Skip to main content

AwqExpertPayload

ruda_model::tensor

Struct AwqExpertPayload

pub struct AwqExpertPayload<B>where
    B: Backend,{
    pub qweight: <B as BackendTypes>::IntTensorPrimitive,
    pub qzeros: <B as BackendTypes>::IntTensorPrimitive,
    pub scales: <B as BackendTypes>::FloatTensorPrimitive,
    pub bias: Option<<B as BackendTypes>::FloatTensorPrimitive>,
    pub options: AwqExpertOptions,
}

Expand description

Original AWQ expert cube, with scale storage independent of floating activation storage.

Fields§

§qweight: <B as BackendTypes>::IntTensorPrimitive

Original permuted I32 words [E,K,N/8].

§qzeros: <B as BackendTypes>::IntTensorPrimitive

Original I32 zero-point words [E,K/group,N/8].

§scales: <B as BackendTypes>::FloatTensorPrimitive

Original FP32/FP16/BF16 scales [E,K/group,N].

§bias: Option<<B as BackendTypes>::FloatTensorPrimitive>

Actual optional original frozen scale-dtype bias [E,N].

§options: AwqExpertOptions

Exact source geometry and explicit original global expert range.

Trait Implementations§

impl<B> Clone for AwqExpertPayload<B>
where B: Clone + Backend,

fn clone(&self) -> AwqExpertPayload<B>

Returns a duplicate of the value. Read more

1.0.0 (const: unstable) · Source§

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

Performs copy-assignment from source. Read more

impl<B> Debug for AwqExpertPayload<B>
where B: Debug + Backend,

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

Formats the value using the given formatter. Read more

Auto Trait Implementations§

impl<B> Freeze for AwqExpertPayload<B>
where <B as BackendTypes>::IntTensorPrimitive: Freeze, <B as BackendTypes>::FloatTensorPrimitive: Freeze, Option<<B as BackendTypes>::FloatTensorPrimitive>: Freeze,

impl<B> RefUnwindSafe for AwqExpertPayload<B>
where <B as BackendTypes>::IntTensorPrimitive: RefUnwindSafe, <B as BackendTypes>::FloatTensorPrimitive: RefUnwindSafe, Option<<B as BackendTypes>::FloatTensorPrimitive>: RefUnwindSafe,

impl<B> Send for AwqExpertPayload<B>
where <B as BackendTypes>::IntTensorPrimitive: Send, <B as BackendTypes>::FloatTensorPrimitive: Send, Option<<B as BackendTypes>::FloatTensorPrimitive>: Send,

impl<B> Sync for AwqExpertPayload<B>
where <B as BackendTypes>::IntTensorPrimitive: Sync, <B as BackendTypes>::FloatTensorPrimitive: Sync, Option<<B as BackendTypes>::FloatTensorPrimitive>: Sync,

impl<B> Unpin for AwqExpertPayload<B>
where <B as BackendTypes>::IntTensorPrimitive: Unpin, <B as BackendTypes>::FloatTensorPrimitive: Unpin, Option<<B as BackendTypes>::FloatTensorPrimitive>: Unpin,

impl<B> UnsafeUnpin for AwqExpertPayload<B>
where <B as BackendTypes>::IntTensorPrimitive: UnsafeUnpin, <B as BackendTypes>::FloatTensorPrimitive: UnsafeUnpin, Option<<B as BackendTypes>::FloatTensorPrimitive>: UnsafeUnpin,

impl<B> UnwindSafe for AwqExpertPayload<B>
where <B as BackendTypes>::IntTensorPrimitive: UnwindSafe, <B as BackendTypes>::FloatTensorPrimitive: UnwindSafe, Option<<B as BackendTypes>::FloatTensorPrimitive>: UnwindSafe,

Blanket Implementations§

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

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more

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

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more

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

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

Mutably borrows from an owned value. Read more

impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
where ST: ?Sized, DT: ?Sized,

impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
where ST: ?Sized, DT: ?Sized,

impl<T> CloneToUninit for T
where T: Clone,

unsafe fn clone_to_uninit(&self, dest: *mut u8)

🔬This is a nightly-only experimental API. (clone_to_uninit)

Performs copy-assignment from self to dest. Read more

impl<T> From<T> for T

fn from(t: T) -> T

Returns the argument unchanged.

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

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> Read<Exclusive, BecauseExclusive> for T
where T: ?Sized,

impl<T> ToOwned for T
where T: Clone,

type Owned = T

The resulting type after obtaining ownership.

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more

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

type Error = !

The type returned in the event of a conversion error.

fn try_from(value: U) -> Result<T, !>

Performs the conversion.

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.