Function scale_to_param 

pub fn scale_to_param(scale: f32, param: QuantParam) -> f32

Round a scale up to the smallest value representable by the param dtype that is no smaller.

Backends that keep scales in f32 must apply this when quantizing, so that the scale they divide by is the one that will actually be stored. Otherwise a tensor dequantizes differently after a save/load round trip.

Up rather than to nearest, because a scale is derived from the largest magnitude it has to cover. Rounding down puts that value past the end of the quantized range, where it clips, which measured several times worse than the coarser step rounding up costs.