# mypy: disable-error-code="type-arg"
from typing import List, Optional, overload, Sequence, Tuple, Union

from torch import memory_format, Tensor
from torch.types import _bool, _device, _dtype, _int, _size

# Defined in tools/autograd/templates/python_nn_functions.cpp

def adaptive_max_pool2d(input: Tensor, output_size: Union[_int, _size]) -> Tuple[Tensor, Tensor]: ...
def adaptive_max_pool3d(input: Tensor, output_size: Union[_int, _size]) -> Tuple[Tensor, Tensor]: ...
def avg_pool2d(input: Tensor, kernel_size: Union[_int, _size], stride: Optional[Union[_int, _size]] = None, padding: Union[_int, _size] = 0, ceil_mode: bool = False, count_include_pad: bool = True, divisor_override: Optional[int] = None) -> Tensor: ...
def avg_pool3d(input: Tensor, kernel_size: Union[_int, _size], stride: Optional[Union[_int, _size]] = None, padding: Union[_int, _size] = 0, ceil_mode: bool = False, count_include_pad: bool = True, divisor_override: Optional[int] = None) -> Tensor: ...
def elu_(input: Tensor, alpha: float = ...) -> Tensor: ...
def fractional_max_pool2d(input: Tensor, kernel_size: Union[_int, _size], output_size: Union[_int, _size], _random_samples: Tensor) -> Tuple[Tensor, Tensor]: ...
def fractional_max_pool3d(input: Tensor, kernel_size: Union[_int, _size], output_size: Union[_int, _size], _random_samples: Tensor) -> Tuple[Tensor, Tensor]: ...
def gelu(input: Tensor, approximate: str = ...) -> Tensor: ...
def hardsigmoid(input: Tensor, *, out: Optional[Tensor] = None) -> Tensor: ...
def hardtanh(input: Tensor, min_val: float = ..., max_val: float = ..., *, out: Optional[Tensor] = None) -> Tensor: ...
def hardtanh_(input: Tensor, min_val: float = ..., max_val: float = ...) -> Tensor: ...
def leaky_relu(input: Tensor, negative_slope: float = ..., *, out: Optional[Tensor] = None) -> Tensor: ...
def leaky_relu_(input: Tensor, negative_slope: float = ...) -> Tensor: ...
def linear(input: Tensor, weight: Tensor, bias: Optional[Tensor] = None) -> Tensor: ...
def log_sigmoid(input: Tensor) -> Tensor: ...
def one_hot(tensor: Tensor, num_classes: int = ...) -> Tensor: ...
def pad(input: Tensor, pad: Sequence[int], mode: str = ..., value: Optional[float] = None) -> Tensor: ...
def scaled_dot_product_attention(query: Tensor, key: Tensor, value: Tensor, attn_mask: Optional[Tensor] = None, dropout_p: float = 0.0, is_causal: bool = False, scale: Optional[float] = None) -> Tensor: ...
def softplus(input: Tensor, beta: float = ..., threshold: float = ...) -> Tensor: ...
def softshrink(input: Tensor, lambd: float = ...) -> Tensor: ...

# Defined in aten/src/ATen/native/mkldnn/Linear.cpp
def mkldnn_linear(input: Tensor, weight: Tensor, bias: Optional[Tensor]) -> Tensor: ...

# Defined at aten/src/ATen/native/mkldnn/MKLDNNConversions.cpp
def mkldnn_reorder_conv2d_weight(
    self: Tensor,
    padding: List,
    stride: List,
    dilatation: List,
    groups: int,
) -> Tensor: ...
def mkldnn_reorder_conv3d_weight(
    self: Tensor,
    padding: List,
    stride: List,
    dilatation: List,
    groups: int,
) -> Tensor: ...

# Defined in aten/src/ATen/native/mkldnn/Prelu.cpp
def mkldnn_prelu(input: Tensor, weight: Tensor) -> Tensor: ...

# Defined at tools/autograd/templates/python_nn_functions.cpp
@overload
def _parse_to(
    device: _device,
    dtype: _dtype,
    non_blocking: _bool,
    copy: _bool,
    *,
    memory_format: memory_format,
) -> Tuple[_device, _dtype, _bool, memory_format]: ...
@overload
def _parse_to(
    dtype: _dtype,
    non_blocking: _bool,
    copy: _bool,
    *,
    memory_format: memory_format,
) -> Tuple[_device, _dtype, _bool, memory_format]: ...
@overload
def _parse_to(
    tensor: Tensor,
    non_blocking: _bool,
    copy: _bool,
    *,
    memory_format: memory_format,
) -> Tuple[_device, _dtype, _bool, memory_format]: ...

# Defined in aten/src/ATen/native/PadSequence.cpp
def pad_sequence(
    sequences: List[Tensor],
    batch_first: bool = False,
    padding_value: float = ...,
) -> Tensor: ...
def flatten_dense_tensors(tensors: List[Tensor]) -> Tensor: ...
def unflatten_dense_tensors(flat: Tensor, tensors: List[Tensor]) -> List[Tensor]: ...