pub fn glm_hc_expand(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
hidden: DevicePtr,
streams: DevicePtr,
num_tokens: u32,
hidden_size: u32,
hc_mult: u32,
stream: u64,
) -> Result<()>Expand description
Expand one BF16 hidden state into the hc_mult FP32 highway streams. First layer only.