pub fn dequant_q4_1(src: &[u8]) -> Result<Vec<f32>, QuantError>Expand description
Dequantize a Q4_1 buffer into f32. Formula verified against real
ggml-quants.c::dequantize_row_q4_1: y = q*d + m, no bias
subtraction (unlike Q4_0’s symmetric q-8).