Enum VecQuant 

pub enum VecQuant {
    F32,
    F16,
    Bf16,
    I8,
}

Scalar representation stored in the index (lower precision = less memory).

Variants

F32

32-bit float (default; full precision).

F16

16-bit half-precision IEEE float (half the memory, slight recall loss).

Bf16

16-bit brain float (half the memory, wider range than f16).

I8

8-bit integer quantization (quarter the memory).

Trait Implementations

impl Clone for VecQuant

fn clone(&self) -> VecQuant

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for VecQuant

impl Debug for VecQuant

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

Formats the value using the given formatter.

impl From<VecQuant> for ScalarKind

fn from(q: VecQuant) -> Self

Converts to this type from the input type.

impl ValueEnum for VecQuant

fn value_variants<'a>() -> &'a [Self]

All possible argument values, in display order.

fn to_possible_value<'a>(&self) -> Option<PossibleValue>

The canonical argument value.

fn from_str(input: &str, ignore_case: bool) -> Result<Self, String>

Parse an argument into Self.