Constant RECOGNIZER_ORDER 

pub const RECOGNIZER_ORDER: &[(&str, fn(&[Stmt<'_>], &Interner) -> Option<TensorOpSpec>)];

The recognizers a statement is tried against, in order — the CUDA orchestrator’s order, extended with the exact-shape recognizers it has no stage for. The composite blocks (moe, attention) go first: they contain matmul-like loops and a softmax the simpler recognizers would otherwise claim.