Trait LayerWriteOnAccept 

pub trait LayerWriteOnAccept {
    // Provided methods
    fn gdn_woa_stash_seq_floats(&self) -> Option<usize> { ... }
    fn gdn_woa_bind(&self, _flag: DevicePtr, _stash: DevicePtr, _seqs: usize) { ... }
    fn gdn_carry_seq_floats(&self) -> Option<usize> { ... }
    fn gdn_carry_bind(&self, _binding: GdnCarryBinding) { ... }
    fn gdn_verify_run_batched(
        &self,
        _states: &[&mut (dyn LayerState + 'static)],
        _kk: usize,
        _gdn_wyn: bool,
        _wy_tables: DevicePtr,
    ) -> Result<Option<bool>> { ... }
    fn gdn_fold_accepted(
        &self,
        _gpu: &dyn GpuBackend,
        _h_table: DevicePtr,
        _na_tab: DevicePtr,
        _k_rows: usize,
        _n: usize,
        _stream: u64,
    ) -> Result<bool> { ... }
}

2026-09-26: A supertrait of TransformerLayer; see the module header.

Provided Methods

fn gdn_woa_stash_seq_floats(&self) -> Option<usize>

2026-09-25: Per-sequence write-on-accept stash size in f32 elements when this layer can run write-on-accept, None otherwise (the default). The model sizes the stash from the largest answer and binds each GDN layer with Self::gdn_woa_bind.

fn gdn_woa_bind(&self, _flag: DevicePtr, _stash: DevicePtr, _seqs: usize)

2026-09-25: Bind this layer’s write-on-accept flag word and stash slab (seqs sequences of Self::gdn_woa_stash_seq_floats f32 each). The model calls it once, on the first write-on-accept request and before its graph decision, and never moves the buffers afterwards (gdn_woa.rs).

fn gdn_carry_seq_floats(&self) -> Option<usize>

2026-09-26: Per-slot carried-state stash size in f32 elements when this layer can run the carried-state verify, None otherwise (the default).

fn gdn_carry_bind(&self, _binding: GdnCarryBinding)

2026-09-26: Bind this layer’s carried-state buffers. Called once, before any capture; the buffers never move afterwards.

fn gdn_verify_run_batched( &self, _states: &[&mut (dyn LayerState + 'static)], _kk: usize, _gdn_wyn: bool, _wy_tables: DevicePtr, ) -> Result<Option<bool>>

2026-09-30: Whether a batched verify runs one run of states (adjacent sequences of width kk, under the WY tables at wy_tables) through the batched conv and the table-form WY, as this layer’s own batched verify decides it; None for a layer without a batched GDN verify (the default). The circuit executor picks each run’s arm with it.

fn gdn_fold_accepted( &self, _gpu: &dyn GpuBackend, _h_table: DevicePtr, _na_tab: DevicePtr, _k_rows: usize, _n: usize, _stream: u64, ) -> Result<bool>

2026-09-25: Apply the accepted rows of the last batched verify to this layer’s h states. h_table is the layer’s WY pointer-table slice, na_tab a device u32[n] of accepted row counts in batch order. Ok(false) when the layer did nothing, as the default does.

Implementors

impl LayerWriteOnAccept for Qwen3AttentionLayer

impl LayerWriteOnAccept for Qwen3SsmLayer