pub fn layer_norm<'a>(
x: &Array,
weight: impl Into<Option<&'a Array>>,
bias: impl Into<Option<&'a Array>>,
eps: f32,
) -> ArrayExpand description
Layer normalisation over the last axis, (x - mean) / sqrt(var + eps) · weight + bias,
as MLX’s fast.layer_norm: statistics in float32, the result in the promoted type.