[Test] Unify L2/L3 test layout, Buildkite steps, and test helpers (#2556)

Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>

tests/dfx/stability/scripts/test_stability_qwen3_omni.py

@@ -35,6 +35,7 @@ benchmark_indices = create_benchmark_indices(BENCHMARK_CONFIGS, server_to_benchm
 
 
 @pytest.mark.slow
+@pytest.mark.omni
 @pytest.mark.parametrize("omni_server", test_params, indirect=True)
 @pytest.mark.parametrize("stability_benchmark_params", benchmark_indices, indirect=True)
 def test_stability_qwen3_omni(omni_server, stability_benchmark_params):

tests/dfx/stability/scripts/test_stability_qwen3_tts.py

@@ -35,6 +35,7 @@ benchmark_indices = create_benchmark_indices(BENCHMARK_CONFIGS, server_to_benchm
 
 
 @pytest.mark.slow
+@pytest.mark.tts
 @pytest.mark.parametrize("omni_server", test_params, indirect=True)
 @pytest.mark.parametrize("stability_benchmark_params", benchmark_indices, indirect=True)
 def test_stability_qwen3_tts(omni_server, stability_benchmark_params):

tests/dfx/stability/scripts/test_stability_qwen_image.py

@@ -35,6 +35,7 @@ benchmark_indices = create_benchmark_indices(BENCHMARK_CONFIGS, server_to_benchm
 
 
 @pytest.mark.slow
+@pytest.mark.diffusion
 @pytest.mark.parametrize("omni_server", test_params, indirect=True)
 @pytest.mark.parametrize("stability_benchmark_params", benchmark_indices, indirect=True)
 def test_stability_qwen_image(omni_server, stability_benchmark_params):

tests/dfx/stability/scripts/test_stability_wan22.py

@@ -35,6 +35,7 @@ benchmark_indices = create_benchmark_indices(BENCHMARK_CONFIGS, server_to_benchm
 
 
 @pytest.mark.slow
+@pytest.mark.diffusion
 @pytest.mark.parametrize("omni_server", test_params, indirect=True)
 @pytest.mark.parametrize("stability_benchmark_params", benchmark_indices, indirect=True)
 def test_stability_wan22(omni_server, stability_benchmark_params):