Struct QuantizationParametersIr 

pub struct QuantizationParametersIr {
    pub scales: TensorIr,
    pub global: Option<TensorIr>,
}

Quantization parameters intermediate representation.

Fields

scales: TensorIr

The scaling factor, one per block or a single one for a per-tensor level.

global: Option<TensorIr>

The per-tensor scale that scales are expressed relative to, for a two-level scheme.

Trait Implementations

impl Clone for QuantizationParametersIr

fn clone(&self) -> QuantizationParametersIr

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizationParametersIr

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuantizationParametersIr

fn deserialize<__D>( __deserializer: __D, ) -> Result<QuantizationParametersIr, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for QuantizationParametersIr

impl Hash for QuantizationParametersIr

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

where __H: Hasher,

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 PartialEq for QuantizationParametersIr

fn eq(&self, other: &QuantizationParametersIr) -> 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 Serialize for QuantizationParametersIr

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for QuantizationParametersIr