pub fn gdn_prefill_regresident(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
h_state: DevicePtr,
query: DevicePtr,
key: DevicePtr,
value: DevicePtr,
gate: DevicePtr,
beta: DevicePtr,
output: DevicePtr,
batch_size: u32,
seq_len: 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: Token-sequential prefill recurrence with H in registers
(gated_delta_rule_prefill_regresident). One warp owns one v-column and
holds its 128 k-rows (4 per lane); there is no shared-memory H and no block
barrier. Requires k_dim == 128 and v_dim % 4 == 0 (4 warps per block).