Struct Quantizer

pub struct Quantizer {
    pub calibration: Calibration,
    pub scheme: QuantScheme,
}

Describes how to quantize a module.

Fields

calibration: Calibration

The calibration method used in quantization.

scheme: QuantScheme

The quantization scheme.

Trait Implementations

impl<B> ModuleMapper<B> for Quantizer

where B: Backend,

fn map_float<const D: usize>( &mut self, param: Param<Tensor<B, D>>, ) -> Param<Tensor<B, D>>

Map a float parameter in the module.

fn enter_module(&mut self, name: &str, container_type: &str)

Called when entering a submodule.

fn exit_module(&mut self, name: &str, container_type: &str)

Called when exiting a submodule.

fn map_int<const D: usize>( &mut self, param: Param<Tensor<B, D, Int>>, ) -> Param<Tensor<B, D, Int>>

Map an int parameter in the module.

fn map_bool<const D: usize>( &mut self, param: Param<Tensor<B, D, Bool>>, ) -> Param<Tensor<B, D, Bool>>

Map a bool parameter in the module.