router: catch CuTeDSL warmup failures fast, don't let MLIR errors slow down init

dsv4/ops/router.py

@@ -36,11 +36,15 @@ def warmup_router_compilation(router) -> None:
     """
     if router.mode == "dense":
         # Dummy forward at small N triggers decode-path compile.
+        # CuTeDSL fused kernel is WIP — falls through to prefill path.
         dummy = torch.zeros(
             1, router.hidden_size,
             dtype=torch.bfloat16, device=router.device,
         )
-        router._run_dense_impl(dummy)
+        try:
+            router._run_dense_impl(dummy)
+        except Exception:
+            pass  # CuTeDSL kernel not yet working; prefill path is fine
     else:
         dummy = torch.zeros(1, dtype=torch.int32, device=router.device)
         router._run_hash_impl(dummy)