[CI] Update test markers and configurations to use 'full_model' for L4 nightly tests (#2641)

Signed-off-by: wangyu <410167048@qq.com>

tests/dfx/perf/scripts/run_benchmark.py

@@ -17,6 +17,9 @@ from tests.dfx.conftest import (
 )
 from tests.helpers.runtime import OmniServer
 
+pytestmark = [pytest.mark.full_model, pytest.mark.omni]
+
+
 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
 os.environ["VLLM_TEST_CLEAN_GPU_MEMORY"] = "0"
 
@@ -293,6 +296,7 @@ def assert_result(
                 print(f"ERROR: Test results exceeded baseline: {metric_name}: {current_value} < {baseline_value}")
 
 
+@pytest.mark.benchmark
 @pytest.mark.parametrize("omni_server", test_params, indirect=True)
 @pytest.mark.parametrize("benchmark_params", benchmark_indices, indirect=True)
 def test_performance_benchmark(omni_server, benchmark_params):

tests/dfx/perf/scripts/run_diffusion_benchmark.py

@@ -32,6 +32,8 @@ from typing import Any, cast
 import psutil
 import pytest
 
+pytestmark = [pytest.mark.diffusion, pytest.mark.full_model]
+
 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
 os.environ["VLLM_TEST_CLEAN_GPU_MEMORY"] = "0"
 os.environ.setdefault("DIFFUSION_ATTENTION_BACKEND", "FLASH_ATTN")
@@ -662,8 +664,7 @@ def assert_result(result: dict[str, Any], params: dict[str, Any]) -> None:
 # ---------------------------------------------------------------------------
 # Test entry point
 # ---------------------------------------------------------------------------
-
-
+@pytest.mark.benchmark
 @pytest.mark.parametrize(
     "diffusion_server",
     server_params,