pub fn gdn_carry_flush(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
h_table: DevicePtr,
table_layer_entries: u64,
carry_base: DevicePtr,
carry_layer_floats: u64,
slot_tab: DevicePtr,
pend: DevicePtr,
pend_layer_entries: u32,
seq_floats: u32,
batch_size: u32,
num_v_heads: u32,
layers: u32,
stream: u64,
) -> Result<()>Expand description
2026-09-26: Standalone fold (gdn_carry_flush) over layers GDN layers:
layer l reads its h pointers at entry l * table_layer_entries of
h_table, its stash at carry_base + l * carry_layer_floats floats and
its counts at pend + l * pend_layer_entries. A count of 0 leaves H alone;
pend is not cleared.