pub fn gdn_decode_chunk2(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
h_state: DevicePtr,
query: DevicePtr,
key: DevicePtr,
value: DevicePtr,
gate: DevicePtr,
beta: DevicePtr,
output: DevicePtr,
h_state_intermediate: 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,
stream: u64,
) -> Result<()>Expand description
2026-09-25: Two tokens through the GDN recurrence in one launch
(gated_delta_rule_chunk2). The state after the first token is written to
h_state_intermediate, for rollback when the draft is rejected. The
strides are in elements, not bytes.