timm/layers/norm.py [139:171]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    __constants__ = ['normalized_shape', 'eps', 'elementwise_affine', '_fast_norm']
    normalized_shape: Tuple[int, ...]
    eps: float
    elementwise_affine: bool
    _fast_norm: bool

    def __init__(self, channels, eps=1e-6, affine=True, device=None, dtype=None) -> None:
        factory_kwargs = {'device': device, 'dtype': dtype}
        super().__init__()
        normalized_shape = channels
        if isinstance(normalized_shape, numbers.Integral):
            # mypy error: incompatible types in assignment
            normalized_shape = (normalized_shape,)  # type: ignore[assignment]
        self.normalized_shape = tuple(normalized_shape)  # type: ignore[arg-type]
        self.eps = eps
        self.elementwise_affine = affine
        self._fast_norm = is_fast_norm()  # can't script unless we have these flags here (no globals)

        if self.elementwise_affine:
            self.weight = nn.Parameter(torch.empty(self.normalized_shape, **factory_kwargs))
        else:
            self.register_parameter('weight', None)

        self.reset_parameters()

    def reset_parameters(self) -> None:
        if self.elementwise_affine:
            nn.init.ones_(self.weight)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        # NOTE fast norm fallback needs our rms norm impl, so both paths through here.
        # Since there is no built-in PyTorch impl, always use APEX RmsNorm if is installed.
        if self._fast_norm:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/layers/norm.py [227:257]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    __constants__ = ['normalized_shape', 'eps', 'elementwise_affine', '_fast_norm']
    normalized_shape: Tuple[int, ...]
    eps: float
    elementwise_affine: bool
    _fast_norm: bool

    def __init__(self, channels, eps=1e-6, affine=True, device=None, dtype=None) -> None:
        factory_kwargs = {'device': device, 'dtype': dtype}
        super().__init__()
        normalized_shape = channels
        if isinstance(normalized_shape, numbers.Integral):
            # mypy error: incompatible types in assignment
            normalized_shape = (normalized_shape,)  # type: ignore[assignment]
        self.normalized_shape = tuple(normalized_shape)  # type: ignore[arg-type]
        self.eps = eps
        self.elementwise_affine = affine
        self._fast_norm = is_fast_norm()  # can't script unless we have these flags here (no globals)

        if self.elementwise_affine:
            self.weight = nn.Parameter(torch.empty(self.normalized_shape, **factory_kwargs))
        else:
            self.register_parameter('weight', None)

        self.reset_parameters()

    def reset_parameters(self) -> None:
        if self.elementwise_affine:
            nn.init.ones_(self.weight)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        if self._fast_norm:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -