Struct KvCachePolicyConfig

Source

pub struct KvCachePolicyConfig {
    pub q8_threshold: f32,
    pub q4_threshold: f32,
    pub hysteresis: f32,
    pub ewma_alpha: f32,
    pub min_level: KvCacheLevel,
    pub max_level: KvCacheLevel,
}

Expand description

Configuration for KvCachePolicy.

Default values: upgrade to Q8 above 80 % cache occupancy, upgrade to Q4 above 95 %; hysteresis margin 5 %; EWMA factor 0.20.

Fields§

§q8_threshold: f32

Cache occupancy threshold (0.0..=1.0) above which we upgrade FP16 → Q8.

§q4_threshold: f32

Cache occupancy threshold above which we upgrade Q8 → Q4.

§hysteresis: f32

Symmetric hysteresis margin: a downgrade fires only after pressure drops below threshold - hysteresis.

§ewma_alpha: f32

EWMA smoothing factor (alpha in s_t = alpha * x_t + (1-alpha)*s_{t-1}). Higher = more reactive, lower = more stable.

§min_level: KvCacheLevel

Initial / minimum tier — set to Fp16 to allow downgrade.

§max_level: KvCacheLevel

Maximum tier — set to Q4 to allow full compression range.

Implementations§

Source §

impl KvCachePolicyConfig

Source

pub fn fp16_only() -> Self

Conservative profile — never upgrades from FP16.

Source

pub fn aggressive() -> Self

Aggressive profile — starts at Q8 and reaches Q4 sooner.

Trait Implementations§

Source §

impl Clone for KvCachePolicyConfig

Source §

fn clone(&self) -> KvCachePolicyConfig

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

Source §

impl Debug for KvCachePolicyConfig

Source §

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

Formats the value using the given formatter. Read more

Source §

impl Default for KvCachePolicyConfig

Source §

fn default() -> Self

Returns the “default value” for a type. Read more

Auto Trait Implementations§

§

impl UnwindSafe for KvCachePolicyConfig

Blanket Implementations§

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

Source §

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

Source §

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

Source §

impl<T> From<T> for T

Source §

fn from(t: T) -> T

Returns the argument unchanged.

Source §

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

Source §

fn from_ref(input: &T) -> T

Converts to this type from a reference to the input type.

Source §

impl<T> Instrument for T

Source §

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

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

Source §

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.

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

Source §