pub fn ple_add_highway(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
ple_out: DevicePtr,
hidden: DevicePtr,
n: u32,
stream: u64,
) -> Result<()>Expand description
highway += ple_out, in FP32. The reference adds PLE’s output to the
residual before that layer’s attention hyper-connection.