[CI] Add local job runner scripts for L2-L4 pytest execution (#4672)

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

tests/dfx/perf/scripts/run_diffusion_benchmark.py

@@ -36,7 +36,7 @@ import pytest
 
 from benchmarks.diffusion.backends import endpoint_filename_token, normalize_endpoint
 
-pytestmark = [pytest.mark.diffusion, pytest.mark.full_model]
+pytestmark = [pytest.mark.diffusion, pytest.mark.full_model, pytest.mark.local_model]
 
 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
 os.environ.setdefault("DIFFUSION_ATTENTION_BACKEND", "FLASH_ATTN")