pub(super) fn qwen4_exp_check_rows(
m: &CpuModel<'_>,
st: &mut State,
gpu: &Gpu<'_>,
rows: &[u32],
next: Option<&[u32]>,
pos0: usize,
label: &str,
prefill: bool,
) -> Result<()>Expand description
Compare the GPU’s rows against the CPU reference, which forwards the
same tokens one at a time. With next (the token after each row), the
CPU also runs the MTP head per row and the last row’s draft logits are
compared with the GPU’s.