Enum QuantValue 

pub enum QuantValue {
    Q8F,
    E5M2,
    E4M3,
    Q4F,
    E2M1,
    Q2F,
    Q8S,
    Q4S,
    Q2S,
}

Data type used to represent quantized values.

Variants

Q8F

8-bit quantization with full range.

E5M2

8-bit floating point, e5m2 format.

E4M3

8-bit floating point, e4m3 format.

Q4F

4-bit quantization with full range.

E2M1

4-bit floating point, e2m1 format.

Q2F

2-bit quantization with full range.

Q8S

8-bit quantization with symmetric range.

Q4S

4-bit quantization with symmetric range.

Q2S

2-bit quantization with symmetric range.

Implementations

impl QuantValue

pub fn size_bits(&self) -> usize

Returns the size of the quantization input type in bits.

pub fn native_packing(&self) -> usize

Packing factor for the native representation used for intermediate values. If > 1, values should always be processed in native_packing sized chunks.

pub fn range(&self) -> (f32, f32)

The possible range of values allowed by the quant value.

pub fn is_symmetric(&self) -> bool

If the range of values is symmetric around zero.

Trait Implementations

impl Clone for QuantValue

fn clone(&self) -> QuantValue

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantValue

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuantValue

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Hash for QuantValue

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl Ord for QuantValue

fn cmp(&self, other: &QuantValue) -> Ordering

This method returns an Ordering between self and other.

fn max(self, other: Self) -> Self

where Self: Sized,

Compares and returns the maximum of two values.

fn min(self, other: Self) -> Self

where Self: Sized,

Compares and returns the minimum of two values.

fn clamp(self, min: Self, max: Self) -> Self

where Self: Sized,

Restrict a value to a certain interval.

impl PartialEq for QuantValue

fn eq(&self, other: &QuantValue) -> 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 PartialOrd for QuantValue

fn partial_cmp(&self, other: &QuantValue) -> Option<Ordering>

This method returns an ordering between self and other values if one exists.

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

Tests less than (for self and other) and is used by the < operator.

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

Tests less than or equal to (for self and other) and is used by the <= operator.

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

Tests greater than (for self and other) and is used by the > operator.

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

Tests greater than or equal to (for self and other) and is used by the >= operator.

impl Serialize for QuantValue

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for QuantValue

impl Eq for QuantValue

impl StructuralPartialEq for QuantValue