Function hc_expand 

pub fn hc_expand(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    hidden: DevicePtr,
    streams: DevicePtr,
    num_tokens: u32,
    hidden_size: u32,
    hc_mult: u32,
    stream: u64,
) -> Result<()>

Broadcast a single hidden state into hc_mult identical streams: streams[t, i, d] = hidden[t, d]. One block per token.