pub fn rms_norm(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
input: DevicePtr,
weight: &DenseWeight,
output: DevicePtr,
num_tokens: u32,
hidden_size: u32,
eps: f32,
stream: u64,
) -> Result<()>pub fn rms_norm(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
input: DevicePtr,
weight: &DenseWeight,
output: DevicePtr,
num_tokens: u32,
hidden_size: u32,
eps: f32,
stream: u64,
) -> Result<()>