Function dequantize 

pub fn dequantize(
    data: &[u8],
    scales: &[u16],
    group_len: usize,
    bits: u8,
    tensor_len: usize,
    frame_count: usize,
    out: &mut Vec<f32>,
)

Dequantize packed codes using f16 scales, writing f32 values.