Skip to main content

quantize_with_cache_optimization

Function quantize_with_cache_optimization 

Source
pub fn quantize_with_cache_optimization(
    input: &[f32],
    scale: f32,
    zero_point: i32,
    output: &mut [f32],
    cache_params: Option<&CacheAwareParams>,
) -> Result<()>
Expand description

Auto-select optimal quantization algorithm based on cache analysis