Struct TransformerDecoderLayerAutoregressiveCache

pub struct TransformerDecoderLayerAutoregressiveCache<B>where
    B: Backend,{
    pub cross_attn: MhaCache<B>,
    pub self_attn: MhaCache<B>,
    pub pwff: TensorCache<B, 3>,
    pub norm_1: TensorCache<B, 3>,
    pub norm_2: TensorCache<B, 3>,
    pub norm_3: TensorCache<B, 3>,
}

Expand description

Autoregressive cache for a single Transformer Decoder Layer.

Fields§

§cross_attn: MhaCache

Cross-attention cache.

§self_attn: MhaCache

Self-attention cache.

§pwff: TensorCache<B, 3>

Position-wise feed-forward cache.

§norm_1: TensorCache<B, 3>

First layer norm cache.

§norm_2: TensorCache<B, 3>

Second layer norm cache.

§norm_3: TensorCache<B, 3>

Third layer norm cache.

Implementations§

§

impl TransformerDecoderLayerAutoregressiveCache
where B: Backend,

pub fn empty() -> TransformerDecoderLayerAutoregressiveCache

Create an empty cache.

Auto Trait Implementations§

§

impl Freeze for TransformerDecoderLayerAutoregressiveCache
where ::FloatTensorPrimitive: Freeze, ::QuantizedTensorPrimitive: Freeze,

§

impl RefUnwindSafe for TransformerDecoderLayerAutoregressiveCache
where ::FloatTensorPrimitive: RefUnwindSafe, ::QuantizedTensorPrimitive: RefUnwindSafe,

§

impl Send for TransformerDecoderLayerAutoregressiveCache

§

impl Sync for TransformerDecoderLayerAutoregressiveCache

§

impl Unpin for TransformerDecoderLayerAutoregressiveCache
where ::FloatTensorPrimitive: Unpin, ::QuantizedTensorPrimitive: Unpin,

§

impl UnwindSafe for TransformerDecoderLayerAutoregressiveCache
where ::FloatTensorPrimitive: UnwindSafe, ::QuantizedTensorPrimitive: UnwindSafe,

Blanket Implementations§

§

impl<T> Adaptor<()> for T

§

fn adapt(&self)

Adapt the type to be passed to a metric.

Source §

impl<T> Any for T
where T: 'static + ?Sized,

Source §

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

Source §

impl<T> Borrow<T> for T
where T: ?Sized,

Source §

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

Source §

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source §

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more

§

fn from(t: T) -> T

Returns the argument unchanged.

§

impl<T> Instrument for T

§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided [Span], returning an Instrumented wrapper. Read more

§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more

Source §

impl<T, U> Into for T
where U: From<T>,

Source §

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

§

impl<T> IntoComptime for T

§

fn comptime(self) -> Self

Source §

impl<T> IntoEither for T

Source §

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

Source §

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more

§