Struct burn::tensor::quantization::QuantizationParametersPrimitive

pub struct QuantizationParametersPrimitive<B>
where
    B: Backend,
{
    pub scale: <B as Backend>::FloatTensorPrimitive,
    pub offset: Option<<B as Backend>::IntTensorPrimitive>,
}

The quantization parameters primitive.

Remarks

This is a low-level struct used internally by the library to provide the quantization parameters to the backends. It is not designed for direct usage by users, and not recommended to import or use this struct directly.

Users should prefer the QuantizationParameters struct, which is designed for public use.

Fields

scale: <B as Backend>::FloatTensorPrimitive

The scaling factor.

offset: Option<<B as Backend>::IntTensorPrimitive>

The zero-point offset.

Trait Implementations

impl<B> From<QuantizationParameters<B>> for QuantizationParametersPrimitive<B>

where B: Backend,

fn from(value: QuantizationParameters<B>) -> QuantizationParametersPrimitive<B>

Converts to this type from the input type.

impl<B> From<QuantizationParametersPrimitive<Fusion<B>>> for FusionQuantizationParameters<<B as FusionBackend>::FusionRuntime>

where B: FusionBackend,

fn from( value: QuantizationParametersPrimitive<Fusion<B>>, ) -> FusionQuantizationParameters<<B as FusionBackend>::FusionRuntime>

Converts to this type from the input type.