[Bugfix] remove default sampling parameters (#2173)

This commit is contained in:
rein yang authored and GitHub committed 2026-03-25 20:34:13 -07:00
1 parent fb5d8ffd4e
commit 8305477750
4 files changed
+21 -60

No files matched your search

@@ -44,7 +44,6 @@ test_params = [
common_args = ["python", os.path.join(example_dir, "openai_chat_completion_client_for_multimodal_generation.py")]
@pytest.mark.skip(reason="issue #2168")
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@@ -82,7 +81,6 @@ def test_send_multimodal_request_001(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.skip(reason="issue #2168")
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@@ -120,7 +118,6 @@ def test_send_multimodal_request_002(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.skip(reason="issue #2168")
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@@ -129,7 +126,7 @@ def test_send_multimodal_request_003(omni_server) -> None:
command = [
"bash",
os.path.join(example_dir, "qwen2_5_omni/run_curl_multimodal_generation.sh"),
"use_mixed_modalities",
"mixed_modalities",
]
result = run_cmd(command)
@@ -148,7 +145,6 @@ def test_send_multimodal_request_003(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.skip(reason="issue #2168")
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@@ -179,7 +175,6 @@ def test_modality_control_001(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.skip(reason="issue #2168")
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@@ -209,7 +204,6 @@ def test_modality_control_002(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.skip(reason="issue #2168")
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})
@@ -248,7 +242,6 @@ def test_modality_control_003(omni_server) -> None:
# TODO: Verify the E2E latency after confirmation baseline.
@pytest.mark.skip(reason="issue #2168")
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards={"cuda": 4, "rocm": 2})