Skip to main content

quantize_activations_q8

Function quantize_activations_q8 

Source
pub fn quantize_activations_q8(x: &[f32]) -> Q8Activations
Expand 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.