[CI]: Add core_model and cpu markers for L1 use case. (#1709)

Signed-off-by: zhumingjue <zhumingjue@huawei.com>

tests/diffusion/distributed/test_hsdp.py

@@ -11,7 +11,7 @@ import torch.nn as nn
 from vllm_omni.diffusion.data import DiffusionParallelConfig
 from vllm_omni.diffusion.distributed.hsdp import HSDPInferenceConfig
 
-pytestmark = [pytest.mark.diffusion, pytest.mark.parallel, pytest.mark.cpu]
+pytestmark = [pytest.mark.diffusion, pytest.mark.parallel, pytest.mark.cpu, pytest.mark.core_model]
 
 
 class TestHSDPInferenceConfig:

tests/diffusion/distributed/test_parallel_state_sp_groups.py

@@ -11,10 +11,7 @@ import torch
 
 from vllm_omni.diffusion.distributed.parallel_state import RankGenerator, set_seq_parallel_pg
 
-pytestmark = [
-    pytest.mark.diffusion,
-    pytest.mark.parallel,
-]
+pytestmark = [pytest.mark.diffusion, pytest.mark.parallel, pytest.mark.core_model, pytest.mark.cpu]
 
 
 def _fake_new_group_factory(created_groups: list[SimpleNamespace]):

tests/diffusion/distributed/test_sp_plan_hooks.py

@@ -47,6 +47,8 @@ requires_distributed = pytest.mark.skipif(
 pytestmark = [
     pytest.mark.diffusion,
     pytest.mark.parallel,
+    pytest.mark.core_model,
+    pytest.mark.cpu,
 ]
 
 # =============================================================================

tests/diffusion/distributed/test_vae_patch_parallel.py

@@ -8,6 +8,8 @@ import torch
 
 from vllm_omni.diffusion.distributed import vae_patch_parallel as vae_patch_parallel
 
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
+
 
 class _DummyConfig:
     def __init__(self, **attrs):

tests/diffusion/models/nextstep_1_1/test_nextstep_cfg_parallel_layout.py

@@ -8,6 +8,8 @@ import vllm_omni.diffusion.models.nextstep_1_1.pipeline_nextstep_1_1 as nextstep
 from vllm_omni.diffusion.models.nextstep_1_1.modeling_nextstep_heads import FlowMatchingHead
 from vllm_omni.diffusion.models.nextstep_1_1.pipeline_nextstep_1_1 import NextStep11Pipeline
 
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
+
 
 class _DummyImageHead:
     def __init__(self, token_dim: int):

tests/diffusion/models/z_image/test_zimage_tp_constraints.py

@@ -2,6 +2,8 @@ import pytest
 
 from vllm_omni.diffusion.models.z_image.z_image_transformer import validate_zimage_tp_constraints
 
+pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
+
 
 def test_validate_zimage_tp_constraints_tp2_ok():
     ffn_hidden_dim, final_out_dims, supported_tp = validate_zimage_tp_constraints(

tests/diffusion/test_multiproc_executor_concurrency.py

@@ -12,7 +12,7 @@ from vllm_omni.diffusion.data import DiffusionOutput
 from vllm_omni.diffusion.executor.multiproc_executor import MultiprocDiffusionExecutor
 from vllm_omni.diffusion.scheduler import Scheduler
 
-pytestmark = [pytest.mark.diffusion]
+pytestmark = [pytest.mark.diffusion, pytest.mark.core_model, pytest.mark.cpu]
 
 
 # ───────────────────────────────────────────── helpers ─────────────────────