::Tensor & self, at::IntArrayRef padding, at::Tensor & out); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rsub_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rsub_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..f901c4ab46aaf01cd2db626c1f645bcd54247b6a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/rsub_ops.h @@ -0,0 +1,61 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API rsub_Tensor { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, const at::Scalar &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::rsub") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "rsub.Tensor(Tensor self, Tensor other, *, Scalar alpha=1) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha); +}; + +struct TORCH_API rsub_Scalar { + using schema = at::Tensor (const at::Tensor &, const at::Scalar &, const at::Scalar &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::rsub") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "rsub.Scalar(Tensor self, Scalar other, Scalar alpha=1) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Scalar & other, const at::Scalar & alpha); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other, const at::Scalar & alpha); +}; + +struct TORCH_API rsub_Tensor_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, const at::Scalar &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::rsub") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "rsub.Tensor_out(Tensor self, Tensor other, *, Scalar alpha=1, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha, at::Tensor & out); +}; + +struct TORCH_API rsub_Scalar_out { + using schema = at::Tensor & (const at::Tensor &, const at::Scalar &, const at::Scalar &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::rsub") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Scalar_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "rsub.Scalar_out(Tensor self, Scalar other, Scalar alpha=1, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Scalar & other, const at::Scalar & alpha, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Scalar & other, const at::Scalar & alpha, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_native.h new file mode 100644 index 0000000000000000000000000000000000000000..27397dbc79c167314d29b5705f766dd91a4a0639 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/set_native.h @@ -0,0 +1,38 @@ +#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 set(const at::Tensor & self, at::Storage source); +TORCH_API at::Tensor & set_source_Storage_out(const at::Tensor & self, at::Storage source, at::Tensor & out); +TORCH_API at::Tensor & set_(at::Tensor & self, at::Storage source); +TORCH_API at::Tensor set_symint(const at::Tensor & self, at::Storage source, c10::SymInt storage_offset, c10::SymIntArrayRef size, c10::SymIntArrayRef stride={}); +TORCH_API at::Tensor & set_source_Storage_storage_offset_out_symint(const at::Tensor & self, at::Storage source, c10::SymInt storage_offset, c10::SymIntArrayRef size, c10::SymIntArrayRef stride, at::Tensor & out); +TORCH_API at::Tensor & set_storage_cpu_(at::Tensor & self, at::Storage source, int64_t storage_offset, at::IntArrayRef size, at::IntArrayRef stride={}); +TORCH_API at::Tensor & set_storage_cuda_(at::Tensor & self, at::Storage source, int64_t storage_offset, at::IntArrayRef size, at::IntArrayRef stride={}); +TORCH_API at::Tensor & set_storage_meta__symint(at::Tensor & self, at::Storage source, c10::SymInt storage_offset, c10::SymIntArrayRef size, c10::SymIntArrayRef stride={}); +TORCH_API at::Tensor & set_storage_quantized_(at::Tensor & self, at::Storage source, int64_t storage_offset, at::IntArrayRef size, at::IntArrayRef stride={}); +TORCH_API at::Tensor & set__symint(at::Tensor & self, const at::Tensor & source, c10::SymInt storage_offset, c10::SymIntArrayRef size, c10::SymIntArrayRef stride={}); +TORCH_API at::Tensor set(const at::Tensor & self, const at::Tensor & source); +TORCH_API at::Tensor & set_source_Tensor_out(const at::Tensor & self, const at::Tensor & source, at::Tensor & out); +TORCH_API at::Tensor & set_tensor_(at::Tensor & self, const at::Tensor & source); +TORCH_API at::Tensor set(const at::Tensor & self); +TORCH_API at::Tensor & set_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & set_cpu_(at::Tensor & self); +TORCH_API at::Tensor & set_cuda_(at::Tensor & self); +TORCH_API at::Tensor & set_meta_(at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinh_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinh_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3d6f6c423497449d155ae3af0e75439e4a6e65e8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sinh_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 sinh(const at::Tensor & self); +TORCH_API at::Tensor & sinh_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & sinh_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & sinh_(at::Tensor & self); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..2da48e78d2c8df7a5cb6b858b1e503406e4c220d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slice_backward.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::slice_backward(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step) -> Tensor +inline at::Tensor slice_backward(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t start, int64_t end, int64_t step) { + return at::_ops::slice_backward::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, start, end, step); +} +namespace symint { + template ::value>> + at::Tensor slice_backward(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t start, int64_t end, int64_t step) { + return at::_ops::slice_backward::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, start, end, step); + } +} + +// aten::slice_backward(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step) -> Tensor +inline at::Tensor slice_backward_symint(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step) { + return at::_ops::slice_backward::call(grad_output, input_sizes, dim, start, end, step); +} +namespace symint { + template ::value>> + at::Tensor slice_backward(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step) { + return at::_ops::slice_backward::call(grad_output, input_sizes, dim, start, end, step); + } +} + +// aten::slice_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_backward_out(at::Tensor & out, const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t start, int64_t end, int64_t step) { + return at::_ops::slice_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, start, end, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_backward_out(at::Tensor & out, const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t start, int64_t end, int64_t step) { + return at::_ops::slice_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, start, end, step, out); + } +} + +// aten::slice_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_backward_outf(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t start, int64_t end, int64_t step, at::Tensor & out) { + return at::_ops::slice_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, start, end, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_backward_outf(const at::Tensor & grad_output, at::IntArrayRef input_sizes, int64_t dim, int64_t start, int64_t end, int64_t step, at::Tensor & out) { + return at::_ops::slice_backward_out::call(grad_output, c10::fromIntArrayRefSlow(input_sizes), dim, start, end, step, out); + } +} + +// aten::slice_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_backward_symint_out(at::Tensor & out, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step) { + return at::_ops::slice_backward_out::call(grad_output, input_sizes, dim, start, end, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_backward_out(at::Tensor & out, const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step) { + return at::_ops::slice_backward_out::call(grad_output, input_sizes, dim, start, end, step, out); + } +} + +// aten::slice_backward.out(Tensor grad_output, SymInt[] input_sizes, int dim, SymInt start, SymInt end, SymInt step, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & slice_backward_symint_outf(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step, at::Tensor & out) { + return at::_ops::slice_backward_out::call(grad_output, input_sizes, dim, start, end, step, out); +} +namespace symint { + template ::value>> + at::Tensor & slice_backward_outf(const at::Tensor & grad_output, c10::SymIntArrayRef input_sizes, int64_t dim, c10::SymInt start, c10::SymInt end, c10::SymInt step, at::Tensor & out) { + return at::_ops::slice_backward_out::call(grad_output, input_sizes, dim, start, end, step, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slow_conv_transpose3d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slow_conv_transpose3d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..69b0f7a5cbfcc7ff4e735a69030293fe37869d0c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/slow_conv_transpose3d_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_transpose3d_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_transpose3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "slow_conv_transpose3d.out(Tensor self, Tensor weight, SymInt[3] kernel_size, Tensor? bias=None, SymInt[3] stride=1, SymInt[3] padding=0, SymInt[3] output_padding=0, SymInt[3] 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_transpose3d { + 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_transpose3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "slow_conv_transpose3d(Tensor self, Tensor weight, SymInt[3] kernel_size, Tensor? bias=None, SymInt[3] stride=1, SymInt[3] padding=0, SymInt[3] output_padding=0, SymInt[3] 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/softplus_backward_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_backward_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..7436f1a636f3ae9fb7cb7979b1bf278b38260d6b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softplus_backward_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_softplus_backward : public TensorIteratorBase { + + + void meta(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & beta, const at::Scalar & threshold); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..039dd3719f721552ec55ad4947932572e8dcdc70 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_entr_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor special_entr(const at::Tensor & self); +TORCH_API at::Tensor & special_entr_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_entr_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfcx_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfcx_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..501d95e4db8c5300f68e444d9e8939dcb78eebee --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_erfcx_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 special_erfcx(const at::Tensor & self); +TORCH_API at::Tensor & special_erfcx_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & special_erfcx_outf(const at::Tensor & self, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_he_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_he_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..e90ea164a1ca94cd75aac0caef7281bd3bc54958 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_hermite_polynomial_he_compositeexplicitautograd_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API at::Tensor special_hermite_polynomial_he(const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_hermite_polynomial_he_out(at::Tensor & out, const at::Scalar & x, const at::Tensor & n); +TORCH_API at::Tensor & special_hermite_polynomial_he_outf(const at::Scalar & x, const at::Tensor & n, at::Tensor & out); +TORCH_API at::Tensor special_hermite_polynomial_he(const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_hermite_polynomial_he_out(at::Tensor & out, const at::Tensor & x, const at::Scalar & n); +TORCH_API at::Tensor & special_hermite_polynomial_he_outf(const at::Tensor & x, const at::Scalar & n, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_k0.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_k0.h new file mode 100644 index 0000000000000000000000000000000000000000..421187889d91d626b9a2e184d2bf82098d70100a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_k0.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::special_modified_bessel_k0(Tensor self) -> Tensor +inline at::Tensor special_modified_bessel_k0(const at::Tensor & self) { + return at::_ops::special_modified_bessel_k0::call(self); +} + +// aten::special_modified_bessel_k0.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_modified_bessel_k0_out(at::Tensor & out, const at::Tensor & self) { + return at::_ops::special_modified_bessel_k0_out::call(self, out); +} +// aten::special_modified_bessel_k0.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & special_modified_bessel_k0_outf(const at::Tensor & self, at::Tensor & out) { + return at::_ops::special_modified_bessel_k0_out::call(self, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b4264836072be955d962661e47f684bce7a8ef49 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_spherical_bessel_j0_meta_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor special_spherical_bessel_j0(const at::Tensor & x); +TORCH_API at::Tensor & special_spherical_bessel_j0_out(at::Tensor & out, const at::Tensor & x); +TORCH_API at::Tensor & special_spherical_bessel_j0_outf(const at::Tensor & x, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8c511ad8573ddf129674014e5461348b5cff1282 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_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 std(const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, const c10::optional & correction=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & std_out(at::Tensor & out, const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, const c10::optional & correction=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & std_outf(const at::Tensor & self, at::OptionalIntArrayRef dim, const c10::optional & correction, bool keepdim, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_mean_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_mean_native.h new file mode 100644 index 0000000000000000000000000000000000000000..5c94a015ce795db8c13fcc9e603a7022da869738 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/std_mean_native.h @@ -0,0 +1,26 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple std_mean(const at::Tensor & self, bool unbiased=true); +TORCH_API ::std::tuple std_mean(const at::Tensor & self, at::OptionalIntArrayRef dim, bool unbiased=true, bool keepdim=false); +TORCH_API ::std::tuple std_mean_correction_out(const at::Tensor & self, at::OptionalIntArrayRef dim, const c10::optional & correction, bool keepdim, at::Tensor & out0, at::Tensor & out1); +TORCH_API ::std::tuple std_mean(const at::Tensor & self, at::OptionalIntArrayRef dim=c10::nullopt, const c10::optional & correction=c10::nullopt, bool keepdim=false); +TORCH_API ::std::tuple std_mean(const at::Tensor & self, at::DimnameList dim, bool unbiased=true, bool keepdim=false); +TORCH_API ::std::tuple std_mean(const at::Tensor & self, at::DimnameList dim, const c10::optional & correction=c10::nullopt, bool keepdim=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/t_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/t_native.h new file mode 100644 index 0000000000000000000000000000000000000000..a02a3b122d993eb9454259426c3fe070398c55ae --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/t_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 t(const at::Tensor & self); +TORCH_API at::Tensor & t_(at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..68e3727e44bb341665c6218bdab80302b2a2a6e7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/take_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor take(const at::Tensor & self, const at::Tensor & index); +TORCH_API at::Tensor & take_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & index); +TORCH_API at::Tensor & take_outf(const at::Tensor & self, const at::Tensor & index, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b6940f845cd2ba9d0300001907e23ab542bf56d3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unfold_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 unfold(const at::Tensor & self, int64_t dimension, int64_t size, int64_t step); + +} // namespace cpu +} // namespace at