Enum KVCacheType 

pub enum KVCacheType {
    F32,
    TurboQuantMSE {
        bits: u8,
    },
    TurboQuantProd {
        bits: u8,
    },
}

Which KV cache implementation to use.

Variants

F32

Standard f32 KV cache (default).

TurboQuantMSE

TurboQuant MSE: Hadamard rotation + scalar quantization (biased, lower overhead).

Fields

bits: u8

TurboQuantProd

TurboQuant prod: MSE + QJL correction (unbiased, higher accuracy).

Fields

bits: u8

Implementations

impl KVCacheType

pub fn to_tq_config(&self, dim: usize) -> Option<TurboQuantConfig>

Convert to a TurboQuantConfig if this is a TurboQuant variant.

pub fn is_turboquant(&self) -> bool

Whether this is any TurboQuant variant.

Trait Implementations

impl Clone for KVCacheType

fn clone(&self) -> KVCacheType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for KVCacheType

impl Debug for KVCacheType

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

Formats the value using the given formatter.

impl Default for KVCacheType

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for KVCacheType

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for KVCacheType

impl PartialEq for KVCacheType

fn eq(&self, other: &KVCacheType) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for KVCacheType

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for KVCacheType