Function layer_norm 

pub fn layer_norm<const D: usize>(
    input: Tensor<D>,
    gamma: Tensor<1>,
    beta: Option<Tensor<1>>,
    epsilon: f64,
) -> Tensor<D>

Applies Layer Normalization over the last dimension of the input tensor.

Computes (x - mean) / sqrt(var + epsilon) * gamma + beta, where mean and (biased) var are reduced over the last axis.

Shapes

• input: [..., any, d_model]
• output: [..., any, d_model]