Function matvec_rows2 

pub fn matvec_rows2(
    pool: Option<&Pool>,
    w: &[f32],
    x1: &[f32],
    x2: &[f32],
    out1: &mut [f32],
    out2: &mut [f32],
)

Two-input row matvec: one pass over the weight rows serves BOTH inputs — CPU decode is memory-bound, so the second position costs a fraction of the first (this is where MTP speculative verify wins). Per-output accumulation order matches the single-input path exactly → bit-identical results.