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

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

tests/e2e/offline_inference/test_quantization_fp8.py

@@ -27,9 +27,6 @@ Usage:
 """
 
 import os
-
-os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
-
 from pathlib import Path
 from typing import Any
 
@@ -44,6 +41,8 @@ from vllm_omni.platforms import current_omni_platform
 
 pytestmark = [pytest.mark.core_model, pytest.mark.diffusion]
 
+os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
+
 # ─── helpers ──────────────────────────────────────────────────────────────────