Function hc_post 

pub fn hc_post(
    x: &[f32],
    residual: &[f32],
    post: &[f32],
    comb: &[f32],
    tokens: usize,
    hc: usize,
    dim: usize,
) -> Vec<f32>

Block.hc_post: y[k][d] = post[k] * x[d] + sum_j comb[j][k] * residual[j][d], to bf16.