Enum KvMode 

pub enum KvMode {
    F32,
    Q8 {
        k: bool,
        v: bool,
    },
}

KV storage mode. CMF_KV=q8 enables the q8_2f cache: an int8 row per (position, head) + an f32 scale per row + a per-channel scale field, frozen after WARMUP positions with retroactive requantization (D4: “KV-quant 2f”). Memory ×~3.7 smaller than f32.

Variants

F32

Q8

Quantized components: (K, V) — sensitivity diagnostics.

Fields

k: bool

v: bool

Implementations

impl KvMode

pub fn from_env() -> Self

Trait Implementations

impl Clone for KvMode

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for KvMode

impl Debug for KvMode

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

Formats the value using the given formatter.

impl Eq for KvMode

impl PartialEq for KvMode

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for KvMode