anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: wangyu <410167048@qq.com>
This commit is contained in:
wangyu authored and GitHub committed 2026-04-22 15:14:20 +08:00
1 parent 554233208f
commit e18cb89d5a
50 files changed
+173 -322
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/examples/offline_inference/test_text_to_image.py
+2 -1
View File
@@ -11,7 +11,8 @@ from tests.examples.helpers import EXAMPLES, ExampleRunner, ReadmeSnippet
from tests.helpers.assertions import assert_image_valid
from tests.helpers.mark import hardware_marks
pytestmark = [pytest.mark.advanced_model, pytest.mark.example, *hardware_marks(res={"cuda": "H100"})]
pytestmark = [pytest.mark.full_model, pytest.mark.example, *hardware_marks(res={"cuda": "H100"})]
T2I_SCRIPT = EXAMPLES / "offline_inference" / "text_to_image" / "text_to_image.py"
README_PATH = T2I_SCRIPT.with_name("README.md")
tests/examples/online_serving/test_qwen2_5_omni.py
+3 -18
View File
@@ -4,9 +4,6 @@ See examples/online_serving/qwen2_5_omni/README.md
"""
import os
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
from pathlib import Path
import pytest
@@ -21,7 +18,9 @@ from tests.helpers.media import convert_audio_file_to_text, cosine_similarity_te
from tests.helpers.runtime import OmniServerParams
from tests.helpers.stage_config import get_deploy_config_path
pytestmark = [pytest.mark.advanced_model, pytest.mark.example]
pytestmark = [pytest.mark.full_model, pytest.mark.example, pytest.mark.omni]
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
models = ["Qwen/Qwen2.5-Omni-7B"]
@@ -40,8 +39,6 @@ test_params = [
common_args = ["python", os.path.join(example_dir, "openai_chat_completion_client_for_multimodal_generation.py")]
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_send_multimodal_request_001(omni_server) -> None:
@@ -77,8 +74,6 @@ def test_send_multimodal_request_001(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_send_multimodal_request_002(omni_server) -> None:
@@ -114,8 +109,6 @@ def test_send_multimodal_request_002(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_send_multimodal_request_003(omni_server) -> None:
@@ -141,8 +134,6 @@ def test_send_multimodal_request_003(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_modality_control_001(omni_server) -> None:
@@ -171,8 +162,6 @@ def test_modality_control_001(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_modality_control_002(omni_server) -> None:
@@ -200,8 +189,6 @@ def test_modality_control_002(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_modality_control_003(omni_server) -> None:
@@ -238,8 +225,6 @@ def test_modality_control_003(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_stream_001(omni_server) -> None:
tests/examples/online_serving/test_qwen3_omni.py
+3 -18
View File
@@ -4,9 +4,6 @@ See examples/online_serving/qwen3_omni/README.md
"""
import os
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
from pathlib import Path
import pytest
@@ -21,7 +18,9 @@ from tests.helpers.media import convert_audio_file_to_text, cosine_similarity_te
from tests.helpers.runtime import OmniServerParams
from tests.helpers.stage_config import get_deploy_config_path
pytestmark = [pytest.mark.advanced_model, pytest.mark.example]
pytestmark = [pytest.mark.full_model, pytest.mark.example, pytest.mark.omni]
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
models = ["Qwen/Qwen3-Omni-30B-A3B-Instruct"]
@@ -39,8 +38,6 @@ test_params = [
common_args = ["python", os.path.join(example_dir, "openai_chat_completion_client_for_multimodal_generation.py")]
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_send_multimodal_request_001(omni_server) -> None:
@@ -69,8 +66,6 @@ def test_send_multimodal_request_001(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_send_multimodal_request_002(omni_server) -> None:
@@ -102,8 +97,6 @@ def test_send_multimodal_request_002(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_send_multimodal_request_003(omni_server) -> None:
@@ -119,8 +112,6 @@ def test_send_multimodal_request_003(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_modality_control_001(omni_server) -> None:
@@ -143,8 +134,6 @@ def test_modality_control_001(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_modality_control_002(omni_server) -> None:
@@ -167,8 +156,6 @@ def test_modality_control_002(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_modality_control_003(omni_server) -> None:
@@ -199,8 +186,6 @@ def test_modality_control_003(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_stream_001(omni_server) -> None:
tests/examples/online_serving/test_text_to_image.py
+1 -1
View File
@@ -18,7 +18,7 @@ from tests.helpers.assertions import assert_image_valid
from tests.helpers.mark import hardware_marks
from tests.helpers.runtime import OmniServer, OmniServerParams
pytestmark = [pytest.mark.advanced_model, pytest.mark.example, *hardware_marks(res={"cuda": "H100"})]
pytestmark = [pytest.mark.full_model, pytest.mark.example, *hardware_marks(res={"cuda": "H100"})]
T2I_ONLINE_CLIENT = EXAMPLES / "online_serving" / "text_to_image" / "openai_chat_client.py"
EXAMPLE_OUTPUT_SUBFOLDER = "example_online_t2i"