Skip to main content

quantize

burn_cubecl::kernel::quantization

Function quantize 

Source 
pub fn quantize(
    tensor: CubeTensor,
    scheme: &QuantScheme,
    scale: CubeTensor,
    global: Option<CubeTensor>,
) -> CubeTensor
Expand description

Convert the tensor to a lower precision data type based on the quantization scheme and parameters.