diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Half_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Half_native.h new file mode 100644 index 0000000000000000000000000000000000000000..c8c6859b04d4fc067381c61c6ff6eb3586705759 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cast_Half_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor _cast_Half(const at::Tensor & self, bool non_blocking=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_double_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_double_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..1c0ad3879b658222bdbbe956c86301c46621b8a0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_convolution_double_backward_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple _convolution_double_backward(const c10::optional & ggI, const c10::optional & ggW, const c10::optional & ggb, const at::Tensor & gO, const at::Tensor & weight, const at::Tensor & self, at::IntArrayRef stride, at::IntArrayRef padding, at::IntArrayRef dilation, bool transposed, at::IntArrayRef output_padding, int64_t groups, ::std::array output_mask); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cslt_sparse_mm_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cslt_sparse_mm_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3e4ec67d49cade17d22cce4993b0b64b2c480022 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_cslt_sparse_mm_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 _cslt_sparse_mm(const at::Tensor & compressed_A, const at::Tensor & dense_B, const c10::optional & bias={}, const c10::optional & alpha={}, c10::optional out_dtype=c10::nullopt, bool transpose_result=false, int64_t alg_id=0); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_efficientzerotensor_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_efficientzerotensor_native.h new file mode 100644 index 0000000000000000000000000000000000000000..fc33e580d053c8d2816e367e8493a9741b57067d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_efficientzerotensor_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 & _efficientzerotensor_out_symint(c10::SymIntArrayRef size, at::Tensor & out); +TORCH_API at::Tensor _efficientzerotensor(at::IntArrayRef size, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +TORCH_API at::Tensor _efficientzerotensor_cuda(at::IntArrayRef size, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +TORCH_API at::Tensor _efficientzerotensor_meta(at::IntArrayRef size, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log1p_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log1p_native.h new file mode 100644 index 0000000000000000000000000000000000000000..0d060589c1280d6da947d1b936f5e26fc25048f1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_log1p_native.h @@ -0,0 +1,25 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API void _foreach_log1p_out(at::TensorList self, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_log1p_slow(at::TensorList self); +TORCH_API void foreach_tensor_log1p_slow_(at::TensorList self); +TORCH_API ::std::vector foreach_tensor_log1p_cuda(at::TensorList self); +TORCH_API void foreach_tensor_log1p_cuda_(at::TensorList self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_neg_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_neg_native.h new file mode 100644 index 0000000000000000000000000000000000000000..93c97c452959bfcf3cb010ed663b7038dc3a5266 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_foreach_neg_native.h @@ -0,0 +1,25 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API void _foreach_neg_out(at::TensorList self, at::TensorList out); +TORCH_API ::std::vector foreach_tensor_neg_slow(at::TensorList self); +TORCH_API void foreach_tensor_neg_slow_(at::TensorList self); +TORCH_API ::std::vector foreach_tensor_neg_cuda(at::TensorList self); +TORCH_API void foreach_tensor_neg_cuda_(at::TensorList self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_dropout.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_dropout.h new file mode 100644 index 0000000000000000000000000000000000000000..862fa4734d9c87a01232771fae0a0dbf30bb9988 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_dropout.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::_fused_dropout(Tensor self, float p, Generator? generator=None) -> (Tensor, Tensor) +inline ::std::tuple _fused_dropout(const at::Tensor & self, double p, c10::optional generator=c10::nullopt) { + return at::_ops::_fused_dropout::call(self, p, generator); +} + +// aten::_fused_dropout.out(Tensor self, float p, Generator? generator=None, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple _fused_dropout_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & self, double p, c10::optional generator=c10::nullopt) { + return at::_ops::_fused_dropout_out::call(self, p, generator, out0, out1); +} +// aten::_fused_dropout.out(Tensor self, float p, Generator? generator=None, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple _fused_dropout_outf(const at::Tensor & self, double p, c10::optional generator, at::Tensor & out0, at::Tensor & out1) { + return at::_ops::_fused_dropout_out::call(self, p, generator, out0, out1); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_sgd_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_sgd_native.h new file mode 100644 index 0000000000000000000000000000000000000000..e082b0629f1ded168ed5ddb21c0f56fb070dd1b6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_fused_sgd_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::vector,::std::vector,::std::vector> _fused_sgd(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, double lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const c10::optional & grad_scale={}, const c10::optional & found_inf={}); +TORCH_API void _fused_sgd_out(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, double lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const c10::optional & grad_scale, const c10::optional & found_inf, at::TensorList out); +TORCH_API void _fused_sgd_kernel_cuda_(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, double lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const c10::optional & grad_scale={}, const c10::optional & found_inf={}); +TORCH_API ::std::tuple<::std::vector,::std::vector,::std::vector> _fused_sgd(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, const at::Tensor & lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const c10::optional & grad_scale={}, const c10::optional & found_inf={}); +TORCH_API void _fused_sgd_tensor_lr_out(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, const at::Tensor & lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const c10::optional & grad_scale, const c10::optional & found_inf, at::TensorList out); +TORCH_API void _fused_sgd_kernel_cuda_(at::TensorList self, at::TensorList grads, at::TensorList momentum_buffer_list, double weight_decay, double momentum, const at::Tensor & lr, double dampening, bool nesterov, bool maximize, bool is_first_step, const c10::optional & grad_scale={}, const c10::optional & found_inf={}); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_cts_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_cts_native.h new file mode 100644 index 0000000000000000000000000000000000000000..5a1c6f509077000535bc622334bc42b20f01c13c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_histogramdd_from_bin_cts_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 & _histogramdd_from_bin_cts_out(const at::Tensor & self, at::IntArrayRef bins, c10::optional> range, const c10::optional & weight, bool density, at::Tensor & out); +TORCH_API at::Tensor _histogramdd(const at::Tensor & self, at::IntArrayRef bins, c10::optional> range=c10::nullopt, const c10::optional & weight={}, bool density=false); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_det.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_det.h new file mode 100644 index 0000000000000000000000000000000000000000..a3c6231477dda4a57e26bb29652176bfc10833e1 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_det.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::_linalg_det(Tensor A) -> (Tensor result, Tensor LU, Tensor pivots) +inline ::std::tuple _linalg_det(const at::Tensor & A) { + return at::_ops::_linalg_det::call(A); +} + +// aten::_linalg_det.result(Tensor A, *, Tensor(a!) result, Tensor(b!) LU, Tensor(c!) pivots) -> (Tensor(a!) result, Tensor(b!) LU, Tensor(c!) pivots) +inline ::std::tuple _linalg_det_out(at::Tensor & result, at::Tensor & LU, at::Tensor & pivots, const at::Tensor & A) { + return at::_ops::_linalg_det_result::call(A, result, LU, pivots); +} +// aten::_linalg_det.result(Tensor A, *, Tensor(a!) result, Tensor(b!) LU, Tensor(c!) pivots) -> (Tensor(a!) result, Tensor(b!) LU, Tensor(c!) pivots) +inline ::std::tuple _linalg_det_outf(const at::Tensor & A, at::Tensor & result, at::Tensor & LU, at::Tensor & pivots) { + return at::_ops::_linalg_det_result::call(A, result, LU, pivots); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_det_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_det_native.h new file mode 100644 index 0000000000000000000000000000000000000000..4eeee9e3b1467a1e7dc86a8892f7ed1d6957b204 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_linalg_det_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured__linalg_det_out : public at::meta::structured__linalg_det { +void impl(const at::Tensor & A, const at::Tensor & result, const at::Tensor & LU, const at::Tensor & pivots); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_enum_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_enum_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..d582342979f5011a9643a79f5216ebf2d052cf39 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_pad_enum_compositeimplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor _pad_enum(const at::Tensor & self, at::IntArrayRef pad, int64_t mode, c10::optional value=c10::nullopt); +TORCH_API at::Tensor _pad_enum_symint(const at::Tensor & self, c10::SymIntArrayRef pad, int64_t mode, c10::optional value=c10::nullopt); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_mm_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_mm_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0b01f32fb5305c6461636dff8ba4aac97a0ec350 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_scaled_mm_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API ::std::tuple _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); +TORCH_API ::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); +TORCH_API ::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); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_initialize_state.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_initialize_state.h new file mode 100644 index 0000000000000000000000000000000000000000..385a33ea851b7d5372ed01434be6719f5e610788 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sobol_engine_initialize_state.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::_sobol_engine_initialize_state_(Tensor(a!) self, int dimension) -> Tensor(a!) +inline at::Tensor & _sobol_engine_initialize_state_(at::Tensor & self, int64_t dimension) { + return at::_ops::_sobol_engine_initialize_state_::call(self, dimension); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_coo_tensor_with_dims_and_tensors_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_coo_tensor_with_dims_and_tensors_native.h new file mode 100644 index 0000000000000000000000000000000000000000..19ec586254889405e32ad83b88cd452fd24a8879 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_sparse_coo_tensor_with_dims_and_tensors_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 & _sparse_coo_tensor_with_dims_and_tensors_out_symint(int64_t sparse_dim, int64_t dense_dim, c10::SymIntArrayRef size, const at::Tensor & indices, const at::Tensor & values, c10::optional is_coalesced, at::Tensor & out); +TORCH_API at::Tensor new_with_dims_and_tensor_sparse_symint(int64_t sparse_dim, int64_t dense_dim, c10::SymIntArrayRef size, const at::Tensor & indices, const at::Tensor & values, c10::optional dtype={}, c10::optional layout={}, c10::optional device={}, c10::optional pin_memory={}, c10::optional is_coalesced=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_autograd_multiple_dispatch_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_autograd_multiple_dispatch_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..aba9833ebcebc86aff330796d313bf92b99ac2d9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_test_autograd_multiple_dispatch_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 _test_autograd_multiple_dispatch_fullcoverage { + 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::_test_autograd_multiple_dispatch") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "fullcoverage") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_test_autograd_multiple_dispatch.fullcoverage(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 _test_autograd_multiple_dispatch_ntonly { + using schema = at::Tensor (const at::Tensor &, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_test_autograd_multiple_dispatch") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "ntonly") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_test_autograd_multiple_dispatch.ntonly(Tensor self, bool b) -> Tensor") + static at::Tensor call(const at::Tensor & self, bool b); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool b); +}; + +struct TORCH_API _test_autograd_multiple_dispatch_fullcoverage_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::_test_autograd_multiple_dispatch") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "fullcoverage_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_test_autograd_multiple_dispatch.fullcoverage_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/_thnn_fused_gru_cell_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_gru_cell_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..69f4bedbef8a432650ef403200b55e1b740c15c8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_thnn_fused_gru_cell_compositeexplicitautograd_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautograd { + +TORCH_API ::std::tuple _thnn_fused_gru_cell_out(at::Tensor & out0, at::Tensor & out1, const at::Tensor & input_gates, const at::Tensor & hidden_gates, const at::Tensor & hx, const c10::optional & input_bias={}, const c10::optional & hidden_bias={}); +TORCH_API ::std::tuple _thnn_fused_gru_cell_outf(const at::Tensor & input_gates, const at::Tensor & hidden_gates, const at::Tensor & hx, const c10::optional & input_bias, const c10::optional & hidden_bias, 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/_unsafe_index_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_index_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..f5f4b8f57cf62069bbce8159bb496c70f8de1884 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_unsafe_index_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 _unsafe_index_Tensor { + using schema = at::Tensor (const at::Tensor &, const c10::List> &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_unsafe_index") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Tensor") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_unsafe_index.Tensor(Tensor self, Tensor?[] indices) -> Tensor") + static at::Tensor call(const at::Tensor & self, const c10::List> & indices); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const c10::List> & indices); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..bffa26fc3c83042fa141cd93f7155b43f8cd3774 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_upsample_nearest_exact3d_meta_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor _upsample_nearest_exact3d(const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor _upsample_nearest_exact3d_symint(const at::Tensor & self, c10::SymIntArrayRef output_size, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & _upsample_nearest_exact3d_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & _upsample_nearest_exact3d_outf(const at::Tensor & self, at::IntArrayRef output_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); +TORCH_API at::Tensor & _upsample_nearest_exact3d_symint_out(at::Tensor & out, const at::Tensor & self, c10::SymIntArrayRef output_size, c10::optional scales_d=c10::nullopt, c10::optional scales_h=c10::nullopt, c10::optional scales_w=c10::nullopt); +TORCH_API at::Tensor & _upsample_nearest_exact3d_symint_outf(const at::Tensor & self, c10::SymIntArrayRef output_size, c10::optional scales_d, c10::optional scales_h, c10::optional scales_w, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_rnn_flatten_weight_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_rnn_flatten_weight_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..8ca201683d21473e427140bec55bbe62eddcded4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/_use_cudnn_rnn_flatten_weight_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 _use_cudnn_rnn_flatten_weight { + using schema = bool (); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::_use_cudnn_rnn_flatten_weight") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "_use_cudnn_rnn_flatten_weight() -> bool") + static bool call(); + static bool redispatch(c10::DispatchKeySet dispatchKeySet); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmm_compositeexplicitautogradnonfunctional_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmm_compositeexplicitautogradnonfunctional_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..278a318677bf49f8a7a2a20ff58a1ab9b49d234b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/addmm_compositeexplicitautogradnonfunctional_dispatch.h @@ -0,0 +1,24 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeexplicitautogradnonfunctional { + +TORCH_API at::Tensor addmm(const at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta=1, const at::Scalar & alpha=1); +TORCH_API at::Tensor & addmm_(at::Tensor & self, const at::Tensor & mat1, const at::Tensor & mat2, const at::Scalar & beta=1, const at::Scalar & alpha=1); + +} // namespace compositeexplicitautogradnonfunctional +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arctan_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arctan_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..58d9b00c34891c0eb226df3135e66e0379a06361 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/arctan_compositeimplicitautograd_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 compositeimplicitautograd { + +TORCH_API at::Tensor arctan(const at::Tensor & self); +TORCH_API at::Tensor & arctan_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & arctan_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & arctan_(at::Tensor & self); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argmax_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argmax_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8bb43e43dfca57018898530bb1127a8be876326b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argmax_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 argmax(const at::Tensor & self, c10::optional dim=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & argmax_out(at::Tensor & out, const at::Tensor & self, c10::optional dim=c10::nullopt, bool keepdim=false); +TORCH_API at::Tensor & argmax_outf(const at::Tensor & self, c10::optional dim, bool keepdim, at::Tensor & out); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3e0506928beb883cbcb732c7081950a8ddcbce02 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/argsort_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 argsort { + using schema = at::Tensor (const at::Tensor &, int64_t, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::argsort") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "argsort(Tensor self, int dim=-1, bool descending=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, int64_t dim, bool descending); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, bool descending); +}; + +struct TORCH_API argsort_stable { + using schema = at::Tensor (const at::Tensor &, bool, int64_t, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::argsort") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "stable") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "argsort.stable(Tensor self, *, bool stable, int dim=-1, bool descending=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, bool stable, int64_t dim, bool descending); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool stable, int64_t dim, bool descending); +}; + +struct TORCH_API argsort_dimname { + using schema = at::Tensor (const at::Tensor &, at::Dimname, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::argsort") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "dimname") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "argsort.dimname(Tensor self, Dimname dim, bool descending=False) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::Dimname dim, bool descending); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Dimname dim, bool descending); +}; + +struct TORCH_API argsort_stable_out { + using schema = at::Tensor & (const at::Tensor &, bool, int64_t, 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::argsort") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "stable_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "argsort.stable_out(Tensor self, *, bool stable, int dim=-1, bool descending=False, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, bool stable, int64_t dim, bool descending, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, bool stable, int64_t dim, bool descending, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/broadcast_to_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/broadcast_to_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..2e524cf21995319bc369397f91724fe2cbe72654 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/broadcast_to_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 broadcast_to { + using schema = at::Tensor (const at::Tensor &, c10::SymIntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::broadcast_to") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "broadcast_to(Tensor(a) self, SymInt[] size) -> Tensor(a)") + static at::Tensor call(const at::Tensor & self, c10::SymIntArrayRef size); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, c10::SymIntArrayRef size); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat.h new file mode 100644 index 0000000000000000000000000000000000000000..379403a0c896a6900c151aeb34f1f532a0e605de --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/cat.h @@ -0,0 +1,53 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::cat(Tensor[] tensors, int dim=0) -> Tensor +inline at::Tensor cat(const at::ITensorListRef & tensors, int64_t dim=0) { + return at::_ops::cat::call(tensors, dim); +} + +// aten::cat.out(Tensor[] tensors, int dim=0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & cat_out(at::Tensor & out, const at::ITensorListRef & tensors, int64_t dim=0) { + return at::_ops::cat_out::call(tensors, dim, out); +} +// aten::cat.out(Tensor[] tensors, int dim=0, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & cat_outf(const at::ITensorListRef & tensors, int64_t dim, at::Tensor & out) { + return at::_ops::cat_out::call(tensors, dim, out); +} + +// aten::cat.names(Tensor[] tensors, Dimname dim) -> Tensor +inline at::Tensor cat(at::TensorList tensors, at::Dimname dim) { + return at::_ops::cat_names::call(tensors, dim); +} + +// aten::cat.names_out(Tensor[] tensors, Dimname dim, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & cat_out(at::Tensor & out, at::TensorList tensors, at::Dimname dim) { + return at::_ops::cat_names_out::call(tensors, dim, out); +} +// aten::cat.names_out(Tensor[] tensors, Dimname dim, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & cat_outf(at::TensorList tensors, at::Dimname dim, at::Tensor & out) { + return at::_ops::cat_names_out::call(tensors, dim, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chunk.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chunk.h new file mode 100644 index 0000000000000000000000000000000000000000..d2295f9c4baef00acfdd52dea94492442bd23b3d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/chunk.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::chunk(Tensor(a -> *) self, int chunks, int dim=0) -> Tensor(a)[] +inline ::std::vector chunk(const at::Tensor & self, int64_t chunks, int64_t dim=0) { + return at::_ops::chunk::call(self, chunks, dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_transpose1d_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_transpose1d_native.h new file mode 100644 index 0000000000000000000000000000000000000000..004518937c61d63f207d02d1bb17a94beb7c100d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/conv_transpose1d_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor conv_transpose1d_symint(const at::Tensor & input, const at::Tensor & weight, const c10::optional & bias={}, c10::SymIntArrayRef stride=c10::SymInt(1), c10::SymIntArrayRef padding=c10::SymInt(0), c10::SymIntArrayRef output_padding=c10::SymInt(0), c10::SymInt groups=1, c10::SymIntArrayRef dilation=c10::SymInt(1)); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/div_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/div_native.h new file mode 100644 index 0000000000000000000000000000000000000000..f7073fba5f517aa072decc244ff5bf4abd9519d6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/div_native.h @@ -0,0 +1,41 @@ +#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_div_out : public at::meta::structured_div_Tensor { +void impl(const at::Tensor & self, const at::Tensor & other, const at::Tensor & out); +}; +TORCH_API at::Tensor NestedTensor_div_Tensor(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor div_sparse(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & div_out_sparse_zerodim(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & div_sparse_(at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor div_zerotensor(const at::Tensor & self, const at::Tensor & other); +struct TORCH_API structured_div_out_mode : public at::meta::structured_div_Tensor_mode { +void impl(const at::Tensor & self, const at::Tensor & other, c10::optional rounding_mode, const at::Tensor & out); +}; +TORCH_API at::Tensor div_sparse(const at::Tensor & self, const at::Tensor & other, c10::optional rounding_mode); +TORCH_API at::Tensor & div_out_sparse_zerodim(const at::Tensor & self, const at::Tensor & other, c10::optional rounding_mode, at::Tensor & out); +TORCH_API at::Tensor & div_sparse_(at::Tensor & self, const at::Tensor & other, c10::optional rounding_mode); +TORCH_API at::Tensor div(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor & div_Scalar_out(const at::Tensor & self, const at::Scalar & other, at::Tensor & out); +TORCH_API at::Tensor & div_(at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor NestedTensor_div_Scalar(const at::Tensor & self, const at::Scalar & other); +TORCH_API at::Tensor div(const at::Tensor & self, const at::Scalar & other, c10::optional rounding_mode); +TORCH_API at::Tensor & div_Scalar_mode_out(const at::Tensor & self, const at::Scalar & other, c10::optional rounding_mode, at::Tensor & out); +TORCH_API at::Tensor & div_(at::Tensor & self, const at::Scalar & other, c10::optional rounding_mode); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_dense_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_dense_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..74c32d54f7191b346ecc466c2df3bcc4ffa24fbd --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_dense_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::embedding_dense_backward(Tensor grad_output, Tensor indices, SymInt num_weights, SymInt padding_idx, bool scale_grad_by_freq) -> Tensor +inline at::Tensor embedding_dense_backward(const at::Tensor & grad_output, const at::Tensor & indices, int64_t num_weights, int64_t padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq); +} +namespace symint { + template ::value>> + at::Tensor embedding_dense_backward(const at::Tensor & grad_output, const at::Tensor & indices, int64_t num_weights, int64_t padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq); + } +} + +// aten::embedding_dense_backward(Tensor grad_output, Tensor indices, SymInt num_weights, SymInt padding_idx, bool scale_grad_by_freq) -> Tensor +inline at::Tensor embedding_dense_backward_symint(const at::Tensor & grad_output, const at::Tensor & indices, c10::SymInt num_weights, c10::SymInt padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq); +} +namespace symint { + template ::value>> + at::Tensor embedding_dense_backward(const at::Tensor & grad_output, const at::Tensor & indices, c10::SymInt num_weights, c10::SymInt padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq); + } +} + +// aten::embedding_dense_backward.out(Tensor grad_output, Tensor indices, SymInt num_weights, SymInt padding_idx, bool scale_grad_by_freq, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & embedding_dense_backward_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & indices, int64_t num_weights, int64_t padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); +} +namespace symint { + template ::value>> + at::Tensor & embedding_dense_backward_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & indices, int64_t num_weights, int64_t padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); + } +} + +// aten::embedding_dense_backward.out(Tensor grad_output, Tensor indices, SymInt num_weights, SymInt padding_idx, bool scale_grad_by_freq, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & embedding_dense_backward_outf(const at::Tensor & grad_output, const at::Tensor & indices, int64_t num_weights, int64_t padding_idx, bool scale_grad_by_freq, at::Tensor & out) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); +} +namespace symint { + template ::value>> + at::Tensor & embedding_dense_backward_outf(const at::Tensor & grad_output, const at::Tensor & indices, int64_t num_weights, int64_t padding_idx, bool scale_grad_by_freq, at::Tensor & out) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); + } +} + +// aten::embedding_dense_backward.out(Tensor grad_output, Tensor indices, SymInt num_weights, SymInt padding_idx, bool scale_grad_by_freq, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & embedding_dense_backward_symint_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & indices, c10::SymInt num_weights, c10::SymInt padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); +} +namespace symint { + template ::value>> + at::Tensor & embedding_dense_backward_out(at::Tensor & out, const at::Tensor & grad_output, const at::Tensor & indices, c10::SymInt num_weights, c10::SymInt padding_idx, bool scale_grad_by_freq) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); + } +} + +// aten::embedding_dense_backward.out(Tensor grad_output, Tensor indices, SymInt num_weights, SymInt padding_idx, bool scale_grad_by_freq, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & embedding_dense_backward_symint_outf(const at::Tensor & grad_output, const at::Tensor & indices, c10::SymInt num_weights, c10::SymInt padding_idx, bool scale_grad_by_freq, at::Tensor & out) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); +} +namespace symint { + template ::value>> + at::Tensor & embedding_dense_backward_outf(const at::Tensor & grad_output, const at::Tensor & indices, c10::SymInt num_weights, c10::SymInt padding_idx, bool scale_grad_by_freq, at::Tensor & out) { + return at::_ops::embedding_dense_backward_out::call(grad_output, indices, num_weights, padding_idx, scale_grad_by_freq, out); + } +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_renorm_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_renorm_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..7af0ff4477aa3ae9e08d0b200115fa6217872ee7 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/embedding_renorm_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 & embedding_renorm_(at::Tensor & self, const at::Tensor & indices, double max_norm, double norm_type); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/equal_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/equal_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..74af76ef345ce977a9533dddf97d32ff10e8266e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/equal_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 equal { + using schema = bool (const at::Tensor &, const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::equal") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "equal(Tensor self, Tensor other) -> bool") + static bool call(const at::Tensor & self, const at::Tensor & other); + static bool redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & other); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/erfc_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/erfc_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..923d9528e4f32766b26bca1f77a5dc1c5489270b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/erfc_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 erfc { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::erfc") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "erfc(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API erfc_ { + using schema = at::Tensor & (at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::erfc_") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "erfc_(Tensor(a!) self) -> Tensor(a!)") + static at::Tensor & call(at::Tensor & self); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, at::Tensor & self); +}; + +struct TORCH_API erfc_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::erfc") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "erfc.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/exp_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/exp_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b6e2df918d750d8abca4d71f3809949694fbd3f0 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/exp_cpu_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor exp(const at::Tensor & self); +TORCH_API at::Tensor & exp_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & exp_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & exp_(at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..3a918173b1fe0aadebe2d77c28e658e8c879ac7a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/fake_quantize_per_channel_affine_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor fake_quantize_per_channel_affine(const at::Tensor & self, const at::Tensor & scale, const at::Tensor & zero_point, int64_t axis, int64_t quant_min, int64_t quant_max); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/flatten.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/flatten.h new file mode 100644 index 0000000000000000000000000000000000000000..f56084c629a99aa3acee43bb644deedffbeb5e9b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/flatten.h @@ -0,0 +1,45 @@ +#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::flatten.using_ints(Tensor(a) self, int start_dim=0, int end_dim=-1) -> Tensor(a) +inline at::Tensor flatten(const at::Tensor & self, int64_t start_dim=0, int64_t end_dim=-1) { + return at::_ops::flatten_using_ints::call(self, start_dim, end_dim); +} + +// aten::flatten.named_out_dim(Tensor(a) self, int start_dim, int end_dim, Dimname out_dim) -> Tensor(a) +inline at::Tensor flatten(const at::Tensor & self, int64_t start_dim, int64_t end_dim, at::Dimname out_dim) { + return at::_ops::flatten_named_out_dim::call(self, start_dim, end_dim, out_dim); +} + +// aten::flatten.using_names(Tensor(a) self, Dimname start_dim, Dimname end_dim, Dimname out_dim) -> Tensor(a) +inline at::Tensor flatten(const at::Tensor & self, at::Dimname start_dim, at::Dimname end_dim, at::Dimname out_dim) { + return at::_ops::flatten_using_names::call(self, start_dim, end_dim, out_dim); +} + +// aten::flatten.DimnameList(Tensor(a) self, Dimname[] dims, Dimname out_dim) -> Tensor(a) +inline at::Tensor flatten(const at::Tensor & self, at::DimnameList dims, at::Dimname out_dim) { + return at::_ops::flatten_DimnameList::call(self, dims, out_dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gcd_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gcd_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b4da98875bd67285dcbe23e315738679c527937e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/gcd_meta_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace meta { + +TORCH_API at::Tensor gcd(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & gcd_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & gcd_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); +TORCH_API at::Tensor & gcd_(at::Tensor & self, const at::Tensor & other); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/geometric_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/geometric_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..0441115d0719dd7c5b5b0262d95330a5ae76b534 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/geometric_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 & geometric_(at::Tensor & self, double p, c10::optional generator=c10::nullopt); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..74d78b15aa4301194fb36806f2cdccc2ddc53f7b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/grid_sampler_3d_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 grid_sampler_3d_backward { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, bool, ::std::array); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::grid_sampler_3d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "grid_sampler_3d_backward(Tensor grad_output, Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners, bool[2] output_mask) -> (Tensor, Tensor)") + static ::std::tuple call(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask); +}; + +struct TORCH_API grid_sampler_3d_backward_out { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, int64_t, int64_t, bool, ::std::array, 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::grid_sampler_3d_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "grid_sampler_3d_backward.out(Tensor grad_output, Tensor input, Tensor grid, int interpolation_mode, int padding_mode, bool align_corners, bool[2] output_mask, *, Tensor(a!) out0, Tensor(b!) out1) -> (Tensor(a!), Tensor(b!))") + static ::std::tuple call(const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & input, const at::Tensor & grid, int64_t interpolation_mode, int64_t padding_mode, bool align_corners, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardtanh_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardtanh_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..52ebf990dc8426aa9e3c1aa15dbb10d7803c0770 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/hardtanh_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::hardtanh_backward.grad_input(Tensor grad_output, Tensor self, Scalar min_val, Scalar max_val, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & hardtanh_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & min_val, const at::Scalar & max_val) { + return at::_ops::hardtanh_backward_grad_input::call(grad_output, self, min_val, max_val, grad_input); +} +// aten::hardtanh_backward.grad_input(Tensor grad_output, Tensor self, Scalar min_val, Scalar max_val, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & hardtanh_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & min_val, const at::Scalar & max_val, at::Tensor & grad_input) { + return at::_ops::hardtanh_backward_grad_input::call(grad_output, self, min_val, max_val, grad_input); +} + +// aten::hardtanh_backward(Tensor grad_output, Tensor self, Scalar min_val, Scalar max_val) -> Tensor +inline at::Tensor hardtanh_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & min_val, const at::Scalar & max_val) { + return at::_ops::hardtanh_backward::call(grad_output, self, min_val, max_val); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss_backward_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss_backward_native.h new file mode 100644 index 0000000000000000000000000000000000000000..ce9a5ab12b2a0bff4c7ed9d14a09f61989ddde0e --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/huber_loss_backward_native.h @@ -0,0 +1,22 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor huber_loss_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double delta); +TORCH_API at::Tensor & huber_loss_backward_out(const at::Tensor & grad_output, const at::Tensor & self, const at::Tensor & target, int64_t reduction, double delta, at::Tensor & grad_input); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igamma_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igamma_native.h new file mode 100644 index 0000000000000000000000000000000000000000..54d9e0795ba9082731aa555f094b8fbbefe1fa3a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/igamma_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +namespace at { +namespace native { +struct TORCH_API structured_igamma_out : public at::meta::structured_igamma { +void impl(const at::Tensor & self, const at::Tensor & other, const at::Tensor & out); +}; +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..44a027d892974e210c2827bec65aa11ba37f3760 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/instance_norm_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor instance_norm(const at::Tensor & input, const c10::optional & weight, const c10::optional & bias, const c10::optional & running_mean, const c10::optional & running_var, bool use_input_stats, double momentum, double eps, bool cudnn_enabled); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..b3cc0c2aef24d27b671ce468072cd20b328de88c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/leaky_relu_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_leaky_relu : public TensorIteratorBase { + + + void meta(const at::Tensor & self, const at::Scalar & negative_slope); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vector_norm.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vector_norm.h new file mode 100644 index 0000000000000000000000000000000000000000..a28586335297f3235b0eacfe2c8fcc5993669edf --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/linalg_vector_norm.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::linalg_vector_norm(Tensor self, Scalar ord=2, int[1]? dim=None, bool keepdim=False, *, ScalarType? dtype=None) -> Tensor +inline at::Tensor linalg_vector_norm(const at::Tensor & self, const at::Scalar & ord=2, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt) { + return at::_ops::linalg_vector_norm::call(self, ord, dim, keepdim, dtype); +} + +// aten::linalg_vector_norm.out(Tensor self, Scalar ord=2, int[1]? dim=None, bool keepdim=False, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_vector_norm_out(at::Tensor & out, const at::Tensor & self, const at::Scalar & ord=2, at::OptionalIntArrayRef dim=c10::nullopt, bool keepdim=false, c10::optional dtype=c10::nullopt) { + return at::_ops::linalg_vector_norm_out::call(self, ord, dim, keepdim, dtype, out); +} +// aten::linalg_vector_norm.out(Tensor self, Scalar ord=2, int[1]? dim=None, bool keepdim=False, *, ScalarType? dtype=None, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & linalg_vector_norm_outf(const at::Tensor & self, const at::Scalar & ord, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype, at::Tensor & out) { + return at::_ops::linalg_vector_norm_out::call(self, ord, dim, keepdim, dtype, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_softmax_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_softmax_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..f89cc73bb04dad56225b164d77689259dab35e1a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/log_softmax_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 log_softmax_int { + using schema = at::Tensor (const at::Tensor &, int64_t, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::log_softmax") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "int") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "log_softmax.int(Tensor self, int dim, ScalarType? dtype=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, int64_t dim, c10::optional dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, c10::optional dtype); +}; + +struct TORCH_API log_softmax_int_out { + using schema = at::Tensor & (const at::Tensor &, int64_t, 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::log_softmax") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "int_out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "log_softmax.int_out(Tensor self, int dim, ScalarType? dtype=None, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, int64_t dim, c10::optional dtype, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, int64_t dim, c10::optional dtype, at::Tensor & out); +}; + +struct TORCH_API log_softmax_Dimname { + using schema = at::Tensor (const at::Tensor &, at::Dimname, c10::optional); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::log_softmax") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "Dimname") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "log_softmax.Dimname(Tensor self, Dimname dim, *, ScalarType? dtype=None) -> Tensor") + static at::Tensor call(const at::Tensor & self, at::Dimname dim, c10::optional dtype); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Dimname dim, c10::optional dtype); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logsumexp.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logsumexp.h new file mode 100644 index 0000000000000000000000000000000000000000..75ab038c04098c9ed19ea7a54633f40b83e4d892 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/logsumexp.h @@ -0,0 +1,53 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::logsumexp(Tensor self, int[1] dim, bool keepdim=False) -> Tensor +inline at::Tensor logsumexp(const at::Tensor & self, at::IntArrayRef dim, bool keepdim=false) { + return at::_ops::logsumexp::call(self, dim, keepdim); +} + +// aten::logsumexp.out(Tensor self, int[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & logsumexp_out(at::Tensor & out, const at::Tensor & self, at::IntArrayRef dim, bool keepdim=false) { + return at::_ops::logsumexp_out::call(self, dim, keepdim, out); +} +// aten::logsumexp.out(Tensor self, int[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & logsumexp_outf(const at::Tensor & self, at::IntArrayRef dim, bool keepdim, at::Tensor & out) { + return at::_ops::logsumexp_out::call(self, dim, keepdim, out); +} + +// aten::logsumexp.names(Tensor self, Dimname[1] dim, bool keepdim=False) -> Tensor +inline at::Tensor logsumexp(const at::Tensor & self, at::DimnameList dim, bool keepdim=false) { + return at::_ops::logsumexp_names::call(self, dim, keepdim); +} + +// aten::logsumexp.names_out(Tensor self, Dimname[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & logsumexp_out(at::Tensor & out, const at::Tensor & self, at::DimnameList dim, bool keepdim=false) { + return at::_ops::logsumexp_names_out::call(self, dim, keepdim, out); +} +// aten::logsumexp.names_out(Tensor self, Dimname[1] dim, bool keepdim=False, *, Tensor(a!) out) -> Tensor(a!) +inline at::Tensor & logsumexp_outf(const at::Tensor & self, at::DimnameList dim, bool keepdim, at::Tensor & out) { + return at::_ops::logsumexp_names_out::call(self, dim, keepdim, out); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..0e163b0b4661f3d3b5518a4999fb305513b455b6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_pool2d_with_indices_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::max_pool2d_with_indices_backward.grad_input(Tensor grad_output, Tensor self, int[2] kernel_size, int[2] stride, int[2] padding, int[2] dilation, bool ceil_mode, Tensor indices, *, Tensor(a!) grad_input) -> Tensor(a!) +inline 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) { + return at::_ops::max_pool2d_with_indices_backward_grad_input::call(grad_output, self, kernel_size, stride, padding, dilation, ceil_mode, indices, grad_input); +} +// aten::max_pool2d_with_indices_backward.grad_input(Tensor grad_output, Tensor self, int[2] kernel_size, int[2] stride, int[2] padding, int[2] dilation, bool ceil_mode, Tensor indices, *, Tensor(a!) grad_input) -> Tensor(a!) +inline 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) { + return at::_ops::max_pool2d_with_indices_backward_grad_input::call(grad_output, self, kernel_size, stride, padding, dilation, ceil_mode, indices, grad_input); +} + +// aten::max_pool2d_with_indices_backward(Tensor grad_output, Tensor self, int[2] kernel_size, int[2] stride, int[2] padding, int[2] dilation, bool ceil_mode, Tensor indices) -> Tensor +inline 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) { + return at::_ops::max_pool2d_with_indices_backward::call(grad_output, self, kernel_size, stride, padding, dilation, ceil_mode, indices); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..b2b7689b6eaa665d5299d21e633c804a25c685a5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/max_unpool3d_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_unpool3d_out { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, at::IntArrayRef, at::IntArrayRef, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::max_unpool3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "max_unpool3d.out(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding, at::Tensor & out); +}; + +struct TORCH_API max_unpool3d { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &, c10::SymIntArrayRef, at::IntArrayRef, at::IntArrayRef); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::max_unpool3d") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "max_unpool3d(Tensor self, Tensor indices, SymInt[3] output_size, int[3] stride, int[3] padding) -> Tensor") + static at::Tensor call(const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, const at::Tensor & indices, c10::SymIntArrayRef output_size, at::IntArrayRef stride, at::IntArrayRef padding); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mean_meta.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mean_meta.h new file mode 100644 index 0000000000000000000000000000000000000000..627aba6e5da11928a6622157d73b39a0594eec75 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mean_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_mean_dim : public at::impl::MetaBase { + + + void meta(const at::Tensor & self, at::OptionalIntArrayRef dim, bool keepdim, c10::optional dtype); +}; + +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_linear_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_linear_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..53ed0b0196eee5a7900844182bd6b4591b237fc5 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_linear_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::mkldnn_linear_backward(Tensor self, Tensor grad_output, Tensor weight, bool[3] output_mask) -> (Tensor, Tensor, Tensor) +inline ::std::tuple mkldnn_linear_backward(const at::Tensor & self, const at::Tensor & grad_output, const at::Tensor & weight, ::std::array output_mask) { + return at::_ops::mkldnn_linear_backward::call(self, grad_output, weight, output_mask); +} + +// aten::mkldnn_linear_backward.out(Tensor self, Tensor grad_output, Tensor weight, bool[3] output_mask, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2) -> (Tensor(a!), Tensor(b!), Tensor(c!)) +inline ::std::tuple mkldnn_linear_backward_out(at::Tensor & out0, at::Tensor & out1, at::Tensor & out2, const at::Tensor & self, const at::Tensor & grad_output, const at::Tensor & weight, ::std::array output_mask) { + return at::_ops::mkldnn_linear_backward_out::call(self, grad_output, weight, output_mask, out0, out1, out2); +} +// aten::mkldnn_linear_backward.out(Tensor self, Tensor grad_output, Tensor weight, bool[3] output_mask, *, Tensor(a!) out0, Tensor(b!) out1, Tensor(c!) out2) -> (Tensor(a!), Tensor(b!), Tensor(c!)) +inline ::std::tuple mkldnn_linear_backward_outf(const at::Tensor & self, const at::Tensor & grad_output, const at::Tensor & weight, ::std::array output_mask, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2) { + return at::_ops::mkldnn_linear_backward_out::call(self, grad_output, weight, output_mask, out0, out1, out2); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_rnn_layer_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_rnn_layer_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..00ae70a7aae59bc05cccbeffd3f6cbc821b6aac9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/mkldnn_rnn_layer_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 mkldnn_rnn_layer { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, bool, at::IntArrayRef, int64_t, int64_t, int64_t, bool, bool, bool, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::mkldnn_rnn_layer") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "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)") + static ::std::tuple call(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); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, 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); +}; + +struct TORCH_API mkldnn_rnn_layer_out { + using schema = ::std::tuple (const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, const at::Tensor &, bool, at::IntArrayRef, int64_t, int64_t, int64_t, bool, bool, bool, bool, 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::mkldnn_rnn_layer") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "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!))") + static ::std::tuple call(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); + static ::std::tuple redispatch(c10::DispatchKeySet dispatchKeySet, 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); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss_forward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss_forward.h new file mode 100644 index 0000000000000000000000000000000000000000..ad3401fb87cfd3a3001fbb8c4bcc074b821cb217 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/multilabel_margin_loss_forward.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_forward.output(Tensor self, Tensor target, int reduction, *, Tensor(a!) output, Tensor(b!) is_target) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple multilabel_margin_loss_forward_out(at::Tensor & output, at::Tensor & is_target, const at::Tensor & self, const at::Tensor & target, int64_t reduction) { + return at::_ops::multilabel_margin_loss_forward_output::call(self, target, reduction, output, is_target); +} +// aten::multilabel_margin_loss_forward.output(Tensor self, Tensor target, int reduction, *, Tensor(a!) output, Tensor(b!) is_target) -> (Tensor(a!), Tensor(b!)) +inline ::std::tuple multilabel_margin_loss_forward_outf(const at::Tensor & self, const at::Tensor & target, int64_t reduction, at::Tensor & output, at::Tensor & is_target) { + return at::_ops::multilabel_margin_loss_forward_output::call(self, target, reduction, output, is_target); +} + +// aten::multilabel_margin_loss_forward(Tensor self, Tensor target, int reduction) -> (Tensor output, Tensor is_target) +inline ::std::tuple multilabel_margin_loss_forward(const at::Tensor & self, const at::Tensor & target, int64_t reduction) { + return at::_ops::multilabel_margin_loss_forward::call(self, target, reduction); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_group_norm_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_group_norm_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..b3aae65ca4b9d9905ca90771a01c4c556cca0bff --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/native_group_norm_backward_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::tuple native_group_norm_backward(const at::Tensor & grad_out, const at::Tensor & input, const at::Tensor & mean, const at::Tensor & rstd, const c10::optional & weight, int64_t N, int64_t C, int64_t HxW, int64_t group, ::std::array output_mask); +TORCH_API ::std::tuple native_group_norm_backward_symint(const at::Tensor & grad_out, const at::Tensor & input, const at::Tensor & mean, const at::Tensor & rstd, const c10::optional & weight, c10::SymInt N, c10::SymInt C, c10::SymInt HxW, int64_t group, ::std::array output_mask); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pinverse_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pinverse_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..c3cddf4bbb37378c637cac333488656ae63aa464 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pinverse_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor pinverse(const at::Tensor & self, double rcond=1e-15); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pixel_unshuffle_compositeexplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pixel_unshuffle_compositeexplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8c20bedcd8da991d37d60117cbbaae8d429c49e4 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/pixel_unshuffle_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 & pixel_unshuffle_out(at::Tensor & out, const at::Tensor & self, int64_t downscale_factor); +TORCH_API at::Tensor & pixel_unshuffle_outf(const at::Tensor & self, int64_t downscale_factor, at::Tensor & out); + +} // namespace compositeexplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_zero_point_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_zero_point_native.h new file mode 100644 index 0000000000000000000000000000000000000000..210fc8c9e3dcf7b90b4195c748b5d48f23242402 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_zero_point_native.h @@ -0,0 +1,21 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API int64_t q_zero_point_quant(const at::Tensor & self); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_zero_point_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_zero_point_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..3b77ce2b68ecc5584993895556117b5abef957c3 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/q_zero_point_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 q_zero_point { + using schema = int64_t (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::q_zero_point") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "q_zero_point(Tensor self) -> int") + static int64_t call(const at::Tensor & self); + static int64_t redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/quantized_lstm_cell.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/quantized_lstm_cell.h new file mode 100644 index 0000000000000000000000000000000000000000..9a9753baf9709def3d80867b6a7170fe4b04566b --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/quantized_lstm_cell.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::quantized_lstm_cell(Tensor input, Tensor[] hx, Tensor w_ih, Tensor w_hh, Tensor b_ih, Tensor b_hh, Tensor packed_ih, Tensor packed_hh, Tensor col_offsets_ih, Tensor col_offsets_hh, Scalar scale_ih, Scalar scale_hh, Scalar zero_point_ih, Scalar zero_point_hh) -> (Tensor, Tensor) +inline ::std::tuple quantized_lstm_cell(const at::Tensor & input, at::TensorList hx, const at::Tensor & w_ih, const at::Tensor & w_hh, const at::Tensor & b_ih, const at::Tensor & b_hh, const at::Tensor & packed_ih, const at::Tensor & packed_hh, const at::Tensor & col_offsets_ih, const at::Tensor & col_offsets_hh, const at::Scalar & scale_ih, const at::Scalar & scale_hh, const at::Scalar & zero_point_ih, const at::Scalar & zero_point_hh) { + return at::_ops::quantized_lstm_cell::call(input, hx, w_ih, w_hh, b_ih, b_hh, packed_ih, packed_hh, col_offsets_ih, col_offsets_hh, scale_ih, scale_hh, zero_point_ih, zero_point_hh); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..a3c7bf327ded56b22e5ade6809baa7146cb194d8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward_compositeimplicitautograd_dispatch.h @@ -0,0 +1,23 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor silu_backward(const at::Tensor & grad_output, const at::Tensor & self); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..505f27b6861823111cba54240b129dcf36fbf3ca --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/silu_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 silu_backward_grad_input { + using schema = at::Tensor & (const at::Tensor &, const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::silu_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "grad_input") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "silu_backward.grad_input(Tensor grad_output, Tensor self, *, Tensor(a!) grad_input) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self, at::Tensor & grad_input); +}; + +struct TORCH_API silu_backward { + using schema = at::Tensor (const at::Tensor &, const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::silu_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "silu_backward(Tensor grad_output, Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & grad_output, const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad_output, const at::Tensor & self); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward_cuda_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward_cuda_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..4c018f5cd6b174b87233719535e26a9c9d51f918 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/softshrink_backward_cuda_dispatch.h @@ -0,0 +1,25 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cuda { + +TORCH_API at::Tensor softshrink_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd); +TORCH_API at::Tensor & softshrink_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd); +TORCH_API at::Tensor & softshrink_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & lambd, at::Tensor & grad_input); + +} // namespace cuda +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sort_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sort_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9cd0612fbaad6c1491c6484e4d12a1e2bba2ba6a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/sort_compositeimplicitautograd_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API ::std::tuple sort(const at::Tensor & self, at::Dimname dim, bool descending=false); +TORCH_API ::std::tuple sort_out(at::Tensor & values, at::Tensor & indices, const at::Tensor & self, at::Dimname dim, bool descending=false); +TORCH_API ::std::tuple sort_outf(const at::Tensor & self, at::Dimname dim, bool descending, at::Tensor & values, at::Tensor & indices); +TORCH_API ::std::tuple sort(const at::Tensor & self, c10::optional stable, at::Dimname dim, bool descending=false); +TORCH_API ::std::tuple sort_out(at::Tensor & values, at::Tensor & indices, const at::Tensor & self, c10::optional stable, at::Dimname dim, bool descending=false); +TORCH_API ::std::tuple sort_outf(const at::Tensor & self, c10::optional stable, at::Dimname dim, bool descending, at::Tensor & values, at::Tensor & indices); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_u_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_u_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..8264603f34c4956f76ef41a42bdd70ccc64657b9 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_chebyshev_polynomial_u_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_chebyshev_polynomial_u(const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_u_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_chebyshev_polynomial_u_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_laguerre_polynomial_l_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_laguerre_polynomial_l_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..bde62bdd9257a845bc1c975a8c462bd2acc82a71 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_laguerre_polynomial_l_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_laguerre_polynomial_l(const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_laguerre_polynomial_l_out(at::Tensor & out, const at::Tensor & x, const at::Tensor & n); +TORCH_API at::Tensor & special_laguerre_polynomial_l_outf(const at::Tensor & x, const at::Tensor & n, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i1_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i1_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..c091b26771874d8225f49358d098ed267590628a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_modified_bessel_i1_ops.h @@ -0,0 +1,39 @@ +#pragma once + +// @generated by torchgen/gen.py from Operator.h + +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { +namespace _ops { + + +struct TORCH_API special_modified_bessel_i1 { + using schema = at::Tensor (const at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_modified_bessel_i1") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_modified_bessel_i1(Tensor self) -> Tensor") + static at::Tensor call(const at::Tensor & self); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self); +}; + +struct TORCH_API special_modified_bessel_i1_out { + using schema = at::Tensor & (const at::Tensor &, at::Tensor &); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::special_modified_bessel_i1") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "out") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "special_modified_bessel_i1.out(Tensor self, *, Tensor(a!) out) -> Tensor(a!)") + static at::Tensor & call(const at::Tensor & self, at::Tensor & out); + static at::Tensor & redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & self, at::Tensor & out); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_xlog1py_meta_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_xlog1py_meta_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..9a9e1aee35c33e28250bf79860dddef8fcde2dd8 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/special_xlog1py_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_xlog1py(const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & special_xlog1py_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other); +TORCH_API at::Tensor & special_xlog1py_outf(const at::Tensor & self, const at::Tensor & other, at::Tensor & out); + +} // namespace meta +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/subtract_compositeimplicitautograd_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/subtract_compositeimplicitautograd_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..45aaf96b1fa3d61e3c67e4c80a42e8ba431442cc --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/subtract_compositeimplicitautograd_dispatch.h @@ -0,0 +1,28 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace compositeimplicitautograd { + +TORCH_API at::Tensor subtract(const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1); +TORCH_API at::Tensor & subtract_out(at::Tensor & out, const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1); +TORCH_API at::Tensor & subtract_outf(const at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha, at::Tensor & out); +TORCH_API at::Tensor & subtract_(at::Tensor & self, const at::Tensor & other, const at::Scalar & alpha=1); +TORCH_API at::Tensor subtract(const at::Tensor & self, const at::Scalar & other, const at::Scalar & alpha=1); +TORCH_API at::Tensor & subtract_(at::Tensor & self, const at::Scalar & other, const at::Scalar & alpha=1); + +} // namespace compositeimplicitautograd +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_cpu_dispatch.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_cpu_dispatch.h new file mode 100644 index 0000000000000000000000000000000000000000..6b96e1b399c5f2f2d37fb003cb0bf4a71570ed17 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/tanh_cpu_dispatch.h @@ -0,0 +1,26 @@ +#pragma once +// @generated by torchgen/gen.py from DispatchKeyFunction.h + +// NB: The implementing C++ file is RegisterDispatchKey.cpp + +// The only #includes we need are for custom classes that have defaults in the C++ API +#include +#include +#include + +// Forward declarations of any types needed in the operator signatures. +// We can't directly include these classes because it will cause circular include dependencies. +// This file is included by TensorBody.h, which defines the Tensor class. +#include + +namespace at { + +namespace cpu { + +TORCH_API at::Tensor tanh(const at::Tensor & self); +TORCH_API at::Tensor & tanh_out(at::Tensor & out, const at::Tensor & self); +TORCH_API at::Tensor & tanh_outf(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & tanh_(at::Tensor & self); + +} // namespace cpu +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_backward.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_backward.h new file mode 100644 index 0000000000000000000000000000000000000000..04ddb49712a664bc3b49a4af40c9b5f477612393 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/threshold_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::threshold_backward.grad_input(Tensor grad_output, Tensor self, Scalar threshold, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & threshold_backward_out(at::Tensor & grad_input, const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & threshold) { + return at::_ops::threshold_backward_grad_input::call(grad_output, self, threshold, grad_input); +} +// aten::threshold_backward.grad_input(Tensor grad_output, Tensor self, Scalar threshold, *, Tensor(a!) grad_input) -> Tensor(a!) +inline at::Tensor & threshold_backward_outf(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & threshold, at::Tensor & grad_input) { + return at::_ops::threshold_backward_grad_input::call(grad_output, self, threshold, grad_input); +} + +// aten::threshold_backward(Tensor grad_output, Tensor self, Scalar threshold) -> Tensor +inline at::Tensor threshold_backward(const at::Tensor & grad_output, const at::Tensor & self, const at::Scalar & threshold) { + return at::_ops::threshold_backward::call(grad_output, self, threshold); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/topk_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/topk_native.h new file mode 100644 index 0000000000000000000000000000000000000000..9c2f1422270673d90efa12f1a7dda2d9e1280da6 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/topk_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_topk_out_cpu : public at::meta::structured_topk { +void impl(const at::Tensor & self, int64_t k, int64_t dim, bool largest, bool sorted, const at::Tensor & values, const at::Tensor & indices); +}; +struct TORCH_API structured_topk_out_cuda : public at::meta::structured_topk { +void impl(const at::Tensor & self, int64_t k, int64_t dim, bool largest, bool sorted, const at::Tensor & values, const at::Tensor & indices); +}; +TORCH_API ::std::tuple topk_quantized_cpu(const at::Tensor & self, int64_t k, int64_t dim=-1, bool largest=true, bool sorted=true); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unbind.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unbind.h new file mode 100644 index 0000000000000000000000000000000000000000..b540322d4810c3c7859de27c9ed710ac610a895a --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unbind.h @@ -0,0 +1,35 @@ +#pragma once + +// @generated by torchgen/gen.py from Function.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + + +#include + +namespace at { + + +// aten::unbind.int(Tensor(a -> *) self, int dim=0) -> Tensor(a)[] +inline ::std::vector unbind(const at::Tensor & self, int64_t dim=0) { + return at::_ops::unbind_int::call(self, dim); +} + +// aten::unbind.Dimname(Tensor(a -> *) self, Dimname dim) -> Tensor(a)[] +inline ::std::vector unbind(const at::Tensor & self, at::Dimname dim) { + return at::_ops::unbind_Dimname::call(self, dim); +} + +} diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_consecutive_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_consecutive_native.h new file mode 100644 index 0000000000000000000000000000000000000000..3af90cc49765c8fcc31c9e8d79839f0d4bc4cd0d --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/unique_consecutive_native.h @@ -0,0 +1,23 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API ::std::tuple unique_consecutive_out(const at::Tensor & self, bool return_inverse, bool return_counts, c10::optional dim, at::Tensor & out0, at::Tensor & out1, at::Tensor & out2); +TORCH_API ::std::tuple unique_consecutive_cpu(const at::Tensor & self, bool return_inverse=false, bool return_counts=false, c10::optional dim=c10::nullopt); +TORCH_API ::std::tuple unique_consecutive_cuda(const at::Tensor & self, bool return_inverse=false, bool return_counts=false, c10::optional dim=c10::nullopt); +} // namespace native +} // namespace at diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/value_selecting_reduction_backward_ops.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/value_selecting_reduction_backward_ops.h new file mode 100644 index 0000000000000000000000000000000000000000..6cc359fe2d78b098b57c867e8b095e290b66fb1c --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/value_selecting_reduction_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 value_selecting_reduction_backward { + using schema = at::Tensor (const at::Tensor &, int64_t, const at::Tensor &, c10::SymIntArrayRef, bool); + using ptr_schema = schema*; + // See Note [static constexpr char* members for windows NVCC] + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(name, "aten::value_selecting_reduction_backward") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(overload_name, "") + STATIC_CONSTEXPR_STR_INL_EXCEPT_WIN_CUDA(schema_str, "value_selecting_reduction_backward(Tensor grad, int dim, Tensor indices, SymInt[] sizes, bool keepdim) -> Tensor") + static at::Tensor call(const at::Tensor & grad, int64_t dim, const at::Tensor & indices, c10::SymIntArrayRef sizes, bool keepdim); + static at::Tensor redispatch(c10::DispatchKeySet dispatchKeySet, const at::Tensor & grad, int64_t dim, const at::Tensor & indices, c10::SymIntArrayRef sizes, bool keepdim); +}; + +}} // namespace at::_ops diff --git a/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/zero_native.h b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/zero_native.h new file mode 100644 index 0000000000000000000000000000000000000000..39751b677ee39d3614b38dd58454ef41143fec97 --- /dev/null +++ b/tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/include/ATen/ops/zero_native.h @@ -0,0 +1,28 @@ +#pragma once + +// @generated by torchgen/gen.py from NativeFunction.h + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +namespace at { +namespace native { +TORCH_API at::Tensor zero(const at::Tensor & self); +TORCH_API at::Tensor & zero_out(const at::Tensor & self, at::Tensor & out); +TORCH_API at::Tensor & zero_(at::Tensor & self); +TORCH_API at::Tensor & zero_nested_(at::Tensor & self); +TORCH_API at::Tensor & zero_sparse_(at::Tensor & self); +TORCH_API at::Tensor & zero_sparse_csr_(at::Tensor & self); +TORCH_API at::Tensor & zero_meta_(at::Tensor & self); +TORCH_API at::Tensor & mkldnn_zero_(at::Tensor & self); +} // namespace native +} // namespace at