gdn_decode_f32_norm

Function gdn_decode_f32_norm 

Source
pub fn gdn_decode_f32_norm(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    h_state: DevicePtr,
    query: DevicePtr,
    key: DevicePtr,
    value: DevicePtr,
    gate: DevicePtr,
    beta: DevicePtr,
    z_gate: DevicePtr,
    norm_weight: DevicePtr,
    output: DevicePtr,
    batch_size: u32,
    num_k_heads: u32,
    num_v_heads: u32,
    k_dim: u32,
    v_dim: u32,
    eps: f32,
    stream: u64,
) -> Result<()>
Expand description

2026-09-25: FP32 GDN decode fused with the gated RMS norm: the kernel normalises each v-head’s output in the same CTA and writes BF16, with no FP32 output buffer in global memory.