Enum KvType 

pub enum KvType {
    Auto,
    F32,
    F16,
}

K/V activation precision for the decoder’s flash-attention path.

Variants

Auto

f16 for quantized weights, f32 for f32 weights. The best default.

F32

Full-precision K/V.

F16

Half-precision K/V.

Trait Implementations

impl Clone for KvType

fn clone(&self) -> KvType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for KvType

impl Debug for KvType

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

Formats the value using the given formatter.

impl Default for KvType

fn default() -> KvType

Returns the “default value” for a type.

impl Eq for KvType

impl PartialEq for KvType

fn eq(&self, other: &KvType) -> 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 StructuralPartialEq for KvType