pub struct AwqKernelBuffers {
pub weight: Vec<u32>,
pub zeros: Vec<u32>,
pub scales: Vec<f16>,
pub zeros_w: usize,
}Expand description
The kernel-layout buffers for one linear layer.
Fields§
§weight: Vec<u32>[OC, IC/8] packed int4 weights.
zeros: Vec<u32>[OC, zeros_w] packed int4 zero-points.
scales: Vec<f16>[OC, 8 * zeros_w] scales.
zeros_w: usizeWords per zeros row (scales rows hold 8 * zeros_w).
Trait Implementations§
Source§impl Clone for AwqKernelBuffers
impl Clone for AwqKernelBuffers
Source§impl Debug for AwqKernelBuffers
impl Debug for AwqKernelBuffers
Source§impl PartialEq for AwqKernelBuffers
impl PartialEq for AwqKernelBuffers
impl StructuralPartialEq for AwqKernelBuffers
Auto Trait Implementations§
impl Freeze for AwqKernelBuffers
impl RefUnwindSafe for AwqKernelBuffers
impl Send for AwqKernelBuffers
impl Sync for AwqKernelBuffers
impl Unpin for AwqKernelBuffers
impl UnsafeUnpin for AwqKernelBuffers
impl UnwindSafe for AwqKernelBuffers
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self> ⓘ
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 moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self> ⓘ
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self> ⓘ
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