Function recognize_fused_row 

pub fn recognize_fused_row(
    stmts: &[Stmt<'_>],
    interner: &Interner,
) -> Result<FusedRowSpec, ReductionReject>

Recognize the fused row-op idiom. First it lifts the PER-ROW WEIGHTED RMSNorm shape (a row loop whose normalize body Push (X[idx] / denom) * W[col] gives x, weight, y, and whose enclosing loop bounds give rows/cols); failing that it falls back to the weightless flat rmsnorm/softmax sugar (rows == 1, cols == n) via recognize_reduction. Backend-agnostic (CUDA + Tenstorrent).