diff --git a/modelopt/torch/sparsity/state_sparsity/policy.py b/modelopt/torch/sparsity/state_sparsity/policy.py
index 52097f05e76..7baf53e9586 100644
--- a/modelopt/torch/sparsity/state_sparsity/policy.py
+++ b/modelopt/torch/sparsity/state_sparsity/policy.py
@@ -520,7 +520,7 @@ def validate_dasc_decay_parameters(model: nn.Module, policy: DASCPolicy) -> None
                     "DASC policy head mask does not match current decay parameters in layer "
                     f"{name!r}"
                 )
-        stored = torch.tensor(layer.static_horizons, dtype=torch.float64)
+        stored = torch.tensor(layer.static_horizons, device="cpu", dtype=torch.float64)
         numerical_slack = 32.0 * torch.finfo(torch.float64).eps
         if torch.any(stored < lower * (1.0 - numerical_slack)) or torch.any(
             stored > upper * (1.0 + numerical_slack)
diff --git a/tests/unit/torch/sparsity/state_sparsity/test_dasc.py b/tests/unit/torch/sparsity/state_sparsity/test_dasc.py
index ddf4023d6f2..cad44b1501d 100644
--- a/tests/unit/torch/sparsity/state_sparsity/test_dasc.py
+++ b/tests/unit/torch/sparsity/state_sparsity/test_dasc.py
@@ -508,6 +508,17 @@ def test_horizon_computation_ignores_the_default_device():
     assert horizons.device.type == "cpu"
 
 
+def test_policy_lifecycle_ignores_the_default_device():
+    """Keep calibration and checkpoint metadata validation on their declared CPU path."""
+    model = TinyGatedDeltaNetForCausalLM()
+    with torch.device("meta"):
+        calibrated = mtss.calibrate(model, _config(wmax_candidates=[7]), [_candidate(7)])
+        state = mto.modelopt_state(calibrated)
+        policy = mtss.export_policy(calibrated)
+    assert state["modelopt_state_dict"][0][0] == "dasc"
+    assert policy["layers"]["linear_attn"]["static_horizons"]
+
+
 def test_bf16_storage_round_trip_loaded_in_fp32_preserves_policy():
     """Accept BF16-rounded values after a checkpoint loader materializes FP32 tensors."""
     model = mtss.calibrate(