Enum VectorQuantization 

pub enum VectorQuantization {
    Float32,
    Float16,
    Int8,
}

Quantization format for in-memory vector storage.

Variants

Float32

Float32 quantization (default, full accuracy).

Float16

Float16 quantization (half memory footprint).

Int8

Int8 quantization (quarter memory footprint).

Trait Implementations

impl Clone for VectorQuantization

fn clone(&self) -> VectorQuantization

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for VectorQuantization

impl Debug for VectorQuantization

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

Formats the value using the given formatter.

impl Default for VectorQuantization

fn default() -> VectorQuantization

Returns the “default value” for a type.

impl Eq for VectorQuantization

impl FromStr for VectorQuantization

fn from_str(s: &str) -> Result<Self, Self::Err>

Parse a quantization name. Case-insensitive. Accepts float32, float16, and int8. The one canonical mapping shared by every binding.

type Err = VectorError

The associated error which can be returned from parsing.

impl PartialEq for VectorQuantization

fn eq(&self, other: &VectorQuantization) -> 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 VectorQuantization