Function apply_router_lora 

pub fn apply_router_lora(
    gpu: &dyn GpuBackend,
    kernels: &LoraKernels,
    pair: &LoraPair,
    router_in: DevicePtr,
    gate_logits: DevicePtr,
    n: u32,
    max_rows: u32,
    lora_xa: DevicePtr,
    lora_delta: DevicePtr,
    stream: u64,
) -> Result<()>

2026-09-25: Fold the router (mlp.gate) delta onto gate_logits ([n, num_experts], in place) from router_in ([n, hidden]), in blocks of at most max_rows rows.