* add fused group_norm/norm, mul, add * fix spacing * revert rms_norm logic * fix trailing whitespace
argsort
div
sub
addrows
sigmoid
group_norm
* opencl: add `argsort` * opencl: add `div` * opencl: add `add_rows` * opencl: add `sub` * opencl: add `sigmoid`, both `f16` and `f32` * opencl: add `group_norm`