Function gdn_verify_fused_conv_k2 

pub fn gdn_verify_fused_conv_k2(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    conv_state: DevicePtr,
    new_input: DevicePtr,
    weight: &DenseWeight,
    output: DevicePtr,
    conv_state_inter: DevicePtr,
    d_inner: u32,
    d_conv: u32,
    qk_channels: u32,
    head_dim: u32,
    input_stride: u32,
    output_stride: u32,
    l2_eps: f32,
    stream: u64,
) -> Result<()>

2026-09-25: K=2 MTP-verify conv1d + SiLU + L2 norm: both draft positions in one launch, with the position-0 conv-state snapshot written inline.

On return conv_state holds the committed (post position-1) window and conv_state_inter the position-0 rollback snapshot. The gdn_verify_fused_microtest example checks both states, and the gated-norm output computed from this kernel’s output, against the per-token kernels at cos >= 0.99999.

Kernel: gdn_verify_fused_conv_k2(conv_state, new_input, weight, output, conv_state_inter, dim, d_conv, qk_channels, head_dim, input_stride, output_stride, l2_eps) Grid: (ceil(dim/256), 1, 1) Block: (256, 1, 1)