Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
Tensor<Float> -> Tensor<QuantizedInt>
Scale and shift continuous floating-point inputs into low-bitwidth integer representations using predetermined quantization parameters.
Problem it solves
FHE execution pipelines require discrete integer inputs rather than raw high-precision floating-point values.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.