pub enum ExpertPrecision {
Hot,
Warm,
Cold,
}Expand description
Precision level assigned to an expert based on activation frequency.
The three tiers enable differentiated memory/quality tradeoffs:
- Hot: Maximum quality, higher memory usage
- Warm: Balanced quality/memory
- Cold: Aggressive compression, lower memory usage
Variants§
Hot
High precision for frequently-activated (hot) experts.
Typically Q4_K_M or higher for best quality on important experts.
Warm
Medium precision for moderately-activated (warm) experts.
Typically Q3_K or PiQ3 for balanced quality/memory.
Cold
Low precision for rarely-activated (cold) experts.
Typically Q2_K or PiQ2 for maximum compression on seldom-used experts.
Implementations§
Trait Implementations§
Source§impl Clone for ExpertPrecision
impl Clone for ExpertPrecision
Source§fn clone(&self) -> ExpertPrecision
fn clone(&self) -> ExpertPrecision
Returns a duplicate of the value. Read more
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Debug for ExpertPrecision
impl Debug for ExpertPrecision
Source§impl Hash for ExpertPrecision
impl Hash for ExpertPrecision
Source§impl PartialEq for ExpertPrecision
impl PartialEq for ExpertPrecision
impl Copy for ExpertPrecision
impl Eq for ExpertPrecision
impl StructuralPartialEq for ExpertPrecision
Auto Trait Implementations§
impl Freeze for ExpertPrecision
impl RefUnwindSafe for ExpertPrecision
impl Send for ExpertPrecision
impl Sync for ExpertPrecision
impl Unpin for ExpertPrecision
impl UnsafeUnpin for ExpertPrecision
impl UnwindSafe for ExpertPrecision
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
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
Source§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
Source§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
Source§impl<Q, K> Equivalent<K> for Q
impl<Q, K> Equivalent<K> for Q
Source§fn equivalent(&self, key: &K) -> bool
fn equivalent(&self, key: &K) -> bool
Compare self to
key and return true if they are equal.Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
Source§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
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