Enum HeadMode 

pub enum HeadMode {
    All,
    LastRow,
    Skip,
}

What the forward’s exit computes (chunked long-context prefill skips the head: the [t, vocab] logits block of a big chunk is gigabytes and reads/writes no state).

Variants

All

Exit mixer + lm_head on every row ([t, vocab] logits) — the historical shape.

LastRow

Exit mixer on the chunk, lm_head on the LAST row only ([vocab] logits).

Skip

No exit mixer, no lm_head, empty return (mid-prefill chunks).

Trait Implementations

impl Clone for HeadMode

fn clone(&self) -> HeadMode

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for HeadMode

impl Eq for HeadMode

impl PartialEq for HeadMode

fn eq(&self, other: &HeadMode) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for HeadMode