Function tap_highway 

pub fn tap_highway(
    gpu: &dyn GpuBackend,
    streams: DevicePtr,
    layer: usize,
    tag: &str,
    num_tokens: usize,
    hc_dim: usize,
    stream: u64,
)

2026-09-25: Tap the FP32 highway, num_tokens * hc_dim values. No-op unless the dump directory is set. It synchronizes the stream first, so it must not run inside CUDA-graph capture. Errors are logged or dropped, never returned.