pub fn gdn_verify_fused_conv_kn(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
conv_state: DevicePtr,
new_input: DevicePtr,
weight: &DenseWeight,
output: DevicePtr,
conv_state_inter: DevicePtr,
num_tokens: u32,
d_inner: u32,
d_conv: u32,
qk_channels: u32,
head_dim: u32,
input_stride: u32,
output_stride: u32,
inter_stride: u32,
l2_eps: f32,
stream: u64,
) -> Result<()>