Skip to main content

repack_q6_k

Function repack_q6_k 

Source
pub fn repack_q6_k(
    data: &[u8],
) -> Result<(Vec<u32>, Vec<u32>, Vec<u32>, Vec<f32>)>
Expand description

Layout step for Q6_K: split each 210-byte superblock into SoA device arrays — (ql words, qh words, i8 scale words, d f32). 212 B per 256 weights = 6.63 bits/weight (GGUF native is 6.56).