Struct QuantizedLinear 

pub struct QuantizedLinear { /* private fields */ }

Quantized Linear Layer

Performs matrix multiplication in INT8: output = (input @ weights^T + bias) * scale

Implementations

impl QuantizedLinear

pub fn from_fp32(linear: &Linear, input_scale: f32) -> Self

Create from FP32 Linear layer

Arguments

• linear - FP32 linear layer to quantize
• input_scale - Expected input activation scale

pub fn forward_int8( &self, input: &[u8], batch_size: usize, input_scale: f32, input_zero_point: u8, ) -> CnnResult<Tensor>

Forward pass with INT8 computation

Arguments

• input - Quantized u8 input tensor [batch, in_features]
• batch_size - Batch size
• input_scale - Input quantization scale
• input_zero_point - Input quantization zero point

pub fn in_features(&self) -> usize

Get input features

pub fn out_features(&self) -> usize

Get output features

Trait Implementations

impl Clone for QuantizedLinear

fn clone(&self) -> QuantizedLinear

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizedLinear

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

Formats the value using the given formatter.