pub fn quantize_activations_q8(x: &[f32]) -> Q8ActivationsExpand description
Quantize an activation row to Q8Activations (32-element blocks,
ggml quantize_row_q8_0 rounding: d = amax/127, q = round(x/d)).
x.len() must be a multiple of 32.
pub fn quantize_activations_q8(x: &[f32]) -> Q8ActivationsQuantize an activation row to Q8Activations (32-element blocks,
ggml quantize_row_q8_0 rounding: d = amax/127, q = round(x/d)).
x.len() must be a multiple of 32.