gdn_decode

Function gdn_decode 

Source
pub fn gdn_decode(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    h_state: DevicePtr,
    query: DevicePtr,
    key: DevicePtr,
    value: DevicePtr,
    gate: DevicePtr,
    beta: DevicePtr,
    output: DevicePtr,
    batch_size: u32,
    num_k_heads: u32,
    num_v_heads: u32,
    k_dim: u32,
    v_dim: u32,
    stream: u64,
) -> Result<()>
Expand description

2026-09-25: Single-token GDN decode (gated_delta_rule_decode). The batch_size h-states are contiguous: [batch, num_v_heads, k_dim, v_dim] FP32.