pub fn gdn_decode_f32_strided(
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,
qk_stride: u32,
v_stride: u32,
gb_stride: u32,
out_stride: u32,
stream: u64,
) -> Result<()>Expand description
2026-09-25: Strided FP32 GDN decode for several sequences in one launch:
Q/K/V, gate/beta and the output are rows qk_stride, v_stride,
gb_stride and out_stride apart per sequence.