Function dequantize_tensor 

pub fn dequantize_tensor(
    scheme: Scheme,
    qview: &TensorView<'_>,
    shape: &[usize],
    scales: &[f32],
    zero_points: Option<&[i32]>,
    groups: &[u32],
) -> Vec<f32>

Dequantizes a tensor previously written by quantize_tensor, given its already-decoded scale (and, for asymmetric schemes, zero-point) values. Used by crate::validate.