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<()>Expand description
2026-09-25: K-position verify conv1d + SiLU + L2 norm: all num_tokens
draft positions in one launch. Position t’s conv-state snapshot is
written to conv_state_inter + t * inter_stride.
On return conv_state holds the window after the last position, which is
also snapshot num_tokens - 1.
Kernel: gdn_verify_fused_conv_kn(conv_state, new_input, weight, output, conv_state_inter, num_tokens, dim, d_conv, qk_channels, head_dim, input_stride, output_stride, inter_stride, l2_eps)
Grid: (ceil(dim/256), 1, 1) Block: (256, 1, 1)