[Bug Fix] Hunyuan image cfg bugfix (#4752)

Signed-off-by: zhuhh97 <zhuhonghan@huawei.com>
Signed-off-by: dph97 <nenbaying@163.com>
Co-authored-by: zhuhh97 <z00806815@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/diffusion/test_diffusion_model_runner.py

@@ -509,6 +509,25 @@ def test_split_diffusion_output_by_request_slices_tuple_outputs():
     assert torch.equal(outputs[1].output[1], torch.tensor([20]))
 
 
+@pytest.mark.core_model
+@pytest.mark.cpu
+def test_execute_model_runs_forward_after_kv_receive(monkeypatch):
+    """execute_model runs the pipeline forward after the KV receive step."""
+    runner = _make_runner(cache_backend=None, cache_backend_name=None)
+    runner.kv_transfer_manager.receive_multi_kv_cache_distributed = lambda *a, **k: True
+    req = _make_request(skip_cache_refresh=True)
+
+    monkeypatch.setattr(model_runner_module, "set_forward_context", _noop_forward_context)
+    monkeypatch.setattr(model_runner_module.current_omni_platform, "reset_peak_memory_stats", lambda: None)
+    monkeypatch.setattr(model_runner_module.current_omni_platform, "max_memory_reserved", lambda: 0)
+    monkeypatch.setattr(model_runner_module.current_omni_platform, "max_memory_allocated", lambda: 0)
+
+    output = DiffusionModelRunner.execute_model(runner, req)
+
+    assert output.output == "ok"
+    assert runner.pipeline.forward_calls == 1
+
+
 @pytest.mark.core_model
 @pytest.mark.cpu
 def test_load_model_clears_cache_backend_for_unsupported_pipeline(monkeypatch):