Skip to main content

quantize_streaming_with_prefetch

Function quantize_streaming_with_prefetch 

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

Prefetch-aware sequential quantization for streaming data