in candle-core/src/quantized/k_quants.rs [1788:1825]
fn from_float(xs: &[f32], ys: &mut [Self]) -> Result<()> {
let k = xs.len();
if k % QK_K != 0 {
crate::bail!("quantize_row_q8k: {k} is not divisible by {QK_K}")
}
for (i, y) in ys.iter_mut().enumerate() {
let mut max = 0f32;
let mut amax = 0f32;
let xs = &xs[i * QK_K..(i + 1) * QK_K];
for &x in xs.iter() {
if amax < x.abs() {
amax = x.abs();
max = x;
}
}
if amax == 0f32 {
y.d = 0f32;
y.qs.fill(0)
} else {
let iscale = -128f32 / max;
for (j, q) in y.qs.iter_mut().enumerate() {
// ggml uses nearest_int with bit magic here, maybe we want the same
// but we would have to test and benchmark it.
let v = (iscale * xs[j]).round();
*q = v.min(127.) as i8
}
for j in 0..QK_K / 16 {
let mut sum = 0i32;
for ii in 0..16 {
sum += y.qs[j * 16 + ii] as i32
}
y.bsums[j] = sum as i16
}
y.d = 1.0 / iscale
}
}
Ok(())
}