pub enum QuantizationMode {
Affine,
Mxfp4,
Mxfp8,
Nvfp4,
}Expand description
Packed weight format. All variants support CPU and Metal in MLX 0.32.2.
Defaults are (group size, bits): affine (64, 4), mxfp4 (32, 4), mxfp8 (32, 8), and nvfp4 (16, 4). Global scaling is not exposed.
Variants§
Affine
Integer quantization with a scale and bias per group.
Mxfp4
E2M1 values with E8M0 scales.
Mxfp8
E4M3 values with E8M0 scales.
Nvfp4
E2M1 values with E4M3 scales, without a global scale.
Trait Implementations§
Source§impl Clone for QuantizationMode
impl Clone for QuantizationMode
Source§fn clone(&self) -> QuantizationMode
fn clone(&self) -> QuantizationMode
Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreimpl Copy for QuantizationMode
Source§impl Debug for QuantizationMode
impl Debug for QuantizationMode
Source§impl Default for QuantizationMode
impl Default for QuantizationMode
Source§fn default() -> QuantizationMode
fn default() -> QuantizationMode
Returns the “default value” for a type. Read more
impl Eq for QuantizationMode
Source§impl PartialEq for QuantizationMode
impl PartialEq for QuantizationMode
impl StructuralPartialEq for QuantizationMode
Auto Trait Implementations§
impl Freeze for QuantizationMode
impl RefUnwindSafe for QuantizationMode
impl Send for QuantizationMode
impl Sync for QuantizationMode
impl Unpin for QuantizationMode
impl UnsafeUnpin for QuantizationMode
impl UnwindSafe for QuantizationMode
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 moreSource§impl<T> IntoOption<T> for T
impl<T> IntoOption<T> for T
Source§fn into_option(self) -> Option<T>
fn into_option(self) -> Option<T>
Convert into an
Option.