Enum O1State 

pub enum O1State {
    Collecting {
        m: usize,
        w: usize,
        sink: usize,
        q_buf: Vec<f32>,
    },
    Sealed {
        states: Vec<NystromState>,
    },
}

Per-layer O(1) Nyström attention state (runtime attn_type override — spec §7 presence-driven pattern, no format change).

Collecting: the prompt pass still runs EXACT cache attention (the prefill outputs feed the residual stream, so they cannot be deferred) while the per-position rotated queries are buffered; o1_seal() then freezes landmarks + M from the full prompt, replays it into per-Q-head streaming states, and DROPS the full KV. Sealed: decode replaces cache attention with NystromState::step().

Variants

Collecting

Fields

m: usize

w: usize

sink: usize

q_buf: Vec<f32>

Rotated post-norm queries, [pos × num_heads × head_dim].

Sealed

One state per Q head: the far field T̂/Ẑ depends on that head’s own query landmarks, so GQA groups cannot share it. The window K/V is duplicated across the group’s Q heads (×heads_per_kv) — the price of keeping the golden-parity kernel intact; still O(1) in context and far below full KV at depth.

Fields

states: Vec<NystromState>

Trait Implementations

impl Clone for O1State

fn clone(&self) -> O1State

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for O1State

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.