Struct AttendJob 

pub struct AttendJob;

The word a hybrid engine’s core gives its attention side with a token-row of an attention job (Streaming::attention), its fields from the lowest bit, each 32 bits but the last: the row’s region (its first line), its block’s keys’, values’, key scales’ and value scales’ offsets in it, the cached heads, the row’s positions (its own and every one before), the score scale’s bits, the store beats of the row’s query and of its output, and the query heads (16 bits).

Implementations

impl AttendJob

pub const REGION: usize = 0

pub const KEYS: usize = 32

pub const VALUES: usize = 64

pub const KEY_SCALES: usize = 96

pub const VALUE_SCALES: usize = 128

pub const KV_HEADS: usize = 160

pub const POSITIONS: usize = 192

pub const SCALE: usize = 224

pub const QUERY: usize = 256

pub const OUTPUT: usize = 288

pub const HEADS: usize = 320

pub const BITS: usize = 336