Enum MaskKind 

pub enum MaskKind {
    None,
    Causal,
    SlidingWindow(usize),
    Custom,
    Bias,
}

What kind of attention mask the kernel should apply.

Borrowed from MAX’s nn/attention/mha_mask.mojo pattern (#20 in PLAN.md): one attention kernel handles all variants by branching on the mask kind, instead of forcing every caller to materialize a mask tensor. The win is two-fold:

1. None — single unpadded sequence: no mask load, no per-key compare in the inner loop.
2. Causal — autoregressive decode: kernel generates the upper- triangular fill from (qi, ki) directly; no seq² mask tensor ever exists.

Custom is the existing path — read mask values from the 4th input.

Variants

None

No masking — every position attends to every position.

Causal

Causal (autoregressive) — position qi attends only to ki <= qi.

SlidingWindow(usize)

Sliding window — position qi attends to ki ∈ [qi - w, qi].

Custom

Read mask values from the input tensor (default; matches BERT padding-mask behavior). Tensor shape [batch, key_len] with 1.0 = valid, <0.5 = ignored.

Bias

Additive per-head, per-query bias tensor [batch, num_heads, query_len, key_len] added to the QK^T · scale scores before softmax. Lets DETR-style boxRPB and other learned position biases reuse the fast Op::Attention path instead of decomposing into matmul + add + softmax + matmul.

Trait Implementations

impl Clone for MaskKind

fn clone(&self) -> MaskKind

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for MaskKind

impl Debug for MaskKind

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for MaskKind

fn deserialize<__D>( __deserializer: __D, ) -> Result<MaskKind, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for MaskKind

impl Hash for MaskKind

fn hash<__H>(&self, state: &mut __H)

where __H: Hasher,

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for MaskKind

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for MaskKind

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for MaskKind