Rollup merge of #109749 - compiler-errors:new-solver-float-var, r=lcnr

Canonicalize float var as float in new solver

Typo in new canonicalizer -- we should be canonicalizing float vars as `CanonicalTyVarKind::Float`, not `CanonicalTyVarKind::Int`.

Fixes compiler-errors/next-solver-hir-issues#9

compiler/rustc_trait_selection/src/solve/canonicalize.rs

@@ -291,7 +291,7 @@ impl<'tcx> TypeFolder<TyCtxt<'tcx>> for Canonicalizer<'_, 'tcx> {
                 if nt != t {
                     return self.fold_ty(nt);
                 } else {
-                    CanonicalVarKind::Ty(CanonicalTyVarKind::Int)
+                    CanonicalVarKind::Ty(CanonicalTyVarKind::Float)
                 }
             }
             ty::Infer(ty::FreshTy(_) | ty::FreshIntTy(_) | ty::FreshFloatTy(_)) => {