--- BVT pytest attempt 2026-07-07T12:20:05.648929+00:00 (/.local/bin/uv --directory /home/odh/opendatahub-tests...) --- 2026-07-07T12:20:07.589497Z [info ] Writing tests log to /home/odh/opendatahub-tests/results/pytest-tests.log [conftest] 2026-07-07T12:20:07.589795Z [info ] Trying to get client via new_client_from_config [ocp_resources.resource] 2026-07-07T12:20:07.737230Z [info ] kind: DataScienceCluster api version: datasciencecluster.opendatahub.io/v2 [ocp_resources.resource] 2026-07-07T12:20:07.814976Z [info ] kind: DSCInitialization api version: dscinitialization.opendatahub.io/v2 [ocp_resources.resource] ============================= test session starts ============================== platform linux -- Python 3.14.5, pytest-9.0.3, pluggy-1.6.0 -- /home/odh/opendatahub-tests/.venv/bin/python3 cachedir: .pytest_cache metadata: {'Python': '3.14.5', 'Platform': 'Linux-5.14.0-570.120.1.el9_6.x86_64-x86_64-with-glibc2.42', 'Packages': {'pytest': '9.0.3', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.13.0', 'langsmith': '0.8.5', 'asyncio': '1.3.0', 'dependency': '0.6.1', 'html': '4.2.0', 'metadata': '3.1.1', 'order': '1.4.0', 'progress': '1.4.0', 'testconfig': '0.2.0', 'xdist': '3.8.0', 'syrupy': '5.2.0'}} rootdir: /home/odh/opendatahub-tests configfile: pytest.ini plugins: anyio-4.13.0, langsmith-0.8.5, asyncio-1.3.0, dependency-0.6.1, html-4.2.0, metadata-3.1.1, order-1.4.0, progress-1.4.0, testconfig-0.2.0, xdist-3.8.0, syrupy-5.2.0 asyncio: mode=Mode.STRICT, debug=False, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collecting ... collected 57 items / 48 deselected / 9 selected tests/model_serving/model_runtime/mlserver/model_car/test_mlserver_model_car.py::TestMLServerModelCar::test_mlserver_model_car_inference[sklearn-modelcar-standard]  ----------------------------- test_mlserver_model_car_inference[sklearn-modelcar-standard] ----------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:20:08.063687Z [info ] Executing session fixture: event_loop_policy [conftest] 2026-07-07T12:20:08.063872Z [info ] Executing session fixture: _syrupy_apply_ide_patches [conftest] 2026-07-07T12:20:08.064032Z [info ] Executing session fixture: admin_client [conftest] 2026-07-07T12:20:08.064221Z [info ] Trying to get client via new_client_from_config [ocp_resources.resource] 2026-07-07T12:20:08.067571Z [info ] Executing session fixture: dsc_resource [conftest] 2026-07-07T12:20:08.067727Z [info ] kind: DataScienceCluster api version: datasciencecluster.opendatahub.io/v2 [ocp_resources.resource] 2026-07-07T12:20:08.145084Z [info ] Executing session fixture: tmp_path_factory [conftest] 2026-07-07T12:20:08.145445Z [info ] Executing session fixture: tests_tmp_dir [conftest] 2026-07-07T12:20:08.146754Z [info ] Executing session fixture: os_path_environment [conftest] 2026-07-07T12:20:08.147010Z [info ] Executing session fixture: tmpdir_factory [conftest] 2026-07-07T12:20:08.147234Z [info ] Executing session fixture: bin_directory [conftest] 2026-07-07T12:20:08.148454Z [info ] Executing session fixture: oc_binary_path [conftest] 2026-07-07T12:20:08.167986Z [info ] kind: ConsoleCLIDownload api version: console.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:20:08.206254Z [info ] All oc console cli download links: ['https://downloads-openshift-console.apps.rosa.nmanos-konflux1.durx.p3.openshiftapps.com/amd64/linux/oc.tar'] [utilities.infra] name=utilities.infra 2026-07-07T12:20:08.206383Z [info ] Downloading archive using: url=https://downloads-openshift-console.apps.rosa.nmanos-konflux1.durx.p3.openshiftapps.com/amd64/linux/oc.tar [utilities.infra] name=utilities.infra 2026-07-07T12:20:08.937155Z [info ] Extract the downloaded archive. [utilities.infra] name=utilities.infra 2026-07-07T12:20:09.021545Z [info ] Downloaded file: ['oc']  [utilities.infra] name=utilities.infra 2026-07-07T12:20:09.039924Z [info ] Executing session fixture: bin_directory_to_os_path [conftest] 2026-07-07T12:20:09.038716Z [info ] OC binary path: /tmp/pytest-3QJtT3LDwz7RVuLypQKAgW/bin0/oc [tests.conftest] name=tests.conftest 2026-07-07T12:20:09.038780Z [info ] Adding /tmp/pytest-3QJtT3LDwz7RVuLypQKAgW/bin0 to $PATH [tests.conftest] name=tests.conftest 2026-07-07T12:20:09.040447Z [info ] Executing session fixture: nodes [conftest] 2026-07-07T12:20:10.347398Z [info ] Executing session fixture: dsci_resource [conftest] 2026-07-07T12:20:10.347623Z [info ] kind: DSCInitialization api version: dscinitialization.opendatahub.io/v2 [ocp_resources.resource] 2026-07-07T12:20:10.366992Z [info ] Executing session fixture: record_testsuite_property [conftest] 2026-07-07T12:20:10.367157Z [info ] Executing session fixture: junitxml_plugin [conftest] 2026-07-07T12:20:10.367331Z [info ] Executing session fixture: cluster_sanity_scope_session [conftest] 2026-07-07T12:20:10.366146Z [info ] Check cluster sanity.  [utilities.infra] name=utilities.infra 2026-07-07T12:20:10.367593Z [info ] Verify all nodes are in a healthy condition. [ocp_utilities.infra] 2026-07-07T12:20:10.423136Z [info ] Verify all nodes are schedulable. [ocp_utilities.infra] 2026-07-07T12:20:10.479389Z [warning ] Skipping RHOAI resource checks, got --cluster-sanity-skip-rhoai-check [utilities.infra] name=utilities.infra 2026-07-07T12:20:10.481887Z [info ] Executing session fixture: autouse_fixtures [conftest] 2026-07-07T12:20:10.482033Z [info ] Executing session fixture: pytestconfig [conftest] 2026-07-07T12:20:10.482175Z [info ] Executing session fixture: teardown_resources [conftest] 2026-07-07T12:20:10.482408Z [info ] Executing session fixture: mlserver_runtime_image [conftest] 2026-07-07T12:20:10.482544Z [info ] Executing class fixture: model_namespace [conftest] 2026-07-07T12:20:10.482669Z [info ] Create Namespace sklearn-modelcar [ocp_resources Namespace] 2026-07-07T12:20:10.482778Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Namespace', 'metadata': {'name': 'sklearn-modelcar'}, 'spec': {}} [ocp_resources Namespace] 2026-07-07T12:20:10.534289Z [info ] Wait for Namespace sklearn-modelcar status to be Active [ocp_resources Namespace] 2026-07-07T12:20:10.534452Z [info ] Waiting for 120 seconds [0:02:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:20:10.569817Z [info ] Status of Namespace sklearn-modelcar is Active [ocp_resources Namespace] 2026-07-07T12:20:10.569967Z [info ] Elapsed time: 0.00010538101196289062 [0:00:00.000105] [timeout_sampler] 2026-07-07T12:20:10.570091Z [info ] Executing class fixture: mlserver_serving_runtime [conftest] 2026-07-07T12:20:10.570243Z [info ] kind: Template api version: template.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:20:10.702259Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:20:10.702457Z [info ] Create ServingRuntime mlserver-runtime [ocp_resources ServingRuntime] 2026-07-07T12:20:10.702693Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': '1.7.1', 'openshift.io/display-name': 'MLServer ServingRuntime for KServe', 'serving.kserve.io/server-type': 'mlserver'}, 'labels': {'opendatahub.io/dashboard': 'true'}, 'name': 'mlserver-runtime', 'namespace': 'sklearn-modelcar'}, 'spec': {'annotations': {'monitoring.opendatahub.io/scrape': 'true', 'opendatahub.io/kserve-runtime': 'mlserver', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8082'}, 'containers': [{'env': [{'name': 'MLSERVER_MODEL_IMPLEMENTATION', 'value': '{{.Labels.modelClass}}'}, {'name': 'MLSERVER_HTTP_PORT', 'value': '8080'}, {'name': 'MLSERVER_MODELS_DIR', 'value': '/mnt/models'}], 'image': 'registry.redhat.io/rhoai/odh-mlserver-rhel9@sha256:ec5a786c5a01e83e3ccbadc2a6ccb8c38485baf6296bb6285baaef06c71aaba1', 'livenessProbe': {'failureThreshold': 6, 'httpGet': {'path': '/v2/models/{{.Name}}/ready', 'port': 8080}, 'initialDelaySeconds': 20, 'periodSeconds': 10, 'timeoutSeconds': 5}, 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}], 'readinessProbe': {'failureThreshold': 3, 'httpGet': {'path': '/v2/models/{{.Name}}/ready', 'port': 8080}, 'initialDelaySeconds': 5, 'periodSeconds': 5, 'timeoutSeconds': 5}, 'securityContext': {'allowPrivilegeEscalation': False, 'capabilities': {'drop': ['ALL']}, 'privileged': False, 'runAsNonRoot': True}, 'startupProbe': {'exec': {'command': ['/bin/sh', '-c', '[ -n "$(ls -A /mnt/models 2>/dev/null)" ]\n']}, 'failureThreshold': 1, 'initialDelaySeconds': 1, 'periodSeconds': 1}}], 'multiModel': False, 'protocolVersions': ['v2'], 'supportedModelFormats': [{'name': 'sklearn', 'version': '0'}, {'name': 'sklearn', 'version': '1'}, {'name': 'xgboost', 'version': '1'}, {'name': 'xgboost', 'version': '2'}, {'name': 'lightgbm', 'version': '3'}, {'name': 'lightgbm', 'version': '4'}, {'name': 'onnx', 'version': '1'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:20:10.777741Z [info ] Executing class fixture: mlserver_model_car_inference_service [conftest] 2026-07-07T12:20:10.777911Z [info ] kind: InferenceService api version: serving.kserve.io/v1beta1 [ocp_resources.resource] 2026-07-07T12:20:10.778058Z [info ] Create InferenceService sklearn-modelcar [ocp_resources InferenceService] 2026-07-07T12:20:10.778236Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'name': 'sklearn-modelcar', 'annotations': {'serving.kserve.io/deploymentMode': 'Standard'}, 'namespace': 'sklearn-modelcar'}, 'spec': {'predictor': {'model': {'modelFormat': {'name': 'sklearn'}, 'version': None, 'runtime': 'mlserver-runtime', 'storageUri': 'oci://quay.io/jooholee/mlserver-sklearn@sha256:ec9bc6b520909c52bd1d4accc2b2d28adb04981bd4c3ce94f17f23dd573e1f55'}}}} [ocp_resources InferenceService] 2026-07-07T12:20:10.939537Z [info ] Wait for InferenceService/sklearn-modelcar's 'Ready' condition to be 'True' [ocp_resources InferenceService] 2026-07-07T12:20:10.939697Z [info ] Wait until InferenceService sklearn-modelcar is created [ocp_resources InferenceService] 2026-07-07T12:20:10.939827Z [info ] Waiting for 899.9999868869781 seconds [0:14:59.999987], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:20:10.959601Z [info ] Elapsed time: 0.00010704994201660156 [0:00:00.000107] [timeout_sampler] 2026-07-07T12:20:10.959775Z [info ] Waiting for 899.9797503948212 seconds [0:14:59.979750], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_condition.lambda: self.instance) [timeout_sampler] 2026-07-07T12:20:28.316537Z [info ] Elapsed time: 17.330631494522095 [0:00:17.330631] [timeout_sampler] 2026-07-07T12:20:28.340551Z [info ] Waiting for 882.5986514091492 seconds [0:14:42.598651], retry every 5 seconds. (Function: utilities.inference_utils._is_model_loaded) [timeout_sampler] 2026-07-07T12:20:28.364174Z [info ] Elapsed time: 0.00011467933654785156 [0:00:00.000115] [timeout_sampler] 2026-07-07T12:20:28.392290Z [info ] Executing function fixture: snapshot [conftest] 2026-07-07T12:20:28.392994Z [info ] Executing function fixture: mlserver_response_snapshot [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- PASSED TEST: TestMLServerModelCar.test_mlserver_model_car_inference[sklearn-modelcar-standard] STATUS: PASSED ------------------------------------------------------- TEARDOWN ------------------------------------------------------- 2026-07-07T12:20:28.813073Z [info ] Delete InferenceService sklearn-modelcar [ocp_resources InferenceService] 2026-07-07T12:20:28.867793Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'sklearn', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-07-07T12:20:10Z', 'finalizers': ['inferenceservice.finalizers', 'odh.inferenceservice.finalizers'], 'generation': 1, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/deploymentMode': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:model': {'.': {}, 'f:modelFormat': {'.': {}, 'f:name': {}}, 'f:runtime': {}, 'f:storageUri': {}}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:20:10Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-07-07T12:20:11Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:modelClass': {}}}, 'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {'.': {}, 'f:url': {}}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}, 'f:totalCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-07-07T12:20:27Z'}], 'name': 'sklearn-modelcar', 'namespace': 'sklearn-modelcar', 'resourceVersion': '18733017', 'uid': 'a35b7463-36cd-41fb-9882-32c2e9eb732a'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'model': {'modelFormat': {'name': 'sklearn'}, 'name': '', 'resources': {}, 'runtime': 'mlserver-runtime', 'storageUri': 'oci://quay.io/jooholee/mlserver-sklearn@sha256:ec9bc6b520909c52bd1d4accc2b2d28adb04981bd4c3ce94f17f23dd573e1f55'}}}, 'status': {'address': {'url': 'http://sklearn-modelcar-predictor.sklearn-modelcar.svc.cluster.local:8080'}, 'components': {'predictor': {'url': 'http://sklearn-modelcar-predictor-sklearn-modelcar.example.com'}}, 'conditions': [{'lastTransitionTime': '2026-07-07T12:20:11Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-07-07T12:20:27Z', 'message': 'ReplicaSet "sklearn-modelcar-predictor-85d9fc9c5c" has successfully progressed.', 'reason': 'NewReplicaSetAvailable', 'status': 'True', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-07-07T12:20:27Z', 'status': 'True', 'type': 'Ready'}, {'lastTransitionTime': '2026-07-07T12:20:11Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0, 'totalCopies': 1}, 'states': {'activeModelState': 'Loaded', 'targetModelState': 'Loaded'}, 'transitionStatus': 'UpToDate'}, 'observedGeneration': 1, 'servingRuntimeName': 'mlserver-runtime', 'url': 'http://sklearn-modelcar-predictor.sklearn-modelcar.svc.cluster.local'}} [ocp_resources InferenceService] 2026-07-07T12:20:28.899659Z [info ] Wait until InferenceService sklearn-modelcar is deleted [ocp_resources InferenceService] 2026-07-07T12:20:28.899818Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:20:29.944031Z [info ] Elapsed time: 1.023958683013916 [0:00:01.023959] [timeout_sampler] 2026-07-07T12:20:29.944302Z [info ] Delete ServingRuntime mlserver-runtime [ocp_resources ServingRuntime] 2026-07-07T12:20:29.986306Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': '1.7.1', 'openshift.io/display-name': 'MLServer ServingRuntime for KServe', 'serving.kserve.io/server-type': 'mlserver'}, 'creationTimestamp': '2026-07-07T12:20:10Z', 'generation': 1, 'labels': {'opendatahub.io/dashboard': 'true'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:opendatahub.io/runtime-version': {}, 'f:openshift.io/display-name': {}, 'f:serving.kserve.io/server-type': {}}, 'f:labels': {'.': {}, 'f:opendatahub.io/dashboard': {}}}, 'f:spec': {'.': {}, 'f:annotations': {'.': {}, 'f:monitoring.opendatahub.io/scrape': {}, 'f:opendatahub.io/kserve-runtime': {}, 'f:prometheus.io/path': {}, 'f:prometheus.io/port': {}}, 'f:containers': {}, 'f:multiModel': {}, 'f:protocolVersions': {}, 'f:supportedModelFormats': {}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:20:10Z'}], 'name': 'mlserver-runtime', 'namespace': 'sklearn-modelcar', 'resourceVersion': '18732636', 'uid': '5c1f6ccb-78c4-492a-9bcc-48c47cfbab05'}, 'spec': {'annotations': {'monitoring.opendatahub.io/scrape': 'true', 'opendatahub.io/kserve-runtime': 'mlserver', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8082'}, 'containers': [{'env': [{'name': 'MLSERVER_MODEL_IMPLEMENTATION', 'value': '{{.Labels.modelClass}}'}, {'name': 'MLSERVER_HTTP_PORT', 'value': '8080'}, {'name': 'MLSERVER_MODELS_DIR', 'value': '/mnt/models'}], 'image': 'registry.redhat.io/rhoai/odh-mlserver-rhel9@sha256:ec5a786c5a01e83e3ccbadc2a6ccb8c38485baf6296bb6285baaef06c71aaba1', 'livenessProbe': {'failureThreshold': 6, 'httpGet': {'path': '/v2/models/{{.Name}}/ready', 'port': 8080}, 'initialDelaySeconds': 20, 'periodSeconds': 10, 'timeoutSeconds': 5}, 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}], 'readinessProbe': {'failureThreshold': 3, 'httpGet': {'path': '/v2/models/{{.Name}}/ready', 'port': 8080}, 'initialDelaySeconds': 5, 'periodSeconds': 5, 'timeoutSeconds': 5}, 'securityContext': {'allowPrivilegeEscalation': False, 'capabilities': {'drop': ['ALL']}, 'privileged': False, 'runAsNonRoot': True}, 'startupProbe': {'exec': {'command': ['/bin/sh', '-c', '[ -n "$(ls -A /mnt/models 2>/dev/null)" ]\n']}, 'failureThreshold': 1, 'initialDelaySeconds': 1, 'periodSeconds': 1}}], 'multiModel': False, 'protocolVersions': ['v2'], 'supportedModelFormats': [{'name': 'sklearn', 'version': '0'}, {'name': 'sklearn', 'version': '1'}, {'name': 'xgboost', 'version': '1'}, {'name': 'xgboost', 'version': '2'}, {'name': 'lightgbm', 'version': '3'}, {'name': 'lightgbm', 'version': '4'}, {'name': 'onnx', 'version': '1'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:20:30.008012Z [info ] Wait until ServingRuntime mlserver-runtime is deleted [ocp_resources ServingRuntime] 2026-07-07T12:20:30.008168Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:20:30.027472Z [info ] Elapsed time: 4.76837158203125e-05 [0:00:00.000048] [timeout_sampler] 2026-07-07T12:20:30.099717Z [info ] Delete Namespace sklearn-modelcar [ocp_resources Namespace] 2026-07-07T12:20:30.137932Z [info ] Deleting {'kind': 'Namespace', 'apiVersion': 'v1', 'metadata': {'name': 'sklearn-modelcar', 'uid': '671e34e1-2f49-4db2-90d7-d0b5575b9f46', 'resourceVersion': '18732610', 'creationTimestamp': '2026-07-07T12:20:10Z', 'labels': {'kubernetes.io/metadata.name': 'sklearn-modelcar', 'pod-security.kubernetes.io/audit': 'restricted', 'pod-security.kubernetes.io/audit-version': 'latest', 'pod-security.kubernetes.io/warn': 'restricted', 'pod-security.kubernetes.io/warn-version': 'latest'}, 'annotations': {'openshift.io/sa.scc.mcs': 's0:c30,c25', 'openshift.io/sa.scc.supplemental-groups': '1000920000/10000', 'openshift.io/sa.scc.uid-range': '1000920000/10000', 'security.openshift.io/MinimallySufficientPodSecurityStandard': 'restricted'}, 'managedFields': [{'manager': 'cluster-policy-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:10Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:openshift.io/sa.scc.mcs': {}, 'f:openshift.io/sa.scc.supplemental-groups': {}, 'f:openshift.io/sa.scc.uid-range': {}}}}}, {'manager': 'pod-security-admission-label-synchronization-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:10Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:security.openshift.io/MinimallySufficientPodSecurityStandard': {}}, 'f:labels': {'f:pod-security.kubernetes.io/audit': {}, 'f:pod-security.kubernetes.io/audit-version': {}, 'f:pod-security.kubernetes.io/warn': {}, 'f:pod-security.kubernetes.io/warn-version': {}}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:10Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:kubernetes.io/metadata.name': {}}}}}]}, 'spec': {'finalizers': ['kubernetes']}, 'status': {'phase': 'Active'}} [ocp_resources Namespace] 2026-07-07T12:20:30.168011Z [info ] Wait until Namespace sklearn-modelcar is deleted [ocp_resources Namespace] 2026-07-07T12:20:30.168159Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] _ 1 of 9 completed, 1 Pass, 0 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/openvino/test_ovms_model_deployment.py::TestOpenVINOModels::test_openvino_model_inference[onnx-standard-rest-deployment] 2026-07-07T12:20:39.388546Z [info ] Elapsed time: 9.199280261993408 [0:00:09.199280] [timeout_sampler]  ----------------------------- test_openvino_model_inference[onnx-standard-rest-deployment] ----------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:20:39.390548Z [info ] Executing session fixture: aws_access_key_id [conftest] 2026-07-07T12:20:39.390688Z [info ] Executing session fixture: aws_secret_access_key [conftest] 2026-07-07T12:20:39.390844Z [info ] Executing session fixture: ci_s3_bucket_endpoint [conftest] 2026-07-07T12:20:39.390974Z [info ] Executing session fixture: valid_aws_config [conftest] 2026-07-07T12:20:39.434382Z [info ] AWS credentials validated successfully via STS GetCallerIdentity [tests.conftest] name=tests.conftest 2026-07-07T12:20:39.436923Z [info ] Executing session fixture: models_s3_bucket_name [conftest] 2026-07-07T12:20:39.437053Z [info ] Executing session fixture: s3_models_storage_uri [conftest] 2026-07-07T12:20:39.437160Z [info ] Executing session fixture: models_s3_bucket_region [conftest] 2026-07-07T12:20:39.437298Z [info ] Executing session fixture: models_s3_bucket_endpoint [conftest] 2026-07-07T12:20:39.437405Z [info ] Executing session fixture: gpu_count_on_cluster [conftest] 2026-07-07T12:20:39.512807Z [info ] Executing class fixture: model_namespace [conftest] 2026-07-07T12:20:39.512967Z [info ] Create Namespace onnx-standard-rest [ocp_resources Namespace] 2026-07-07T12:20:39.513079Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Namespace', 'metadata': {'name': 'onnx-standard-rest'}, 'spec': {}} [ocp_resources Namespace] 2026-07-07T12:20:39.571496Z [info ] Wait for Namespace onnx-standard-rest status to be Active [ocp_resources Namespace] 2026-07-07T12:20:39.571676Z [info ] Waiting for 120 seconds [0:02:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:20:39.605753Z [info ] Status of Namespace onnx-standard-rest is Active [ocp_resources Namespace] 2026-07-07T12:20:39.605911Z [info ] Elapsed time: 6.151199340820312e-05 [0:00:00.000062] [timeout_sampler] 2026-07-07T12:20:39.606022Z [info ] Executing class fixture: openvino_serving_runtime [conftest] 2026-07-07T12:20:39.606124Z [info ] kind: Template api version: template.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:20:39.698689Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:20:39.698929Z [info ] Create ServingRuntime openvino-runtime [ocp_resources ServingRuntime] 2026-07-07T12:20:39.699119Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/recommended-accelerators': '["nvidia.com/gpu"]', 'opendatahub.io/runtime-version': 'v2026.1.0', 'openshift.io/display-name': 'OpenVINO Model Server'}, 'labels': {'opendatahub.io/dashboard': 'true'}, 'name': 'openvino-runtime', 'namespace': 'onnx-standard-rest'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'ovms', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8888'}, 'containers': [{'args': ['--model_name={{.Name}}', '--port=8001', '--rest_port=8888', '--model_path=/mnt/models', '--file_system_poll_wait_seconds=0', '--metrics_enable'], 'image': 'registry.redhat.io/rhoai/odh-openvino-model-server-rhel9@sha256:8456a5e15035b06449619cd95ce0c73c3b24389723ed46524c06b6d87c988697', 'name': 'kserve-container', 'ports': [{'containerPort': 8888, 'protocol': 'TCP'}]}], 'multiModel': False, 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'autoSelect': True, 'name': 'openvino_ir', 'version': 'opset13'}, {'name': 'onnx', 'version': '1'}, {'autoSelect': True, 'name': 'tensorflow', 'version': '1'}, {'autoSelect': True, 'name': 'tensorflow', 'version': '2'}, {'autoSelect': True, 'name': 'paddle', 'version': '2'}, {'autoSelect': True, 'name': 'pytorch', 'version': '2'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:20:39.754522Z [info ] Executing class fixture: kserve_s3_secret [conftest] 2026-07-07T12:20:39.754707Z [info ] Create Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:20:39.754892Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Secret', 'metadata': {'name': 'models-bucket-secret', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-verifyssl': '0', 'serving.kserve.io/s3-usehttps': '1'}, 'namespace': 'onnx-standard-rest'}, 'stringData': '*******'} [ocp_resources Secret] 2026-07-07T12:20:39.811765Z [info ] Wait until Secret models-bucket-secret is created [ocp_resources Secret] 2026-07-07T12:20:39.812024Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:20:39.835551Z [info ] Elapsed time: 9.632110595703125e-05 [0:00:00.000096] [timeout_sampler] 2026-07-07T12:20:39.835943Z [info ] Executing class fixture: openvino_model_service_account [conftest] 2026-07-07T12:20:39.836061Z [info ] Create ServiceAccount openvino-models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:20:39.836178Z [info ] Posting {'apiVersion': 'v1', 'kind': 'ServiceAccount', 'metadata': {'name': 'openvino-models-bucket-sa', 'namespace': 'onnx-standard-rest'}, 'secrets': [{'name': 'models-bucket-secret'}]} [ocp_resources ServiceAccount] 2026-07-07T12:20:39.877601Z [info ] Executing class fixture: openvino_inference_service [conftest] 2026-07-07T12:20:39.897553Z [info ] kind: InferenceService api version: serving.kserve.io/v1beta1 [ocp_resources.resource] 2026-07-07T12:20:39.897948Z [info ] Create InferenceService onnx  [ocp_resources InferenceService] 2026-07-07T12:20:39.898080Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'name': 'onnx', 'annotations': {'serving.kserve.io/deploymentMode': 'Standard'}, 'namespace': 'onnx-standard-rest'}, 'spec': {'predictor': {'model': {'modelFormat': {'name': 'openvino_ir'}, 'version': None, 'runtime': 'openvino-runtime', 'storageUri': 's3://ods-ci-wisdom/openvino/model_repository/onnx/', 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '2', 'memory': '4Gi'}}}, 'minReplicas': 1, 'serviceAccountName': 'openvino-models-bucket-sa'}}} [ocp_resources InferenceService] 2026-07-07T12:20:39.971589Z [info ] Waiting for 30 seconds [0:00:30], retry every 1 seconds. (Function: utilities.infra.wait_for_isvc_pods Kwargs: {'client': , 'isvc': , 'runtime_name': 'openvino-runtime'}) [timeout_sampler] 2026-07-07T12:20:39.970983Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:20:41.013486Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:20:41.067657Z [info ] Elapsed time: 1.0425748825073242 [0:00:01.042575] [timeout_sampler] 2026-07-07T12:20:41.086118Z [info ] Verifying no failed pods  [utilities.infra] name=utilities.infra 2026-07-07T12:20:41.086848Z [info ] Waiting for 899.9999978542328 seconds [0:14:59.999998], retry every 10 seconds. (Function: utilities.infra.get_pods_by_isvc_label Kwargs: {'client': , 'isvc': , 'runtime_name': 'openvino-runtime'}) [timeout_sampler] 2026-07-07T12:21:01.381799Z [info ] Elapsed time: 20.200564861297607 [0:00:20.200565] [timeout_sampler] 2026-07-07T12:21:01.400263Z [info ] Waiting for 878.5711627006531 seconds [0:14:38.571163], retry every 5 seconds. (Function: ocp_resources.resource.get Kwargs: {'label_selector': 'serving.kserve.io/inferenceservice=onnx', 'client': , 'namespace': 'onnx-standard-rest'}) [timeout_sampler] 2026-07-07T12:21:01.400400Z [info ] kind: Deployment api version: apps/v1 [ocp_resources.resource] 2026-07-07T12:21:01.420667Z [info ] Elapsed time: 5.9604644775390625e-05 [0:00:00.000060] [timeout_sampler] 2026-07-07T12:21:01.420234Z [info ] Waiting for inference deployment replicas to complete [utilities.infra] name=utilities.infra 2026-07-07T12:21:01.476428Z [info ] Waiting for 878.4949798583984 seconds [0:14:38.494980], retry every 5 seconds. (Function: utilities.infra..lambda: deployment.instance) [timeout_sampler] 2026-07-07T12:21:01.495403Z [info ] Elapsed time: 8.440017700195312e-05 [0:00:00.000084] [timeout_sampler] 2026-07-07T12:21:01.495557Z [info ] Wait for Deployment onnx-predictor to be deployed: True [ocp_resources Deployment] 2026-07-07T12:21:01.495696Z [info ] Waiting for 878.4760303497314 seconds [0:14:38.476030], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:01.513477Z [info ] Elapsed time: 4.363059997558594e-05 [0:00:00.000044] [timeout_sampler] 2026-07-07T12:21:01.513629Z [info ] Waiting for 878.4577839374542 seconds [0:14:38.457784], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.instance) [timeout_sampler] 2026-07-07T12:21:01.532857Z [info ] Elapsed time: 2.9802322387695312e-05 [0:00:00.000030] [timeout_sampler] 2026-07-07T12:21:01.533001Z [info ] Wait for InferenceService/onnx's 'Ready' condition to be 'True' [ocp_resources InferenceService] 2026-07-07T12:21:01.533137Z [info ] Wait until InferenceService onnx is created [ocp_resources InferenceService] 2026-07-07T12:21:01.533309Z [info ] Waiting for 878.4383735656738 seconds [0:14:38.438374], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:01.552281Z [info ] Elapsed time: 2.765655517578125e-05 [0:00:00.000028] [timeout_sampler] 2026-07-07T12:21:01.552497Z [info ] Waiting for 878.4190309047699 seconds [0:14:38.419031], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_condition.lambda: self.instance) [timeout_sampler] 2026-07-07T12:21:01.570603Z [info ] Elapsed time: 2.9325485229492188e-05 [0:00:00.000029] [timeout_sampler] 2026-07-07T12:21:01.589219Z [info ] Waiting for 878.3820791244507 seconds [0:14:38.382079], retry every 5 seconds. (Function: utilities.inference_utils._is_model_loaded) [timeout_sampler] 2026-07-07T12:21:01.608293Z [info ] Elapsed time: 4.410743713378906e-05 [0:00:00.000044] [timeout_sampler] 2026-07-07T12:21:01.627385Z [info ] Executing class fixture: protocol [conftest] 2026-07-07T12:21:01.627548Z [info ] Executing function fixture: openvino_pod_resource [conftest] 2026-07-07T12:21:01.665816Z [info ] Executing function fixture: snapshot [conftest] 2026-07-07T12:21:01.666504Z [info ] Executing function fixture: openvino_response_snapshot [conftest] 2026-07-07T12:21:01.667355Z [info ] Executing function fixture: model_format [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- PASSED TEST: TestOpenVINOModels.test_openvino_model_inference[onnx-standard-rest-deployment] STATUS: PASSED ------------------------------------------------------- TEARDOWN ------------------------------------------------------- 2026-07-07T12:21:01.938093Z [info ] Delete InferenceService onnx  [ocp_resources InferenceService] 2026-07-07T12:21:01.980627Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'openvino_ir', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-07-07T12:20:39Z', 'finalizers': ['inferenceservice.finalizers', 'odh.inferenceservice.finalizers'], 'generation': 1, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/deploymentMode': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:minReplicas': {}, 'f:model': {'.': {}, 'f:modelFormat': {'.': {}, 'f:name': {}}, 'f:resources': {'.': {}, 'f:limits': {'.': {}, 'f:cpu': {}, 'f:memory': {}}, 'f:requests': {'.': {}, 'f:cpu': {}, 'f:memory': {}}}, 'f:runtime': {}, 'f:storageUri': {}}, 'f:serviceAccountName': {}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:20:39Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-07-07T12:20:40Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {'.': {}, 'f:url': {}}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}, 'f:totalCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-07-07T12:20:51Z'}], 'name': 'onnx', 'namespace': 'onnx-standard-rest', 'resourceVersion': '18733642', 'uid': '48f0e5e9-5789-4588-b00f-762f26dbc34d'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'minReplicas': 1, 'model': {'modelFormat': {'name': 'openvino_ir'}, 'name': '', 'resources': {'limits': {'cpu': '2', 'memory': '4Gi'}, 'requests': {'cpu': '1', 'memory': '2Gi'}}, 'runtime': 'openvino-runtime', 'storageUri': 's3://ods-ci-wisdom/openvino/model_repository/onnx/'}, 'serviceAccountName': 'openvino-models-bucket-sa'}}, 'status': {'address': {'url': 'http://onnx-predictor.onnx-standard-rest.svc.cluster.local:8080'}, 'components': {'predictor': {'url': 'http://onnx-predictor-onnx-standard-rest.example.com'}}, 'conditions': [{'lastTransitionTime': '2026-07-07T12:20:40Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-07-07T12:20:51Z', 'message': 'ReplicaSet "onnx-predictor-8557d44fc8" has successfully progressed.', 'reason': 'NewReplicaSetAvailable', 'status': 'True', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-07-07T12:20:51Z', 'status': 'True', 'type': 'Ready'}, {'lastTransitionTime': '2026-07-07T12:20:40Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0, 'totalCopies': 1}, 'states': {'activeModelState': 'Loaded', 'targetModelState': 'Loaded'}, 'transitionStatus': 'UpToDate'}, 'observedGeneration': 1, 'servingRuntimeName': 'openvino-runtime', 'url': 'http://onnx-predictor.onnx-standard-rest.svc.cluster.local'}} [ocp_resources InferenceService] 2026-07-07T12:21:02.006377Z [info ] Wait until InferenceService onnx is deleted [ocp_resources InferenceService] 2026-07-07T12:21:02.006556Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:03.045805Z [info ] Elapsed time: 1.0196561813354492 [0:00:01.019656] [timeout_sampler] 2026-07-07T12:21:03.046042Z [info ] Delete ServingRuntime openvino-runtime [ocp_resources ServingRuntime] 2026-07-07T12:21:03.085011Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/recommended-accelerators': '["nvidia.com/gpu"]', 'opendatahub.io/runtime-version': 'v2026.1.0', 'openshift.io/display-name': 'OpenVINO Model Server'}, 'creationTimestamp': '2026-07-07T12:20:39Z', 'generation': 1, 'labels': {'opendatahub.io/dashboard': 'true'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:opendatahub.io/recommended-accelerators': {}, 'f:opendatahub.io/runtime-version': {}, 'f:openshift.io/display-name': {}}, 'f:labels': {'.': {}, 'f:opendatahub.io/dashboard': {}}}, 'f:spec': {'.': {}, 'f:annotations': {'.': {}, 'f:opendatahub.io/kserve-runtime': {}, 'f:prometheus.io/path': {}, 'f:prometheus.io/port': {}}, 'f:containers': {}, 'f:multiModel': {}, 'f:protocolVersions': {}, 'f:supportedModelFormats': {}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:20:39Z'}], 'name': 'openvino-runtime', 'namespace': 'onnx-standard-rest', 'resourceVersion': '18733350', 'uid': '7630a224-6f8f-4cc1-8c40-825d93c59e4f'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'ovms', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8888'}, 'containers': [{'args': ['--model_name={{.Name}}', '--port=8001', '--rest_port=8888', '--model_path=/mnt/models', '--file_system_poll_wait_seconds=0', '--metrics_enable'], 'image': 'registry.redhat.io/rhoai/odh-openvino-model-server-rhel9@sha256:8456a5e15035b06449619cd95ce0c73c3b24389723ed46524c06b6d87c988697', 'name': 'kserve-container', 'ports': [{'containerPort': 8888, 'protocol': 'TCP'}]}], 'multiModel': False, 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'autoSelect': True, 'name': 'openvino_ir', 'version': 'opset13'}, {'name': 'onnx', 'version': '1'}, {'autoSelect': True, 'name': 'tensorflow', 'version': '1'}, {'autoSelect': True, 'name': 'tensorflow', 'version': '2'}, {'autoSelect': True, 'name': 'paddle', 'version': '2'}, {'autoSelect': True, 'name': 'pytorch', 'version': '2'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:21:03.107215Z [info ] Wait until ServingRuntime openvino-runtime is deleted [ocp_resources ServingRuntime] 2026-07-07T12:21:03.107475Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:03.127087Z [info ] Elapsed time: 4.076957702636719e-05 [0:00:00.000041] [timeout_sampler] 2026-07-07T12:21:03.127343Z [info ] Delete ServiceAccount openvino-models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:21:03.168219Z [info ] Deleting {'kind': 'ServiceAccount', 'apiVersion': 'v1', 'metadata': {'name': 'openvino-models-bucket-sa', 'namespace': 'onnx-standard-rest', 'uid': '75f91aa2-9191-4208-8f1c-cc7af95c2aeb', 'resourceVersion': '18733366', 'creationTimestamp': '2026-07-07T12:20:39Z', 'annotations': {'openshift.io/internal-registry-pull-secret-ref': 'openvino-models-bucket-sa-dockercfg-c5hn7'}, 'managedFields': [{'manager': 'openshift.io/image-registry-pull-secrets_service-account-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:39Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:imagePullSecrets': {}, 'f:metadata': {'f:annotations': {'f:openshift.io/internal-registry-pull-secret-ref': {}}}, 'f:secrets': {'k:{"name":"openvino-models-bucket-sa-dockercfg-c5hn7"}': {}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:39Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:secrets': {'.': {}, 'k:{"name":"models-bucket-secret"}': {}}}}]}, 'secrets': [{'name': 'models-bucket-secret'}, {'name': 'openvino-models-bucket-sa-dockercfg-c5hn7'}], 'imagePullSecrets': [{'name': 'openvino-models-bucket-sa-dockercfg-c5hn7'}]} [ocp_resources ServiceAccount] 2026-07-07T12:21:03.191481Z [info ] Wait until ServiceAccount openvino-models-bucket-sa is deleted [ocp_resources ServiceAccount] 2026-07-07T12:21:03.192002Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:03.215021Z [info ] Elapsed time: 3.600120544433594e-05 [0:00:00.000036] [timeout_sampler] 2026-07-07T12:21:03.215259Z [info ] Delete Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:21:03.256985Z [info ] Deleting {'kind': 'Secret', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-secret', 'namespace': 'onnx-standard-rest', 'uid': '3043abeb-4143-4906-a749-dc0dd917f6fb', 'resourceVersion': '18733356', 'creationTimestamp': '2026-07-07T12:20:39Z', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-usehttps': '1', 'serving.kserve.io/s3-verifyssl': '0'}, 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:39Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:data': {'.': {}, 'f:AWS_ACCESS_KEY_ID': {}, 'f:AWS_SECRET_ACCESS_KEY': {}}, 'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/s3-endpoint': {}, 'f:serving.kserve.io/s3-region': {}, 'f:serving.kserve.io/s3-useanoncredential': {}, 'f:serving.kserve.io/s3-usehttps': {}, 'f:serving.kserve.io/s3-verifyssl': {}}}, 'f:type': {}}}]}, 'data': '*******', 'type': 'Opaque'} [ocp_resources Secret] 2026-07-07T12:21:03.283329Z [info ] Wait until Secret models-bucket-secret is deleted [ocp_resources Secret] 2026-07-07T12:21:03.283478Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:03.302879Z [info ] Elapsed time: 3.1948089599609375e-05 [0:00:00.000032] [timeout_sampler] 2026-07-07T12:21:03.322072Z [info ] Delete Namespace onnx-standard-rest [ocp_resources Namespace] 2026-07-07T12:21:03.363468Z [info ] Deleting {'kind': 'Namespace', 'apiVersion': 'v1', 'metadata': {'name': 'onnx-standard-rest', 'uid': 'e574c547-f30b-42a6-a294-a967e07c0b6c', 'resourceVersion': '18733333', 'creationTimestamp': '2026-07-07T12:20:39Z', 'labels': {'kubernetes.io/metadata.name': 'onnx-standard-rest', 'pod-security.kubernetes.io/audit': 'restricted', 'pod-security.kubernetes.io/audit-version': 'latest', 'pod-security.kubernetes.io/warn': 'restricted', 'pod-security.kubernetes.io/warn-version': 'latest'}, 'annotations': {'openshift.io/sa.scc.mcs': 's0:c31,c0', 'openshift.io/sa.scc.supplemental-groups': '1000930000/10000', 'openshift.io/sa.scc.uid-range': '1000930000/10000', 'security.openshift.io/MinimallySufficientPodSecurityStandard': 'restricted'}, 'managedFields': [{'manager': 'cluster-policy-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:39Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:openshift.io/sa.scc.mcs': {}, 'f:openshift.io/sa.scc.supplemental-groups': {}, 'f:openshift.io/sa.scc.uid-range': {}}}}}, {'manager': 'pod-security-admission-label-synchronization-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:39Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:security.openshift.io/MinimallySufficientPodSecurityStandard': {}}, 'f:labels': {'f:pod-security.kubernetes.io/audit': {}, 'f:pod-security.kubernetes.io/audit-version': {}, 'f:pod-security.kubernetes.io/warn': {}, 'f:pod-security.kubernetes.io/warn-version': {}}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:20:39Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:kubernetes.io/metadata.name': {}}}}}]}, 'spec': {'finalizers': ['kubernetes']}, 'status': {'phase': 'Active'}} [ocp_resources Namespace] 2026-07-07T12:21:03.391328Z [info ] Wait until Namespace onnx-standard-rest is deleted [ocp_resources Namespace] 2026-07-07T12:21:03.391503Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] _ 2 of 9 completed, 2 Pass, 0 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/openvino/test_ovms_smoke.py::TestOVMSSmokeInOpenShift::test_ovms_smoke_runs_in_openshift[ovms-smoke] 2026-07-07T12:21:12.587881Z [info ] Elapsed time: 9.174283981323242 [0:00:09.174284] [timeout_sampler]  ------------------------------------ test_ovms_smoke_runs_in_openshift[ovms-smoke] ------------------------------------ -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:21:12.588488Z [info ] Executing session fixture: ovms_runtime_image [conftest] 2026-07-07T12:21:12.588600Z [info ] kind: Template api version: template.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:21:12.631437Z [info ] Executing class fixture: model_namespace [conftest] 2026-07-07T12:21:12.631613Z [info ] Create Namespace ovms-smoke  [ocp_resources Namespace] 2026-07-07T12:21:12.631763Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Namespace', 'metadata': {'name': 'ovms-smoke'}, 'spec': {}} [ocp_resources Namespace] 2026-07-07T12:21:12.683263Z [info ] Wait for Namespace ovms-smoke status to be Active [ocp_resources Namespace] 2026-07-07T12:21:12.683421Z [info ] Waiting for 120 seconds [0:02:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:12.708027Z [info ] Status of Namespace ovms-smoke is Active [ocp_resources Namespace] 2026-07-07T12:21:12.708208Z [info ] Elapsed time: 6.508827209472656e-05 [0:00:00.000065] [timeout_sampler] 2026-07-07T12:21:12.708336Z [info ] Executing class fixture: ovms_smoke_scripts_configmap [conftest] 2026-07-07T12:21:12.710019Z [info ] Create ConfigMap ovms-smoke-scripts [ocp_resources ConfigMap] 2026-07-07T12:21:12.710204Z [info ] Posting {'apiVersion': 'v1', 'kind': 'ConfigMap', 'metadata': {'name': 'ovms-smoke-scripts', 'namespace': 'ovms-smoke'}, 'data': '*******'} [ocp_resources ConfigMap] 2026-07-07T12:21:12.774521Z [info ] Executing class fixture: ovms_smoke_pod [conftest] 2026-07-07T12:21:12.774707Z [info ] Create Pod ovms-smoke-pod  [ocp_resources Pod] 2026-07-07T12:21:12.774854Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Pod', 'metadata': {'name': 'ovms-smoke-pod', 'namespace': 'ovms-smoke'}, 'spec': {'containers': [{'name': 'ovms-smoke', 'image': 'registry.redhat.io/rhoai/odh-openvino-model-server-rhel9@sha256:8456a5e15035b06449619cd95ce0c73c3b24389723ed46524c06b6d87c988697', 'command': ['/bin/sh', '-c'], 'args': ['python3 /scripts/ovms_smoketest.py && python3 /scripts/smoke.py'], 'env': [{'name': 'HOME', 'value': '/tmp'}, {'name': 'HF_HOME', 'value': '/tmp/hf_cache'}, {'name': 'MPLCONFIGDIR', 'value': '/tmp/matplotlib'}], 'volumeMounts': [{'name': 'smoke-scripts', 'mountPath': '/scripts', 'readOnly': True}], 'securityContext': {'allowPrivilegeEscalation': False, 'capabilities': {'drop': ['ALL']}, 'runAsNonRoot': True, 'seccompProfile': {'type': 'RuntimeDefault'}}}], 'restartPolicy': 'Never', 'volumes': [{'name': 'smoke-scripts', 'configMap': {'name': 'ovms-smoke-scripts'}}]}} [ocp_resources Pod] 2026-07-07T12:21:12.908423Z [info ] Waiting for OVMS smoke Pod to complete [tests.model_serving.model_runtime.openvino.conftest] name=tests.model_serving.model_runtime.openvino.conftest 2026-07-07T12:21:12.909386Z [info ] Wait for Pod ovms-smoke-pod status to be Succeeded [ocp_resources Pod] 2026-07-07T12:21:12.909505Z [info ] Waiting for 300 seconds [0:05:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:12.932165Z [info ] Status of Pod ovms-smoke-pod is Pending [ocp_resources Pod] 2026-07-07T12:21:13.961369Z [info ] Status of Pod ovms-smoke-pod is Running [ocp_resources Pod] 2026-07-07T12:21:43.561233Z [info ] Status of Pod ovms-smoke-pod is Succeeded [ocp_resources Pod] 2026-07-07T12:21:43.561438Z [info ] Elapsed time: 30.630895137786865 [0:00:30.630895] [timeout_sampler] --------------------------------------------------------- CALL --------------------------------------------------------- PASSED TEST: TestOVMSSmokeInOpenShift.test_ovms_smoke_runs_in_openshift[ovms-smoke] STATUS: PASSED ------------------------------------------------------- TEARDOWN ------------------------------------------------------- 2026-07-07T12:21:43.580071Z [info ] Delete Pod ovms-smoke-pod  [ocp_resources Pod] 2026-07-07T12:21:43.627218Z [info ] Deleting {'kind': 'Pod', 'apiVersion': 'v1', 'metadata': {'name': 'ovms-smoke-pod', 'namespace': 'ovms-smoke', 'uid': '08ab70f1-ec6a-4693-84e0-2d28a140f4b6', 'resourceVersion': '18734649', 'generation': 1, 'creationTimestamp': '2026-07-07T12:21:12Z', 'labels': {'kyverno-add-imagepullsecret': 'was-here', 'kyverno-replace-image-registry': 'was-here'}, 'annotations': {'k8s.ovn.org/pod-networks': '{"default":{"ip_addresses":["10.128.1.131/23"],"mac_address":"0a:58:0a:80:01:83","gateway_ips":["10.128.0.1"],"routes":[{"dest":"10.128.0.0/14","nextHop":"10.128.0.1"},{"dest":"172.30.0.0/16","nextHop":"10.128.0.1"},{"dest":"169.254.0.5/32","nextHop":"10.128.0.1"},{"dest":"100.64.0.0/16","nextHop":"10.128.0.1"}],"ip_address":"10.128.1.131/23","gateway_ip":"10.128.0.1","role":"primary"}}', 'k8s.v1.cni.cncf.io/network-status': '[{\n "name": "ovn-kubernetes",\n "interface": "eth0",\n "ips": [\n "10.128.1.131"\n ],\n "mac": "0a:58:0a:80:01:83",\n "default": true,\n "dns": {}\n}]', 'openshift.io/scc': 'openshift-ai-llminferenceservice-multi-node-scc', 'seccomp.security.alpha.kubernetes.io/pod': 'runtime/default', 'security.openshift.io/validated-scc-subject-type': 'user'}, 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:12Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:spec': {'f:containers': {'k:{"name":"ovms-smoke"}': {'.': {}, 'f:args': {}, 'f:command': {}, 'f:env': {'.': {}, 'k:{"name":"HF_HOME"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"HOME"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"MPLCONFIGDIR"}': {'.': {}, 'f:name': {}, 'f:value': {}}}, 'f:image': {}, 'f:imagePullPolicy': {}, 'f:name': {}, 'f:resources': {}, 'f:securityContext': {'.': {}, 'f:allowPrivilegeEscalation': {}, 'f:capabilities': {'.': {}, 'f:drop': {}}, 'f:runAsNonRoot': {}, 'f:seccompProfile': {'.': {}, 'f:type': {}}}, 'f:terminationMessagePath': {}, 'f:terminationMessagePolicy': {}, 'f:volumeMounts': {'.': {}, 'k:{"mountPath":"/scripts"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}, 'f:readOnly': {}}}}}, 'f:dnsPolicy': {}, 'f:enableServiceLinks': {}, 'f:restartPolicy': {}, 'f:schedulerName': {}, 'f:securityContext': {}, 'f:terminationGracePeriodSeconds': {}, 'f:volumes': {'.': {}, 'k:{"name":"smoke-scripts"}': {'.': {}, 'f:configMap': {'.': {}, 'f:defaultMode': {}, 'f:name': {}}, 'f:name': {}}}}}}, {'manager': 'ip-10-0-1-76', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:12Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:k8s.ovn.org/pod-networks': {}}}}, 'subresource': 'status'}, {'manager': 'multus-daemon', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:13Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:k8s.v1.cni.cncf.io/network-status': {}}}}, 'subresource': 'status'}, {'manager': 'kubelet', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:43Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'f:conditions': {'k:{"type":"ContainersReady"}': {'.': {}, 'f:lastProbeTime': {}, 'f:lastTransitionTime': {}, 'f:observedGeneration': {}, 'f:reason': {}, 'f:status': {}, 'f:type': {}}, 'k:{"type":"Initialized"}': {'.': {}, 'f:lastProbeTime': {}, 'f:lastTransitionTime': {}, 'f:observedGeneration': {}, 'f:reason': {}, 'f:status': {}, 'f:type': {}}, 'k:{"type":"PodReadyToStartContainers"}': {'.': {}, 'f:lastProbeTime': {}, 'f:lastTransitionTime': {}, 'f:observedGeneration': {}, 'f:status': {}, 'f:type': {}}, 'k:{"type":"PodScheduled"}': {'f:observedGeneration': {}}, 'k:{"type":"Ready"}': {'.': {}, 'f:lastProbeTime': {}, 'f:lastTransitionTime': {}, 'f:observedGeneration': {}, 'f:reason': {}, 'f:status': {}, 'f:type': {}}}, 'f:containerStatuses': {}, 'f:hostIP': {}, 'f:hostIPs': {}, 'f:observedGeneration': {}, 'f:phase': {}, 'f:podIP': {}, 'f:podIPs': {'.': {}, 'k:{"ip":"10.128.1.131"}': {'.': {}, 'f:ip': {}}}, 'f:startTime': {}}}, 'subresource': 'status'}]}, 'spec': {'volumes': [{'name': 'smoke-scripts', 'configMap': {'name': 'ovms-smoke-scripts', 'defaultMode': 420}}, {'name': 'kube-api-access-7nhj9', 'projected': {'sources': [{'serviceAccountToken': {'expirationSeconds': 3607, 'path': 'token'}}, {'configMap': {'name': 'kube-root-ca.crt', 'items': [{'key': 'ca.crt', 'path': 'ca.crt'}]}}, {'downwardAPI': {'items': [{'path': 'namespace', 'fieldRef': {'apiVersion': 'v1', 'fieldPath': 'metadata.namespace'}}]}}, {'configMap': {'name': 'openshift-service-ca.crt', 'items': [{'key': 'service-ca.crt', 'path': 'service-ca.crt'}]}}], 'defaultMode': 420}}], 'containers': [{'name': 'ovms-smoke', 'image': 'quay.io/rhoai/odh-openvino-model-server-rhel9@sha256:8456a5e15035b06449619cd95ce0c73c3b24389723ed46524c06b6d87c988697', 'command': ['/bin/sh', '-c'], 'args': ['python3 /scripts/ovms_smoketest.py && python3 /scripts/smoke.py'], 'env': [{'name': 'HOME', 'value': '/tmp'}, {'name': 'HF_HOME', 'value': '/tmp/hf_cache'}, {'name': 'MPLCONFIGDIR', 'value': '/tmp/matplotlib'}], 'resources': {}, 'volumeMounts': [{'name': 'smoke-scripts', 'readOnly': True, 'mountPath': '/scripts'}, {'name': 'kube-api-access-7nhj9', 'readOnly': True, 'mountPath': '/var/run/secrets/kubernetes.io/serviceaccount'}], 'terminationMessagePath': '/dev/termination-log', 'terminationMessagePolicy': 'File', 'imagePullPolicy': 'IfNotPresent', 'securityContext': {'capabilities': {'drop': ['ALL']}, 'runAsUser': 1000990000, 'runAsNonRoot': True, 'allowPrivilegeEscalation': False, 'seccompProfile': {'type': 'RuntimeDefault'}}}], 'restartPolicy': 'Never', 'terminationGracePeriodSeconds': 30, 'dnsPolicy': 'ClusterFirst', 'serviceAccountName': 'default', 'serviceAccount': 'default', 'nodeName': 'ip-10-0-1-76.us-east-2.compute.internal', 'securityContext': {'seLinuxOptions': {'level': 's0:c31,c30'}, 'seccompProfile': {'type': 'RuntimeDefault'}}, 'imagePullSecrets': [{'name': 'default-dockercfg-8v726'}, {'name': 'pull-secret-quay'}], 'schedulerName': 'default-scheduler', 'tolerations': [{'key': 'node.kubernetes.io/not-ready', 'operator': 'Exists', 'effect': 'NoExecute', 'tolerationSeconds': 300}, {'key': 'node.kubernetes.io/unreachable', 'operator': 'Exists', 'effect': 'NoExecute', 'tolerationSeconds': 300}], 'priority': 0, 'enableServiceLinks': True, 'preemptionPolicy': 'PreemptLowerPriority'}, 'status': {'observedGeneration': 1, 'phase': 'Succeeded', 'conditions': [{'type': 'PodReadyToStartContainers', 'observedGeneration': 1, 'status': 'False', 'lastProbeTime': None, 'lastTransitionTime': '2026-07-07T12:21:43Z'}, {'type': 'Initialized', 'observedGeneration': 1, 'status': 'True', 'lastProbeTime': None, 'lastTransitionTime': '2026-07-07T12:21:12Z', 'reason': 'PodCompleted'}, {'type': 'Ready', 'observedGeneration': 1, 'status': 'False', 'lastProbeTime': None, 'lastTransitionTime': '2026-07-07T12:21:41Z', 'reason': 'PodCompleted'}, {'type': 'ContainersReady', 'observedGeneration': 1, 'status': 'False', 'lastProbeTime': None, 'lastTransitionTime': '2026-07-07T12:21:41Z', 'reason': 'PodCompleted'}, {'type': 'PodScheduled', 'observedGeneration': 1, 'status': 'True', 'lastProbeTime': None, 'lastTransitionTime': '2026-07-07T12:21:12Z'}], 'hostIP': '10.0.1.76', 'hostIPs': [{'ip': '10.0.1.76'}], 'podIP': '10.128.1.131', 'podIPs': [{'ip': '10.128.1.131'}], 'startTime': '2026-07-07T12:21:12Z', 'containerStatuses': [{'name': 'ovms-smoke', 'state': {'terminated': {'exitCode': 0, 'reason': 'Completed', 'startedAt': '2026-07-07T12:21:13Z', 'finishedAt': '2026-07-07T12:21:41Z', 'containerID': 'cri-o://541e5373524be805bc7f58b5d37837eeef11cd474a876e9519ccaf1a644478d9'}}, 'lastState': {}, 'ready': False, 'restartCount': 0, 'image': 'quay.io/rhoai/odh-openvino-model-server-rhel9@sha256:8456a5e15035b06449619cd95ce0c73c3b24389723ed46524c06b6d87c988697', 'imageID': 'quay.io/rhoai/odh-openvino-model-server-rhel9@sha256:8456a5e15035b06449619cd95ce0c73c3b24389723ed46524c06b6d87c988697', 'containerID': 'cri-o://541e5373524be805bc7f58b5d37837eeef11cd474a876e9519ccaf1a644478d9', 'started': False, 'resources': {}, 'volumeMounts': [{'name': 'smoke-scripts', 'mountPath': '/scripts', 'readOnly': True, 'recursiveReadOnly': 'Disabled'}, {'name': 'kube-api-access-7nhj9', 'mountPath': '/var/run/secrets/kubernetes.io/serviceaccount', 'readOnly': True, 'recursiveReadOnly': 'Disabled'}], 'user': {'linux': {'uid': 1000990000, 'gid': 0, 'supplementalGroups': [0]}}}], 'qosClass': 'BestEffort'}} [ocp_resources Pod] 2026-07-07T12:21:43.659183Z [info ] Wait until Pod ovms-smoke-pod is deleted [ocp_resources Pod] 2026-07-07T12:21:43.659434Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:43.678821Z [info ] Elapsed time: 4.863739013671875e-05 [0:00:00.000049] [timeout_sampler] 2026-07-07T12:21:43.679048Z [info ] Delete ConfigMap ovms-smoke-scripts [ocp_resources ConfigMap] 2026-07-07T12:21:43.717794Z [info ] Deleting {'kind': 'ConfigMap', 'apiVersion': 'v1', 'metadata': {'name': 'ovms-smoke-scripts', 'namespace': 'ovms-smoke', 'uid': '2ac3276a-d3dc-4b05-b927-a9c8838d98e0', 'resourceVersion': '18734127', 'creationTimestamp': '2026-07-07T12:21:12Z', 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:12Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:data': {'.': {}, 'f:ovms_smoketest.py': {}, 'f:smoke.py': {}}}}]}, 'data': '*******'} [ocp_resources ConfigMap] 2026-07-07T12:21:43.743683Z [info ] Wait until ConfigMap ovms-smoke-scripts is deleted [ocp_resources ConfigMap] 2026-07-07T12:21:43.743918Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:43.762903Z [info ] Elapsed time: 5.173683166503906e-05 [0:00:00.000052] [timeout_sampler] 2026-07-07T12:21:43.781160Z [info ] Delete Namespace ovms-smoke  [ocp_resources Namespace] 2026-07-07T12:21:43.819162Z [info ] Deleting {'kind': 'Namespace', 'apiVersion': 'v1', 'metadata': {'name': 'ovms-smoke', 'uid': 'c2916003-8a79-4c99-b21c-c955cbdc632e', 'resourceVersion': '18734118', 'creationTimestamp': '2026-07-07T12:21:12Z', 'labels': {'kubernetes.io/metadata.name': 'ovms-smoke', 'pod-security.kubernetes.io/audit': 'restricted', 'pod-security.kubernetes.io/audit-version': 'latest', 'pod-security.kubernetes.io/warn': 'restricted', 'pod-security.kubernetes.io/warn-version': 'latest'}, 'annotations': {'openshift.io/sa.scc.mcs': 's0:c31,c30', 'openshift.io/sa.scc.supplemental-groups': '1000990000/10000', 'openshift.io/sa.scc.uid-range': '1000990000/10000', 'security.openshift.io/MinimallySufficientPodSecurityStandard': 'restricted'}, 'managedFields': [{'manager': 'cluster-policy-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:12Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:openshift.io/sa.scc.mcs': {}, 'f:openshift.io/sa.scc.supplemental-groups': {}, 'f:openshift.io/sa.scc.uid-range': {}}}}}, {'manager': 'pod-security-admission-label-synchronization-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:12Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:security.openshift.io/MinimallySufficientPodSecurityStandard': {}}, 'f:labels': {'f:pod-security.kubernetes.io/audit': {}, 'f:pod-security.kubernetes.io/audit-version': {}, 'f:pod-security.kubernetes.io/warn': {}, 'f:pod-security.kubernetes.io/warn-version': {}}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:12Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:kubernetes.io/metadata.name': {}}}}}]}, 'spec': {'finalizers': ['kubernetes']}, 'status': {'phase': 'Active'}} [ocp_resources Namespace] 2026-07-07T12:21:43.847496Z [info ] Wait until Namespace ovms-smoke is deleted [ocp_resources Namespace] 2026-07-07T12:21:43.847668Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] _ 3 of 9 completed, 3 Pass, 0 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/triton/basic_model_deployment/test_tensorflow_model.py::TestTensorflowModel::test_tensorflow_inference[tensorflow-standard-rest-deployment] 2026-07-07T12:21:52.022094Z [info ] Elapsed time: 8.153506517410278 [0:00:08.153507] [timeout_sampler]  ---------------------------- test_tensorflow_inference[tensorflow-standard-rest-deployment] ---------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:21:52.028034Z [info ] Executing session fixture: root_dir [conftest] 2026-07-07T12:21:52.028308Z [info ] Executing session fixture: triton_runtime_image [conftest] 2026-07-07T12:21:52.028464Z [info ] Executing session fixture: supported_accelerator_type [conftest] 2026-07-07T12:21:52.028595Z [info ] Executing session fixture: s3_models_storage_uri [conftest] 2026-07-07T12:21:52.028699Z [info ] Executing class fixture: triton_rest_serving_runtime_template [conftest] 2026-07-07T12:21:52.028803Z [info ] Create Template triton-rest-runtime-template [ocp_resources Template] 2026-07-07T12:21:52.028917Z [info ] Posting {'apiVersion': 'template.openshift.io/v1', 'kind': 'Template', 'metadata': {'name': 'triton-rest-runtime-template', 'namespace': 'redhat-ods-applications'}, 'objects': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'name': 'triton-rest-runtime', 'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}}, 'spec': {'containers': [{'name': 'kserve-container', 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'args': ['tritonserver', '--model-store=/mnt/models', '--http-port=8080', '--allow-http=True'], 'ports': [{'name': 'http1', 'containerPort': 8080, 'protocol': 'TCP'}], 'volumeMounts': [], 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '1', 'memory': '2Gi'}}}], 'volumes': [], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'name': 'tensorrt', 'version': '8', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'onnx', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'pytorch', 'version': '1', 'autoSelect': True}, {'name': 'triton', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'xgboost', 'version': '1', 'autoSelect': True}, {'name': 'python', 'version': '1', 'autoSelect': True}]}}], 'parameters': []} [ocp_resources Template] 2026-07-07T12:21:52.082390Z [info ] Executing class fixture: triton_grpc_serving_runtime_template [conftest] 2026-07-07T12:21:52.082545Z [info ] Create Template triton-grpc-runtime-template [ocp_resources Template] 2026-07-07T12:21:52.082674Z [info ] Posting {'apiVersion': 'template.openshift.io/v1', 'kind': 'Template', 'metadata': {'name': 'triton-grpc-runtime-template', 'namespace': 'redhat-ods-applications'}, 'objects': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'name': 'triton-grpc-runtime', 'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}}, 'spec': {'containers': [{'name': 'kserve-container', 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'args': ['tritonserver', '--model-store=/mnt/models', '--grpc-port=9000', '--allow-grpc=True'], 'ports': [{'name': 'h2c', 'containerPort': 9000, 'protocol': 'TCP'}], 'volumeMounts': [{'name': 'shm', 'mountPath': '/dev/shm'}], 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '1', 'memory': '2Gi'}}}], 'volumes': [{'name': 'shm', 'emptyDir': {'medium': 'Memory', 'sizeLimit': '2Gi'}}], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'name': 'tensorrt', 'version': '8', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'onnx', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'pytorch', 'version': '1', 'autoSelect': True}, {'name': 'triton', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'xgboost', 'version': '1', 'autoSelect': True}, {'name': 'python', 'version': '1', 'autoSelect': True}]}}], 'parameters': []} [ocp_resources Template] 2026-07-07T12:21:52.134009Z [info ] Executing class fixture: model_namespace [conftest] 2026-07-07T12:21:52.134207Z [info ] Create Namespace tensorflow-standard [ocp_resources Namespace] 2026-07-07T12:21:52.134371Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Namespace', 'metadata': {'name': 'tensorflow-standard'}, 'spec': {}} [ocp_resources Namespace] 2026-07-07T12:21:52.189122Z [info ] Wait for Namespace tensorflow-standard status to be Active [ocp_resources Namespace] 2026-07-07T12:21:52.189321Z [info ] Waiting for 120 seconds [0:02:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:52.210217Z [info ] Status of Namespace tensorflow-standard is Active [ocp_resources Namespace] 2026-07-07T12:21:52.210434Z [info ] Elapsed time: 6.508827209472656e-05 [0:00:00.000065] [timeout_sampler] 2026-07-07T12:21:52.210553Z [info ] Executing class fixture: protocol [conftest] 2026-07-07T12:21:52.210974Z [info ] Executing class fixture: triton_serving_runtime [conftest] 2026-07-07T12:21:52.273951Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 --- [DuplicateFilter: Last log `kind: Template api version: template.openshift.io/v1` repeated 3 times] [ocp_resources.resource] 2026-07-07T12:21:52.274128Z [info ] Create ServingRuntime triton-rest-runtime [ocp_resources ServingRuntime] 2026-07-07T12:21:52.274361Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'name': 'triton-rest-runtime', 'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}, 'namespace': 'tensorflow-standard'}, 'spec': {'containers': [{'name': 'kserve-container', 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'args': ['tritonserver', '--model-store=/mnt/models', '--http-port=8080', '--allow-http=True'], 'ports': [{'name': 'http1', 'containerPort': 8080, 'protocol': 'TCP'}], 'volumeMounts': [], 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '1', 'memory': '2Gi'}}}], 'volumes': [], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'name': 'tensorrt', 'version': '8', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'onnx', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'pytorch', 'version': '1', 'autoSelect': True}, {'name': 'triton', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'xgboost', 'version': '1', 'autoSelect': True}, {'name': 'python', 'version': '1', 'autoSelect': True}]}} [ocp_resources ServingRuntime] 2026-07-07T12:21:52.331539Z [info ] Executing class fixture: kserve_s3_secret [conftest] 2026-07-07T12:21:52.331722Z [info ] Create Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:21:52.331967Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Secret', 'metadata': {'name': 'models-bucket-secret', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-verifyssl': '0', 'serving.kserve.io/s3-usehttps': '1'}, 'namespace': 'tensorflow-standard'}, 'stringData': '*******'} [ocp_resources Secret] 2026-07-07T12:21:52.380747Z [info ] Wait until Secret models-bucket-secret is created [ocp_resources Secret] 2026-07-07T12:21:52.380941Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:21:52.401302Z [info ] Elapsed time: 5.316734313964844e-05 [0:00:00.000053] [timeout_sampler] 2026-07-07T12:21:52.401500Z [info ] Executing class fixture: triton_model_service_account [conftest] 2026-07-07T12:21:52.402153Z [info ] Create ServiceAccount triton-models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:21:52.402396Z [info ] Posting {'apiVersion': 'v1', 'kind': 'ServiceAccount', 'metadata': {'name': 'triton-models-bucket-sa', 'namespace': 'tensorflow-standard'}, 'secrets': [{'name': 'models-bucket-secret'}]} [ocp_resources ServiceAccount] 2026-07-07T12:21:52.444151Z [info ] Executing class fixture: triton_inference_service [conftest] 2026-07-07T12:21:52.469391Z [info ] kind: InferenceService api version: serving.kserve.io/v1beta1 [ocp_resources.resource] 2026-07-07T12:21:52.469602Z [info ] Create InferenceService tensorflow-standard-rest [ocp_resources InferenceService] 2026-07-07T12:21:52.469800Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'name': 'tensorflow-standard-rest', 'annotations': {'serving.kserve.io/deploymentMode': 'Standard'}, 'namespace': 'tensorflow-standard'}, 'spec': {'predictor': {'model': {'modelFormat': {'name': 'tensorrt'}, 'version': None, 'runtime': 'triton-rest-runtime', 'storageUri': 's3://ods-ci-wisdom/triton/model_repository/', 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '2', 'memory': '4Gi'}}}, 'minReplicas': 1, 'serviceAccountName': 'triton-models-bucket-sa'}}} [ocp_resources InferenceService] 2026-07-07T12:21:52.542361Z [info ] Waiting for 30 seconds [0:00:30], retry every 1 seconds. (Function: utilities.infra.wait_for_isvc_pods Kwargs: {'client': , 'isvc': , 'runtime_name': 'triton-rest-runtime'}) [timeout_sampler] 2026-07-07T12:21:52.541530Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:21:53.585581Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:21:53.639428Z [info ] Elapsed time: 1.0441784858703613 [0:00:01.044178] [timeout_sampler] 2026-07-07T12:21:53.657081Z [info ] Verifying no failed pods  [utilities.infra] name=utilities.infra 2026-07-07T12:21:53.658150Z [info ] Waiting for 599.9999914169312 seconds [0:09:59.999991], retry every 10 seconds. (Function: utilities.infra.get_pods_by_isvc_label Kwargs: {'client': , 'isvc': , 'runtime_name': 'triton-rest-runtime'}) [timeout_sampler] 2026-07-07T12:22:03.858321Z [info ] Elapsed time: 10.108207702636719 [0:00:10.108208] [timeout_sampler] 2026-07-07T12:22:03.877446Z [info ] Waiting for 588.6648697853088 seconds [0:09:48.664870], retry every 5 seconds. (Function: ocp_resources.resource.get Kwargs: {'label_selector': 'serving.kserve.io/inferenceservice=tensorflow-standard-rest', 'client': , 'namespace': 'tensorflow-standard'}) [timeout_sampler] 2026-07-07T12:22:03.896571Z [info ] Elapsed time: 0.00012993812561035156 [0:00:00.000130] [timeout_sampler] 2026-07-07T12:22:03.895842Z [info ] Waiting for inference deployment replicas to complete [utilities.infra] name=utilities.infra 2026-07-07T12:22:03.954814Z [info ] Waiting for 588.5875127315521 seconds [0:09:48.587513], retry every 5 seconds. (Function: utilities.infra..lambda: deployment.instance) [timeout_sampler] 2026-07-07T12:22:03.974288Z [info ] Elapsed time: 0.00014781951904296875 [0:00:00.000148] [timeout_sampler] 2026-07-07T12:22:03.974479Z [info ] Wait for Deployment tensorflow-standard-rest-predictor to be deployed: True [ocp_resources Deployment] 2026-07-07T12:22:03.974623Z [info ] Waiting for 588.5678291320801 seconds [0:09:48.567829], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:03.992942Z [info ] Elapsed time: 3.933906555175781e-05 [0:00:00.000039] [timeout_sampler] 2026-07-07T12:22:03.993128Z [info ] Waiting for 588.5491459369659 seconds [0:09:48.549146], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.instance) [timeout_sampler] 2026-07-07T12:22:04.012222Z [info ] Elapsed time: 4.4345855712890625e-05 [0:00:00.000044] [timeout_sampler] 2026-07-07T12:22:04.012398Z [info ] Wait for InferenceService/tensorflow-standard-rest's 'Ready' condition to be 'True' [ocp_resources InferenceService] 2026-07-07T12:22:04.012534Z [info ] Wait until InferenceService tensorflow-standard-rest is created [ocp_resources InferenceService] 2026-07-07T12:22:04.012687Z [info ] Waiting for 588.5298593044281 seconds [0:09:48.529859], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:04.030731Z [info ] Elapsed time: 3.600120544433594e-05 [0:00:00.000036] [timeout_sampler] 2026-07-07T12:22:04.030914Z [info ] Waiting for 588.5113289356232 seconds [0:09:48.511329], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_condition.lambda: self.instance) [timeout_sampler] 2026-07-07T12:22:04.050226Z [info ] Elapsed time: 3.790855407714844e-05 [0:00:00.000038] [timeout_sampler] 2026-07-07T12:22:04.069268Z [info ] Waiting for 588.4729228019714 seconds [0:09:48.472923], retry every 5 seconds. (Function: utilities.inference_utils._is_model_loaded) [timeout_sampler] 2026-07-07T12:22:04.087890Z [info ] Elapsed time: 0.00011110305786132812 [0:00:00.000111] [timeout_sampler] 2026-07-07T12:22:04.107130Z [info ] Executing function fixture: triton_pod_resource [conftest] 2026-07-07T12:22:04.149366Z [info ] Executing function fixture: snapshot [conftest] 2026-07-07T12:22:04.151535Z [info ] Executing function fixture: triton_response_snapshot [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- PASSED TEST: TestTensorflowModel.test_tensorflow_inference[tensorflow-standard-rest-deployment] STATUS: PASSED _ 4 of 9 completed, 4 Pass, 0 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/triton/basic_model_deployment/test_tensorflow_model.py::TestTensorflowModel::test_tensorflow_inference[tensorflow-standard-grpc-deployment] ------------------------------------------------------- TEARDOWN -------------------------------------------------------  ---------------------------- test_tensorflow_inference[tensorflow-standard-grpc-deployment] ---------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:22:07.236163Z [info ] Delete InferenceService tensorflow-standard-rest [ocp_resources InferenceService] 2026-07-07T12:22:07.279969Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'tensorrt', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-07-07T12:21:52Z', 'finalizers': ['inferenceservice.finalizers', 'odh.inferenceservice.finalizers'], 'generation': 1, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/deploymentMode': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:minReplicas': {}, 'f:model': {'.': {}, 'f:modelFormat': {'.': {}, 'f:name': {}}, 'f:resources': {'.': {}, 'f:limits': {'.': {}, 'f:cpu': {}, 'f:memory': {}}, 'f:requests': {'.': {}, 'f:cpu': {}, 'f:memory': {}}}, 'f:runtime': {}, 'f:storageUri': {}}, 'f:serviceAccountName': {}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:21:52Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-07-07T12:21:52Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {'.': {}, 'f:url': {}}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}, 'f:totalCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-07-07T12:22:03Z'}], 'name': 'tensorflow-standard-rest', 'namespace': 'tensorflow-standard', 'resourceVersion': '18735156', 'uid': 'e67e3d30-e517-4af6-a05f-4db07dcb83ee'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'minReplicas': 1, 'model': {'modelFormat': {'name': 'tensorrt'}, 'name': '', 'resources': {'limits': {'cpu': '2', 'memory': '4Gi'}, 'requests': {'cpu': '1', 'memory': '2Gi'}}, 'runtime': 'triton-rest-runtime', 'storageUri': 's3://ods-ci-wisdom/triton/model_repository/'}, 'serviceAccountName': 'triton-models-bucket-sa'}}, 'status': {'address': {'url': 'http://tensorflow-standard-rest-predictor.tensorflow-standard.svc.cluster.local:8080'}, 'components': {'predictor': {'url': 'http://tensorflow-standard-rest-predictor-tensorflow-standard.example.com'}}, 'conditions': [{'lastTransitionTime': '2026-07-07T12:21:52Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-07-07T12:22:03Z', 'message': 'ReplicaSet "tensorflow-standard-rest-predictor-6f846cb87f" has successfully progressed.', 'reason': 'NewReplicaSetAvailable', 'status': 'True', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-07-07T12:22:03Z', 'status': 'True', 'type': 'Ready'}, {'lastTransitionTime': '2026-07-07T12:21:52Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0, 'totalCopies': 1}, 'states': {'activeModelState': 'Loaded', 'targetModelState': 'Loaded'}, 'transitionStatus': 'UpToDate'}, 'observedGeneration': 1, 'servingRuntimeName': 'triton-rest-runtime', 'url': 'http://tensorflow-standard-rest-predictor.tensorflow-standard.svc.cluster.local'}} [ocp_resources InferenceService] 2026-07-07T12:22:07.307592Z [info ] Wait until InferenceService tensorflow-standard-rest is deleted [ocp_resources InferenceService] 2026-07-07T12:22:07.307774Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:08.348165Z [info ] Elapsed time: 1.018995761871338 [0:00:01.018996] [timeout_sampler] 2026-07-07T12:22:08.348512Z [info ] Delete ServingRuntime triton-rest-runtime [ocp_resources ServingRuntime] 2026-07-07T12:22:08.389491Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}, 'creationTimestamp': '2026-07-07T12:21:52Z', 'generation': 1, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:prometheus.kserve.io/path': {}, 'f:prometheus.kserve.io/port': {}}}, 'f:spec': {'.': {}, 'f:containers': {}, 'f:protocolVersions': {}, 'f:supportedModelFormats': {}, 'f:volumes': {}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:21:52Z'}], 'name': 'triton-rest-runtime', 'namespace': 'tensorflow-standard', 'resourceVersion': '18734871', 'uid': '5ec3c77c-98ef-4ef7-bdb2-f0f7e266e1d3'}, 'spec': {'containers': [{'args': ['tritonserver', '--model-store=/mnt/models', '--http-port=8080', '--allow-http=True'], 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'name': 'http1', 'protocol': 'TCP'}], 'resources': {'limits': {'cpu': '1', 'memory': '2Gi'}, 'requests': {'cpu': '1', 'memory': '2Gi'}}, 'volumeMounts': []}], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'autoSelect': True, 'name': 'tensorrt', 'priority': 1, 'version': '8'}, {'autoSelect': True, 'name': 'tensorflow', 'priority': 1, 'version': '1'}, {'autoSelect': True, 'name': 'tensorflow', 'priority': 1, 'version': '2'}, {'autoSelect': True, 'name': 'onnx', 'priority': 1, 'version': '1'}, {'autoSelect': True, 'name': 'pytorch', 'version': '1'}, {'autoSelect': True, 'name': 'triton', 'priority': 1, 'version': '2'}, {'autoSelect': True, 'name': 'xgboost', 'version': '1'}, {'autoSelect': True, 'name': 'python', 'version': '1'}], 'volumes': []}} [ocp_resources ServingRuntime] 2026-07-07T12:22:08.411583Z [info ] Wait until ServingRuntime triton-rest-runtime is deleted [ocp_resources ServingRuntime] 2026-07-07T12:22:08.411749Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:08.431376Z [info ] Elapsed time: 5.91278076171875e-05 [0:00:00.000059] [timeout_sampler] 2026-07-07T12:22:08.431575Z [info ] Executing class fixture: protocol [conftest] 2026-07-07T12:22:08.431720Z [info ] Executing class fixture: triton_serving_runtime [conftest] 2026-07-07T12:22:08.431860Z [info ] kind: Template api version: template.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:22:08.478321Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:22:08.478523Z [info ] Create ServingRuntime triton-grpc-runtime [ocp_resources ServingRuntime] 2026-07-07T12:22:08.478687Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'name': 'triton-grpc-runtime', 'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}, 'namespace': 'tensorflow-standard'}, 'spec': {'containers': [{'name': 'kserve-container', 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'args': ['tritonserver', '--model-store=/mnt/models', '--http-port=8080', '--allow-http=True'], 'ports': [{'name': 'http1', 'containerPort': 8080, 'protocol': 'TCP'}], 'volumeMounts': [], 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '1', 'memory': '2Gi'}}}], 'volumes': [], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'name': 'tensorrt', 'version': '8', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'onnx', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'pytorch', 'version': '1', 'autoSelect': True}, {'name': 'triton', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'xgboost', 'version': '1', 'autoSelect': True}, {'name': 'python', 'version': '1', 'autoSelect': True}]}} [ocp_resources ServingRuntime] 2026-07-07T12:22:08.524920Z [info ] Executing class fixture: triton_inference_service [conftest] 2026-07-07T12:22:08.544890Z [info ] kind: InferenceService api version: serving.kserve.io/v1beta1 [ocp_resources.resource] 2026-07-07T12:22:08.545088Z [info ] Create InferenceService tensorflow-standard-grpc [ocp_resources InferenceService] 2026-07-07T12:22:08.545412Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'name': 'tensorflow-standard-grpc', 'annotations': {'serving.kserve.io/deploymentMode': 'Standard'}, 'namespace': 'tensorflow-standard'}, 'spec': {'predictor': {'model': {'modelFormat': {'name': 'tensorrt'}, 'version': None, 'runtime': 'triton-grpc-runtime', 'storageUri': 's3://ods-ci-wisdom/triton/model_repository/', 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '2', 'memory': '4Gi'}}}, 'minReplicas': 1, 'serviceAccountName': 'triton-models-bucket-sa'}}} [ocp_resources InferenceService] 2026-07-07T12:22:08.612219Z [info ] Waiting for 30 seconds [0:00:30], retry every 1 seconds. (Function: utilities.infra.wait_for_isvc_pods Kwargs: {'client': , 'isvc': , 'runtime_name': 'triton-grpc-runtime'}) [timeout_sampler] 2026-07-07T12:22:08.611380Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:22:09.650263Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:22:09.704677Z [info ] Elapsed time: 1.0390050411224365 [0:00:01.039005] [timeout_sampler] 2026-07-07T12:22:09.722692Z [info ] Verifying no failed pods  [utilities.infra] name=utilities.infra 2026-07-07T12:22:09.723827Z [info ] Waiting for 599.99999833107 seconds [0:09:59.999998], retry every 10 seconds. (Function: utilities.infra.get_pods_by_isvc_label Kwargs: {'client': , 'isvc': , 'runtime_name': 'triton-grpc-runtime'}) [timeout_sampler] 2026-07-07T12:22:30.016877Z [info ] Elapsed time: 20.201402187347412 [0:00:20.201402] [timeout_sampler] 2026-07-07T12:22:30.035610Z [info ] Waiting for 578.5761284828186 seconds [0:09:38.576128], retry every 5 seconds. (Function: ocp_resources.resource.get Kwargs: {'label_selector': 'serving.kserve.io/inferenceservice=tensorflow-standard-grpc', 'client': , 'namespace': 'tensorflow-standard'}) [timeout_sampler] 2026-07-07T12:22:30.055561Z [info ] Elapsed time: 6.127357482910156e-05 [0:00:00.000061] [timeout_sampler] 2026-07-07T12:22:30.055008Z [info ] Waiting for inference deployment replicas to complete [utilities.infra] name=utilities.infra 2026-07-07T12:22:30.119802Z [info ] Waiting for 578.4918870925903 seconds [0:09:38.491887], retry every 5 seconds. (Function: utilities.infra..lambda: deployment.instance) [timeout_sampler] 2026-07-07T12:22:30.139062Z [info ] Elapsed time: 7.367134094238281e-05 [0:00:00.000074] [timeout_sampler] 2026-07-07T12:22:30.139251Z [info ] Wait for Deployment tensorflow-standard-grpc-predictor to be deployed: True [ocp_resources Deployment] 2026-07-07T12:22:30.139520Z [info ] Waiting for 578.4725637435913 seconds [0:09:38.472564], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:30.157605Z [info ] Elapsed time: 3.0994415283203125e-05 [0:00:00.000031] [timeout_sampler] 2026-07-07T12:22:30.157780Z [info ] Waiting for 578.4540932178497 seconds [0:09:38.454093], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.instance) [timeout_sampler] 2026-07-07T12:22:30.177941Z [info ] Elapsed time: 3.910064697265625e-05 [0:00:00.000039] [timeout_sampler] 2026-07-07T12:22:30.178110Z [info ] Wait for InferenceService/tensorflow-standard-grpc's 'Ready' condition to be 'True' [ocp_resources InferenceService] 2026-07-07T12:22:30.178294Z [info ] Wait until InferenceService tensorflow-standard-grpc is created [ocp_resources InferenceService] 2026-07-07T12:22:30.178450Z [info ] Waiting for 578.4337661266327 seconds [0:09:38.433766], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:30.197911Z [info ] Elapsed time: 2.9802322387695312e-05 [0:00:00.000030] [timeout_sampler] 2026-07-07T12:22:30.198069Z [info ] Waiting for 578.4137964248657 seconds [0:09:38.413796], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_condition.lambda: self.instance) [timeout_sampler] 2026-07-07T12:22:30.216499Z [info ] Elapsed time: 4.00543212890625e-05 [0:00:00.000040] [timeout_sampler] 2026-07-07T12:22:30.234767Z [info ] Waiting for 578.3768875598907 seconds [0:09:38.376888], retry every 5 seconds. (Function: utilities.inference_utils._is_model_loaded) [timeout_sampler] 2026-07-07T12:22:30.253010Z [info ] Elapsed time: 5.602836608886719e-05 [0:00:00.000056] [timeout_sampler] 2026-07-07T12:22:30.271443Z [info ] Executing function fixture: triton_pod_resource [conftest] 2026-07-07T12:22:30.310895Z [info ] Executing function fixture: snapshot [conftest] 2026-07-07T12:22:30.311055Z [info ] Executing function fixture: triton_response_snapshot [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- [2026-07-07T12:22:30Z ERROR portforward::portforward] failed to forward connection: failed to send a WebSocket message: WebSocket protocol error: Sending after closing is not allowed [2026-07-07T12:22:31Z ERROR portforward::portforward] failed to forward connection: failed to send a WebSocket message: WebSocket protocol error: Sending after closing is not allowed [2026-07-07T12:22:33Z ERROR portforward::portforward] failed to forward connection: failed to send a WebSocket message: WebSocket protocol error: Sending after closing is not allowed [2026-07-07T12:22:35Z ERROR portforward::portforward] failed to forward connection: failed to send a WebSocket message: WebSocket protocol error: Sending after closing is not allowed [2026-07-07T12:22:40Z ERROR portforward::portforward] failed to forward connection: failed to send a WebSocket message: WebSocket protocol error: Sending after closing is not allowed FAILED TEST: TestTensorflowModel.test_tensorflow_inference[tensorflow-standard-grpc-deployment] STATUS: FAILED 2026-07-07T12:22:40.495766Z [error ] Traceback (most recent call last): File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 353, in from_call result: TResult | None = func() ~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 245, in lambda: runtest_hook(item=item, **kwds), ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_hooks.py", line 512, in __call__ return self._hookexec(self.name, self._hookimpls.copy(), kwargs, firstresult) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_manager.py", line 120, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 167, in _multicall raise exception File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/capture.py", line 900, in pytest_runtest_call return (yield) ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 53, in run_old_style_hookwrapper return result.get_result() ~~~~~~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_result.py", line 103, in get_result raise exc.with_traceback(tb) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 38, in run_old_style_hookwrapper res = yield ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/skipping.py", line 268, in pytest_runtest_call return (yield) ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 121, in _multicall res = hook_impl.function(*args) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 179, in pytest_runtest_call item.runtest() ~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/python.py", line 1720, in runtest self.ihook.pytest_pyfunc_call(pyfuncitem=self) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_hooks.py", line 512, in __call__ return self._hookexec(self.name, self._hookimpls.copy(), kwargs, firstresult) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_manager.py", line 120, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 167, in _multicall raise exception File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 53, in run_old_style_hookwrapper return result.get_result() ~~~~~~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_result.py", line 103, in get_result raise exc.with_traceback(tb) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 38, in run_old_style_hookwrapper res = yield ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 121, in _multicall res = hook_impl.function(*args) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/python.py", line 166, in pytest_pyfunc_call result = testfunction(**testargs) File "/home/odh/opendatahub-tests/tests/model_serving/model_runtime/triton/basic_model_deployment/test_tensorflow_model.py", line 97, in test_tensorflow_inference validate_inference_request( ~~~~~~~~~~~~~~~~~~~~~~~~~~^ pod_name=triton_pod_resource.name, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<5 lines>... root_dir=root_dir, ^^^^^^^^^^^^^^^^^^ ) ^ File "/home/odh/opendatahub-tests/tests/model_serving/model_runtime/triton/basic_model_deployment/utils.py", line 149, in validate_inference_request assert isinstance(response, dict), f"Response is not a dict: {response}" ~~~~~~~~~~^^^^^^^^^^^^^^^^ AssertionError: Response is not a dict: gRPC request (stdin) failed: STDOUT: STDERR: Failed to dial target host "localhost:9000": context deadline exceeded [conftest] ------------------------------------------------------- TEARDOWN ------------------------------------------------------- 2026-07-07T12:22:40.496015Z [info ] Delete InferenceService tensorflow-standard-grpc [ocp_resources InferenceService] 2026-07-07T12:22:40.538321Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'tensorrt', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-07-07T12:22:08Z', 'finalizers': ['inferenceservice.finalizers', 'odh.inferenceservice.finalizers'], 'generation': 1, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/deploymentMode': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:minReplicas': {}, 'f:model': {'.': {}, 'f:modelFormat': {'.': {}, 'f:name': {}}, 'f:resources': {'.': {}, 'f:limits': {'.': {}, 'f:cpu': {}, 'f:memory': {}}, 'f:requests': {'.': {}, 'f:cpu': {}, 'f:memory': {}}}, 'f:runtime': {}, 'f:storageUri': {}}, 'f:serviceAccountName': {}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:22:08Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-07-07T12:22:08Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {'.': {}, 'f:url': {}}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}, 'f:totalCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-07-07T12:22:21Z'}], 'name': 'tensorflow-standard-grpc', 'namespace': 'tensorflow-standard', 'resourceVersion': '18735562', 'uid': 'fcd5a76d-d2e5-4952-8d6d-9b5d956ffc41'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'minReplicas': 1, 'model': {'modelFormat': {'name': 'tensorrt'}, 'name': '', 'resources': {'limits': {'cpu': '2', 'memory': '4Gi'}, 'requests': {'cpu': '1', 'memory': '2Gi'}}, 'runtime': 'triton-grpc-runtime', 'storageUri': 's3://ods-ci-wisdom/triton/model_repository/'}, 'serviceAccountName': 'triton-models-bucket-sa'}}, 'status': {'address': {'url': 'http://tensorflow-standard-grpc-predictor.tensorflow-standard.svc.cluster.local:8080'}, 'components': {'predictor': {'url': 'http://tensorflow-standard-grpc-predictor-tensorflow-standard.example.com'}}, 'conditions': [{'lastTransitionTime': '2026-07-07T12:22:08Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-07-07T12:22:21Z', 'message': 'ReplicaSet "tensorflow-standard-grpc-predictor-5d5bd5d8df" has successfully progressed.', 'reason': 'NewReplicaSetAvailable', 'status': 'True', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-07-07T12:22:21Z', 'status': 'True', 'type': 'Ready'}, {'lastTransitionTime': '2026-07-07T12:22:08Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0, 'totalCopies': 1}, 'states': {'activeModelState': 'Loaded', 'targetModelState': 'Loaded'}, 'transitionStatus': 'UpToDate'}, 'observedGeneration': 1, 'servingRuntimeName': 'triton-grpc-runtime', 'url': 'http://tensorflow-standard-grpc-predictor.tensorflow-standard.svc.cluster.local'}} [ocp_resources InferenceService] 2026-07-07T12:22:40.568360Z [info ] Wait until InferenceService tensorflow-standard-grpc is deleted [ocp_resources InferenceService] 2026-07-07T12:22:40.568565Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:41.610332Z [info ] Elapsed time: 1.021897315979004 [0:00:01.021897] [timeout_sampler] 2026-07-07T12:22:41.610484Z [info ] Delete ServingRuntime triton-grpc-runtime [ocp_resources ServingRuntime] 2026-07-07T12:22:41.648572Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}, 'creationTimestamp': '2026-07-07T12:22:08Z', 'generation': 1, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:prometheus.kserve.io/path': {}, 'f:prometheus.kserve.io/port': {}}}, 'f:spec': {'.': {}, 'f:containers': {}, 'f:protocolVersions': {}, 'f:supportedModelFormats': {}, 'f:volumes': {}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:22:08Z'}], 'name': 'triton-grpc-runtime', 'namespace': 'tensorflow-standard', 'resourceVersion': '18735268', 'uid': '4e55d0a8-4f86-4ce4-ac61-b1f6fceb691e'}, 'spec': {'containers': [{'args': ['tritonserver', '--model-store=/mnt/models', '--http-port=8080', '--allow-http=True'], 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'name': 'http1', 'protocol': 'TCP'}], 'resources': {'limits': {'cpu': '1', 'memory': '2Gi'}, 'requests': {'cpu': '1', 'memory': '2Gi'}}, 'volumeMounts': []}], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'autoSelect': True, 'name': 'tensorrt', 'priority': 1, 'version': '8'}, {'autoSelect': True, 'name': 'tensorflow', 'priority': 1, 'version': '1'}, {'autoSelect': True, 'name': 'tensorflow', 'priority': 1, 'version': '2'}, {'autoSelect': True, 'name': 'onnx', 'priority': 1, 'version': '1'}, {'autoSelect': True, 'name': 'pytorch', 'version': '1'}, {'autoSelect': True, 'name': 'triton', 'priority': 1, 'version': '2'}, {'autoSelect': True, 'name': 'xgboost', 'version': '1'}, {'autoSelect': True, 'name': 'python', 'version': '1'}], 'volumes': []}} [ocp_resources ServingRuntime] 2026-07-07T12:22:41.670602Z [info ] Wait until ServingRuntime triton-grpc-runtime is deleted [ocp_resources ServingRuntime] 2026-07-07T12:22:41.670838Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:41.690034Z [info ] Elapsed time: 6.747245788574219e-05 [0:00:00.000067] [timeout_sampler] 2026-07-07T12:22:41.690220Z [info ] Delete ServiceAccount triton-models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:22:41.735734Z [info ] Deleting {'kind': 'ServiceAccount', 'apiVersion': 'v1', 'metadata': {'name': 'triton-models-bucket-sa', 'namespace': 'tensorflow-standard', 'uid': '5a339cd1-2fec-44cb-997c-fc6b09484fe4', 'resourceVersion': '18734885', 'creationTimestamp': '2026-07-07T12:21:52Z', 'annotations': {'openshift.io/internal-registry-pull-secret-ref': 'triton-models-bucket-sa-dockercfg-65tnt'}, 'managedFields': [{'manager': 'openshift.io/image-registry-pull-secrets_service-account-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:imagePullSecrets': {}, 'f:metadata': {'f:annotations': {'f:openshift.io/internal-registry-pull-secret-ref': {}}}, 'f:secrets': {'k:{"name":"triton-models-bucket-sa-dockercfg-65tnt"}': {}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:secrets': {'.': {}, 'k:{"name":"models-bucket-secret"}': {}}}}]}, 'secrets': [{'name': 'models-bucket-secret'}, {'name': 'triton-models-bucket-sa-dockercfg-65tnt'}], 'imagePullSecrets': [{'name': 'triton-models-bucket-sa-dockercfg-65tnt'}]} [ocp_resources ServiceAccount] 2026-07-07T12:22:41.760679Z [info ] Wait until ServiceAccount triton-models-bucket-sa is deleted [ocp_resources ServiceAccount] 2026-07-07T12:22:41.760853Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:41.780063Z [info ] Elapsed time: 6.079673767089844e-05 [0:00:00.000061] [timeout_sampler] 2026-07-07T12:22:41.780268Z [info ] Delete Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:22:41.825274Z [info ] Deleting {'kind': 'Secret', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-secret', 'namespace': 'tensorflow-standard', 'uid': 'ef4d0859-a29e-4253-b4d9-167684dbbdff', 'resourceVersion': '18734879', 'creationTimestamp': '2026-07-07T12:21:52Z', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-usehttps': '1', 'serving.kserve.io/s3-verifyssl': '0'}, 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:data': {'.': {}, 'f:AWS_ACCESS_KEY_ID': {}, 'f:AWS_SECRET_ACCESS_KEY': {}}, 'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/s3-endpoint': {}, 'f:serving.kserve.io/s3-region': {}, 'f:serving.kserve.io/s3-useanoncredential': {}, 'f:serving.kserve.io/s3-usehttps': {}, 'f:serving.kserve.io/s3-verifyssl': {}}}, 'f:type': {}}}]}, 'data': '*******', 'type': 'Opaque'} [ocp_resources Secret] 2026-07-07T12:22:41.849670Z [info ] Wait until Secret models-bucket-secret is deleted [ocp_resources Secret] 2026-07-07T12:22:41.849807Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:41.873102Z [info ] Elapsed time: 5.650520324707031e-05 [0:00:00.000057] [timeout_sampler] 2026-07-07T12:22:41.944309Z [info ] Delete Namespace tensorflow-standard [ocp_resources Namespace] 2026-07-07T12:22:41.982207Z [info ] Deleting {'kind': 'Namespace', 'apiVersion': 'v1', 'metadata': {'name': 'tensorflow-standard', 'uid': '61a7b67c-f862-48d4-bd59-24ecd9182150', 'resourceVersion': '18734855', 'creationTimestamp': '2026-07-07T12:21:52Z', 'labels': {'kubernetes.io/metadata.name': 'tensorflow-standard', 'pod-security.kubernetes.io/audit': 'restricted', 'pod-security.kubernetes.io/audit-version': 'latest', 'pod-security.kubernetes.io/warn': 'restricted', 'pod-security.kubernetes.io/warn-version': 'latest'}, 'annotations': {'openshift.io/sa.scc.mcs': 's0:c32,c4', 'openshift.io/sa.scc.supplemental-groups': '1001000000/10000', 'openshift.io/sa.scc.uid-range': '1001000000/10000', 'security.openshift.io/MinimallySufficientPodSecurityStandard': 'restricted'}, 'managedFields': [{'manager': 'cluster-policy-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:openshift.io/sa.scc.mcs': {}, 'f:openshift.io/sa.scc.supplemental-groups': {}, 'f:openshift.io/sa.scc.uid-range': {}}}}}, {'manager': 'pod-security-admission-label-synchronization-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:security.openshift.io/MinimallySufficientPodSecurityStandard': {}}, 'f:labels': {'f:pod-security.kubernetes.io/audit': {}, 'f:pod-security.kubernetes.io/audit-version': {}, 'f:pod-security.kubernetes.io/warn': {}, 'f:pod-security.kubernetes.io/warn-version': {}}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:kubernetes.io/metadata.name': {}}}}}]}, 'spec': {'finalizers': ['kubernetes']}, 'status': {'phase': 'Active'}} [ocp_resources Namespace] 2026-07-07T12:22:42.009965Z [info ] Wait until Namespace tensorflow-standard is deleted [ocp_resources Namespace] 2026-07-07T12:22:42.010129Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:51.202921Z [info ] Elapsed time: 9.172454595565796 [0:00:09.172455] [timeout_sampler] 2026-07-07T12:22:51.203163Z [info ] Delete Template triton-grpc-runtime-template [ocp_resources Template] 2026-07-07T12:22:51.249615Z [info ] Deleting {'kind': 'Template', 'apiVersion': 'template.openshift.io/v1', 'metadata': {'name': 'triton-grpc-runtime-template', 'namespace': 'redhat-ods-applications', 'uid': 'aa16972c-f3e1-49e6-8132-c8736c9c390e', 'resourceVersion': '18734833', 'creationTimestamp': '2026-07-07T12:21:52Z', 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'template.openshift.io/v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:objects': {}}}]}, 'objects': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'name': 'triton-grpc-runtime', 'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}}, 'spec': {'containers': [{'name': 'kserve-container', 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'args': ['tritonserver', '--model-store=/mnt/models', '--grpc-port=9000', '--allow-grpc=True'], 'ports': [{'name': 'h2c', 'containerPort': 9000, 'protocol': 'TCP'}], 'volumeMounts': [{'name': 'shm', 'mountPath': '/dev/shm'}], 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '1', 'memory': '2Gi'}}}], 'volumes': [{'name': 'shm', 'emptyDir': {'medium': 'Memory', 'sizeLimit': '2Gi'}}], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'name': 'tensorrt', 'version': '8', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'onnx', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'pytorch', 'version': '1', 'autoSelect': True}, {'name': 'triton', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'xgboost', 'version': '1', 'autoSelect': True}, {'name': 'python', 'version': '1', 'autoSelect': True}]}}]} [ocp_resources Template] 2026-07-07T12:22:51.275645Z [info ] Wait until Template triton-grpc-runtime-template is deleted [ocp_resources Template] 2026-07-07T12:22:51.275791Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:51.297674Z [info ] Elapsed time: 5.412101745605469e-05 [0:00:00.000054] [timeout_sampler] 2026-07-07T12:22:51.297809Z [info ] Delete Template triton-rest-runtime-template [ocp_resources Template] 2026-07-07T12:22:51.343401Z [info ] Deleting {'kind': 'Template', 'apiVersion': 'template.openshift.io/v1', 'metadata': {'name': 'triton-rest-runtime-template', 'namespace': 'redhat-ods-applications', 'uid': '5060aebd-2dbe-408a-a861-fbfc1d2ad2dc', 'resourceVersion': '18734832', 'creationTimestamp': '2026-07-07T12:21:52Z', 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'template.openshift.io/v1', 'time': '2026-07-07T12:21:52Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:objects': {}}}]}, 'objects': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'name': 'triton-rest-runtime', 'annotations': {'prometheus.kserve.io/path': '/metrics', 'prometheus.kserve.io/port': '8002'}}, 'spec': {'containers': [{'name': 'kserve-container', 'image': 'nvcr.io/nvidia/tritonserver:25.02-py3', 'args': ['tritonserver', '--model-store=/mnt/models', '--http-port=8080', '--allow-http=True'], 'ports': [{'name': 'http1', 'containerPort': 8080, 'protocol': 'TCP'}], 'volumeMounts': [], 'resources': {'requests': {'cpu': '1', 'memory': '2Gi'}, 'limits': {'cpu': '1', 'memory': '2Gi'}}}], 'volumes': [], 'protocolVersions': ['v2', 'grpc-v2'], 'supportedModelFormats': [{'name': 'tensorrt', 'version': '8', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'tensorflow', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'onnx', 'version': '1', 'autoSelect': True, 'priority': 1}, {'name': 'pytorch', 'version': '1', 'autoSelect': True}, {'name': 'triton', 'version': '2', 'autoSelect': True, 'priority': 1}, {'name': 'xgboost', 'version': '1', 'autoSelect': True}, {'name': 'python', 'version': '1', 'autoSelect': True}]}}]} [ocp_resources Template] 2026-07-07T12:22:51.370645Z [info ] Wait until Template triton-rest-runtime-template is deleted [ocp_resources Template] 2026-07-07T12:22:51.370842Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] _ TestTensorflowModel.test_tensorflow_inference[tensorflow-standard-grpc-deployment] _ Traceback (most recent call last): File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 353, in from_call result: TResult | None = func() ~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 245, in lambda: runtest_hook(item=item, **kwds), ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_hooks.py", line 512, in __call__ return self._hookexec(self.name, self._hookimpls.copy(), kwargs, firstresult) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_manager.py", line 120, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 167, in _multicall raise exception File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/capture.py", line 900, in pytest_runtest_call return (yield) ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 53, in run_old_style_hookwrapper return result.get_result() ~~~~~~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_result.py", line 103, in get_result raise exc.with_traceback(tb) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 38, in run_old_style_hookwrapper res = yield ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/skipping.py", line 268, in pytest_runtest_call return (yield) ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 121, in _multicall res = hook_impl.function(*args) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 179, in pytest_runtest_call item.runtest() ~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/python.py", line 1720, in runtest self.ihook.pytest_pyfunc_call(pyfuncitem=self) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_hooks.py", line 512, in __call__ return self._hookexec(self.name, self._hookimpls.copy(), kwargs, firstresult) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_manager.py", line 120, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 167, in _multicall raise exception File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 53, in run_old_style_hookwrapper return result.get_result() ~~~~~~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_result.py", line 103, in get_result raise exc.with_traceback(tb) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 38, in run_old_style_hookwrapper res = yield ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 121, in _multicall res = hook_impl.function(*args) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/python.py", line 166, in pytest_pyfunc_call result = testfunction(**testargs) File "/home/odh/opendatahub-tests/tests/model_serving/model_runtime/triton/basic_model_deployment/test_tensorflow_model.py", line 97, in test_tensorflow_inference validate_inference_request( ~~~~~~~~~~~~~~~~~~~~~~~~~~^ pod_name=triton_pod_resource.name, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<5 lines>... root_dir=root_dir, ^^^^^^^^^^^^^^^^^^ ) ^ File "/home/odh/opendatahub-tests/tests/model_serving/model_runtime/triton/basic_model_deployment/utils.py", line 149, in validate_inference_request assert isinstance(response, dict), f"Response is not a dict: {response}" ~~~~~~~~~~^^^^^^^^^^^^^^^^ AssertionError: Response is not a dict: gRPC request (stdin) failed: STDOUT: STDERR: Failed to dial target host "localhost:9000": context deadline exceeded _ 5 of 9 completed, 4 Pass, 1 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/vllm/cpu/cpu_x86/test_vllm_cpu_s3_inference.py::TestVllmCpuX86S3Inference::test_vllm_cpu_x86_inference[facebook-opt-125m-raw-cpu] 2026-07-07T12:22:51.393761Z [info ] Elapsed time: 6.532669067382812e-05 [0:00:00.000065] [timeout_sampler]  -------------------------------- test_vllm_cpu_x86_inference[facebook-opt-125m-raw-cpu] -------------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:22:51.396514Z [info ] Executing session fixture: skip_if_no_supported_cpu_x86_accelerator_type [conftest] 2026-07-07T12:22:51.396681Z [info ] Executing session fixture: vllm_runtime_image [conftest] 2026-07-07T12:22:51.396835Z [info ] Executing session fixture: s3_models_storage_uri [conftest] 2026-07-07T12:22:51.396986Z [info ] Executing session fixture: registry_pull_secret [conftest] 2026-07-07T12:22:51.397134Z [info ] Executing session fixture: registry_host [conftest] 2026-07-07T12:22:51.397311Z [info ] Executing class fixture: model_namespace [conftest] 2026-07-07T12:22:51.397510Z [info ] Create Namespace opt-125m-raw-cpu [ocp_resources Namespace] 2026-07-07T12:22:51.397738Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Namespace', 'metadata': {'name': 'opt-125m-raw-cpu'}, 'spec': {}} [ocp_resources Namespace] 2026-07-07T12:22:51.457324Z [info ] Wait for Namespace opt-125m-raw-cpu status to be Active [ocp_resources Namespace] 2026-07-07T12:22:51.457503Z [info ] Waiting for 120 seconds [0:02:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:51.483104Z [info ] Status of Namespace opt-125m-raw-cpu is Active [ocp_resources Namespace] 2026-07-07T12:22:51.483322Z [info ] Elapsed time: 5.364418029785156e-05 [0:00:00.000054] [timeout_sampler] 2026-07-07T12:22:51.483467Z [info ] Executing class fixture: cpu_x86_serving_runtime [conftest] 2026-07-07T12:22:51.483596Z [info ] kind: Template api version: template.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:22:51.564467Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:22:51.564654Z [info ] Create ServingRuntime vllm-runtime [ocp_resources ServingRuntime] 2026-07-07T12:22:51.564817Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': 'v0.19.1', 'openshift.io/display-name': 'vLLM CPU (x86) ServingRuntime for KServe'}, 'labels': {'opendatahub.io/dashboard': 'true'}, 'name': 'vllm-runtime', 'namespace': 'opt-125m-raw-cpu'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'vllm', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8080'}, 'containers': [{'args': ['--port=8080', '--model=/mnt/models', '--served-model-name={{.Name}}'], 'command': ['python', '-m', 'vllm.entrypoints.openai.api_server'], 'env': [{'name': 'HF_HOME', 'value': '/tmp/hf_home'}], 'image': 'registry.redhat.io/rhaii-early-access/vllm-cpu-rhel9@sha256:139e070c2e4e2bc0254aa852b436c35ec2659e8424e228cc4c77a3bc2ddf50b6', 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}]}], 'multiModel': False, 'supportedModelFormats': [{'autoSelect': True, 'name': 'vLLM'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:22:51.638335Z [info ] Executing class fixture: kserve_endpoint_s3_secret [conftest] 2026-07-07T12:22:51.638506Z [info ] Create Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:22:51.638656Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Secret', 'metadata': {'name': 'models-bucket-secret', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-verifyssl': '0', 'serving.kserve.io/s3-usehttps': '1'}, 'namespace': 'opt-125m-raw-cpu'}, 'stringData': '*******'} [ocp_resources Secret] 2026-07-07T12:22:51.694308Z [info ] Wait until Secret models-bucket-secret is created [ocp_resources Secret] 2026-07-07T12:22:51.694465Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:22:51.715445Z [info ] Elapsed time: 5.125999450683594e-05 [0:00:00.000051] [timeout_sampler] 2026-07-07T12:22:51.715614Z [info ] Executing class fixture: vllm_model_service_account [conftest] 2026-07-07T12:22:51.715764Z [info ] Create ServiceAccount models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:22:51.715892Z [info ] Posting {'apiVersion': 'v1', 'kind': 'ServiceAccount', 'metadata': {'name': 'models-bucket-sa', 'namespace': 'opt-125m-raw-cpu'}, 'secrets': [{'name': 'models-bucket-secret'}]} [ocp_resources ServiceAccount] 2026-07-07T12:22:51.762092Z [info ] Executing class fixture: kserve_registry_pull_secret [conftest] 2026-07-07T12:22:51.762297Z [info ] Executing class fixture: cpu_x86_inference_service [conftest] 2026-07-07T12:22:51.784279Z [info ] kind: InferenceService api version: serving.kserve.io/v1beta1 [ocp_resources.resource] 2026-07-07T12:22:51.784457Z [info ] Create InferenceService opt-125m-raw-cpu [ocp_resources InferenceService] 2026-07-07T12:22:51.784615Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'name': 'opt-125m-raw-cpu', 'labels': {'networking.kserve.io/visibility': 'exposed'}, 'annotations': {'serving.kserve.io/deploymentMode': 'RawDeployment'}, 'namespace': 'opt-125m-raw-cpu'}, 'spec': {'predictor': {'model': {'modelFormat': {'name': 'vLLM'}, 'version': None, 'runtime': 'vllm-runtime', 'storageUri': 's3://ods-ci-wisdom/opt-125m/', 'args': ['--model=/mnt/models', '--uvicorn-log-level=debug', '--enforce-eager', '--max-model-len=256', '--max-num-seqs=20'], 'resources': {'requests': {'cpu': '8', 'memory': '10Gi'}, 'limits': {'cpu': '16', 'memory': '16Gi'}}, 'volumeMounts': [{'name': 'shared-memory', 'mountPath': '/dev/shm'}, {'name': 'tmp', 'mountPath': '/tmp'}, {'name': 'home', 'mountPath': '/home/vllm'}], 'env': [{'name': 'VLLM_CPU_KVCACHE_SPACE', 'value': '4'}, {'name': 'VLLM_WORKER_MULTIPROC_METHOD', 'value': 'spawn'}, {'name': 'OMP_NUM_THREADS', 'value': '8'}]}, 'minReplicas': 1, 'serviceAccountName': 'models-bucket-sa', 'volumes': [{'name': 'shared-memory', 'emptyDir': {'medium': 'Memory', 'sizeLimit': '32Gi'}}, {'name': 'tmp', 'emptyDir': {}}, {'name': 'home', 'emptyDir': {}}]}}} [ocp_resources InferenceService] 2026-07-07T12:22:51.897968Z [info ] Waiting for 30 seconds [0:00:30], retry every 1 seconds. (Function: utilities.infra.wait_for_isvc_pods Kwargs: {'client': , 'isvc': , 'runtime_name': 'vllm-runtime'}) [timeout_sampler] 2026-07-07T12:22:51.897300Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:22:52.941714Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:22:52.995705Z [info ] Elapsed time: 1.0445220470428467 [0:00:01.044522] [timeout_sampler] 2026-07-07T12:22:53.013147Z [info ] Verifying no failed pods  [utilities.infra] name=utilities.infra 2026-07-07T12:22:53.013834Z [info ] Waiting for 1199.9999985694885 seconds [0:19:59.999999], retry every 10 seconds. (Function: utilities.infra.get_pods_by_isvc_label Kwargs: {'client': , 'isvc': , 'runtime_name': 'vllm-runtime'}) [timeout_sampler] 2026-07-07T12:23:43.583885Z [info ] Elapsed time: 50.4746036529541 [0:00:50.474604] [timeout_sampler] 2026-07-07T12:23:43.604042Z [info ] Waiting for 1148.2939670085907 seconds [0:19:08.293967], retry every 5 seconds. (Function: ocp_resources.resource.get Kwargs: {'label_selector': 'serving.kserve.io/inferenceservice=opt-125m-raw-cpu', 'client': , 'namespace': 'opt-125m-raw-cpu'}) [timeout_sampler] 2026-07-07T12:23:43.623962Z [info ] Elapsed time: 0.0001475811004638672 [0:00:00.000148] [timeout_sampler] 2026-07-07T12:23:43.623218Z [info ] Waiting for inference deployment replicas to complete [utilities.infra] name=utilities.infra 2026-07-07T12:23:43.681231Z [info ] Waiting for 1148.216740846634 seconds [0:19:08.216741], retry every 5 seconds. (Function: utilities.infra..lambda: deployment.instance) [timeout_sampler] 2026-07-07T12:23:43.700297Z [info ] Elapsed time: 0.00011920928955078125 [0:00:00.000119] [timeout_sampler] 2026-07-07T12:23:43.700456Z [info ] Wait for Deployment opt-125m-raw-cpu-predictor to be deployed: True [ocp_resources Deployment] 2026-07-07T12:23:43.700577Z [info ] Waiting for 1148.1976161003113 seconds [0:19:08.197616], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.exists) [timeout_sampler] 2026-07-07T12:23:43.719974Z [info ] Elapsed time: 3.647804260253906e-05 [0:00:00.000036] [timeout_sampler] 2026-07-07T12:23:43.720218Z [info ] Waiting for 1148.1778645515442 seconds [0:19:08.177865], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.instance) [timeout_sampler] 2026-07-07T12:23:43.740027Z [info ] Elapsed time: 4.5299530029296875e-05 [0:00:00.000045] [timeout_sampler] 2026-07-07T12:23:43.740178Z [info ] Wait for InferenceService/opt-125m-raw-cpu's 'Ready' condition to be 'True' [ocp_resources InferenceService] 2026-07-07T12:23:43.740317Z [info ] Wait until InferenceService opt-125m-raw-cpu is created [ocp_resources InferenceService] 2026-07-07T12:23:43.740428Z [info ] Waiting for 1148.1578891277313 seconds [0:19:08.157889], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:23:43.760122Z [info ] Elapsed time: 4.315376281738281e-05 [0:00:00.000043] [timeout_sampler] 2026-07-07T12:23:43.760396Z [info ] Waiting for 1148.1377272605896 seconds [0:19:08.137727], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_condition.lambda: self.instance) [timeout_sampler] 2026-07-07T12:23:43.779272Z [info ] Elapsed time: 5.1975250244140625e-05 [0:00:00.000052] [timeout_sampler] 2026-07-07T12:23:43.798311Z [info ] Waiting for 1148.0994522571564 seconds [0:19:08.099452], retry every 5 seconds. (Function: utilities.inference_utils._is_model_loaded) [timeout_sampler] 2026-07-07T12:23:43.817564Z [info ] Elapsed time: 7.62939453125e-05 [0:00:00.000076] [timeout_sampler] 2026-07-07T12:23:43.837241Z [info ] Executing function fixture: skip_if_not_cpu_x86_raw_deployment [conftest] 2026-07-07T12:23:43.857109Z [info ] Executing function fixture: inference_request [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- 2026-07-07T12:23:43.895294Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:23:43.977177Z [info ] Sending completions request  [tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils] name=tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils payload={'model': 'opt-125m-raw-cpu', 'prompt': 'What is Kubernetes?', 'max_tokens': 50} url=https://opt-125m-raw-cpu-opt-125m-raw-cpu.apps.rosa.nmanos-konflux1.durx.p3.openshiftapps.com/v1/completions 2026-07-07T12:23:43.978672Z [info ] kind: Infrastructure api version: config.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:23:44.015021Z [info ] Infrastructure cluster resource tags: [{'key': 'api.openshift.com/environment', 'value': 'production'}, {'key': 'api.openshift.com/id', 'value': '2r2qdb90ltvhjc43lp6iqc6aqb7bgjda'}, {'key': 'api.openshift.com/legal-entity-id', 'value': '1pwwsfazToamNegaehP6eaDg80K'}, {'key': 'api.openshift.com/name', 'value': 'nmanos-konflux1'}, {'key': 'dns', 'value': 'external'}, {'key': 'red-hat-clustertype', 'value': 'rosa'}, {'key': 'red-hat-managed', 'value': 'true'}] [utilities.infra] name=utilities.infra 2026-07-07T12:23:44.015178Z [info ] Running on managed cluster, not using ca bundle [utilities.certificates_utils] name=utilities.certificates_utils PASSED2026-07-07T12:23:59.731927Z [info ] Completions response  [tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils] body_length=658 name=tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils status_code=200  TEST: TestVllmCpuX86S3Inference.test_vllm_cpu_x86_inference[facebook-opt-125m-raw-cpu] STATUS: PASSED ------------------------------------------------------- TEARDOWN ------------------------------------------------------- 2026-07-07T12:23:59.734992Z [info ] Delete InferenceService opt-125m-raw-cpu [ocp_resources InferenceService] 2026-07-07T12:23:59.783810Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'vLLM', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-07-07T12:22:51Z', 'finalizers': ['inferenceservice.finalizers', 'odh.inferenceservice.finalizers'], 'generation': 1, 'labels': {'networking.kserve.io/visibility': 'exposed'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/deploymentMode': {}}, 'f:labels': {'.': {}, 'f:networking.kserve.io/visibility': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:minReplicas': {}, 'f:model': {'.': {}, 'f:args': {}, 'f:env': {'.': {}, 'k:{"name":"OMP_NUM_THREADS"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"VLLM_CPU_KVCACHE_SPACE"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"VLLM_WORKER_MULTIPROC_METHOD"}': {'.': {}, 'f:name': {}, 'f:value': {}}}, 'f:modelFormat': {'.': {}, 'f:name': {}}, 'f:resources': {'.': {}, 'f:limits': {'.': {}, 'f:cpu': {}, 'f:memory': {}}, 'f:requests': {'.': {}, 'f:cpu': {}, 'f:memory': {}}}, 'f:runtime': {}, 'f:storageUri': {}, 'f:volumeMounts': {'.': {}, 'k:{"mountPath":"/dev/shm"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}, 'k:{"mountPath":"/home/vllm"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}, 'k:{"mountPath":"/tmp"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}}}, 'f:serviceAccountName': {}, 'f:volumes': {}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:22:51Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-07-07T12:22:52Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {'.': {}, 'f:url': {}}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}, 'f:totalCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-07-07T12:23:36Z'}], 'name': 'opt-125m-raw-cpu', 'namespace': 'opt-125m-raw-cpu', 'resourceVersion': '18737008', 'uid': '4a643413-8622-4654-a5a4-c07422e21cfd'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'minReplicas': 1, 'model': {'args': ['--model=/mnt/models', '--uvicorn-log-level=debug', '--enforce-eager', '--max-model-len=256', '--max-num-seqs=20'], 'env': [{'name': 'VLLM_CPU_KVCACHE_SPACE', 'value': '4'}, {'name': 'VLLM_WORKER_MULTIPROC_METHOD', 'value': 'spawn'}, {'name': 'OMP_NUM_THREADS', 'value': '8'}], 'modelFormat': {'name': 'vLLM'}, 'name': '', 'resources': {'limits': {'cpu': '16', 'memory': '16Gi'}, 'requests': {'cpu': '8', 'memory': '10Gi'}}, 'runtime': 'vllm-runtime', 'storageUri': 's3://ods-ci-wisdom/opt-125m/', 'volumeMounts': [{'mountPath': '/dev/shm', 'name': 'shared-memory'}, {'mountPath': '/tmp', 'name': 'tmp'}, {'mountPath': '/home/vllm', 'name': 'home'}]}, 'serviceAccountName': 'models-bucket-sa', 'volumes': [{'emptyDir': {'medium': 'Memory', 'sizeLimit': '32Gi'}, 'name': 'shared-memory'}, {'emptyDir': {}, 'name': 'tmp'}, {'emptyDir': {}, 'name': 'home'}]}}, 'status': {'address': {'url': 'http://opt-125m-raw-cpu-predictor.opt-125m-raw-cpu.svc.cluster.local:8080'}, 'components': {'predictor': {'url': 'http://opt-125m-raw-cpu-predictor-opt-125m-raw-cpu.example.com'}}, 'conditions': [{'lastTransitionTime': '2026-07-07T12:22:52Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-07-07T12:23:36Z', 'message': 'ReplicaSet "opt-125m-raw-cpu-predictor-5b46fcbc75" has successfully progressed.', 'reason': 'NewReplicaSetAvailable', 'status': 'True', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-07-07T12:23:36Z', 'status': 'True', 'type': 'Ready'}, {'lastTransitionTime': '2026-07-07T12:22:52Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0, 'totalCopies': 1}, 'states': {'activeModelState': 'Loaded', 'targetModelState': 'Loaded'}, 'transitionStatus': 'UpToDate'}, 'observedGeneration': 1, 'servingRuntimeName': 'vllm-runtime', 'url': 'https://opt-125m-raw-cpu-opt-125m-raw-cpu.apps.rosa.nmanos-konflux1.durx.p3.openshiftapps.com'}} [ocp_resources InferenceService] 2026-07-07T12:23:59.809764Z [info ] Wait until InferenceService opt-125m-raw-cpu is deleted [ocp_resources InferenceService] 2026-07-07T12:23:59.809930Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:24:00.847995Z [info ] Elapsed time: 1.018714189529419 [0:00:01.018714] [timeout_sampler] 2026-07-07T12:24:00.848160Z [info ] Delete ServingRuntime vllm-runtime [ocp_resources ServingRuntime] 2026-07-07T12:24:00.887556Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': 'v0.19.1', 'openshift.io/display-name': 'vLLM CPU (x86) ServingRuntime for KServe'}, 'creationTimestamp': '2026-07-07T12:22:51Z', 'generation': 1, 'labels': {'opendatahub.io/dashboard': 'true'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:opendatahub.io/runtime-version': {}, 'f:openshift.io/display-name': {}}, 'f:labels': {'.': {}, 'f:opendatahub.io/dashboard': {}}}, 'f:spec': {'.': {}, 'f:annotations': {'.': {}, 'f:opendatahub.io/kserve-runtime': {}, 'f:prometheus.io/path': {}, 'f:prometheus.io/port': {}}, 'f:containers': {}, 'f:multiModel': {}, 'f:supportedModelFormats': {}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:22:51Z'}], 'name': 'vllm-runtime', 'namespace': 'opt-125m-raw-cpu', 'resourceVersion': '18736189', 'uid': 'e085a38e-9c0e-4ba6-aa05-989f0551b396'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'vllm', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8080'}, 'containers': [{'args': ['--port=8080', '--model=/mnt/models', '--served-model-name={{.Name}}'], 'command': ['python', '-m', 'vllm.entrypoints.openai.api_server'], 'env': [{'name': 'HF_HOME', 'value': '/tmp/hf_home'}], 'image': 'registry.redhat.io/rhaii-early-access/vllm-cpu-rhel9@sha256:139e070c2e4e2bc0254aa852b436c35ec2659e8424e228cc4c77a3bc2ddf50b6', 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}]}], 'multiModel': False, 'supportedModelFormats': [{'autoSelect': True, 'name': 'vLLM'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:24:00.910416Z [info ] Wait until ServingRuntime vllm-runtime is deleted [ocp_resources ServingRuntime] 2026-07-07T12:24:00.910584Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:24:00.931814Z [info ] Elapsed time: 8.726119995117188e-05 [0:00:00.000087] [timeout_sampler] 2026-07-07T12:24:00.931971Z [info ] Delete ServiceAccount models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:24:00.969970Z [info ] Deleting {'kind': 'ServiceAccount', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-sa', 'namespace': 'opt-125m-raw-cpu', 'uid': '1fd70564-dd09-481c-9105-623441490755', 'resourceVersion': '18736208', 'creationTimestamp': '2026-07-07T12:22:51Z', 'annotations': {'openshift.io/internal-registry-pull-secret-ref': 'models-bucket-sa-dockercfg-lb499'}, 'managedFields': [{'manager': 'openshift.io/image-registry-pull-secrets_service-account-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:22:51Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:imagePullSecrets': {}, 'f:metadata': {'f:annotations': {'f:openshift.io/internal-registry-pull-secret-ref': {}}}, 'f:secrets': {'k:{"name":"models-bucket-sa-dockercfg-lb499"}': {}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:22:51Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:secrets': {'.': {}, 'k:{"name":"models-bucket-secret"}': {}}}}]}, 'secrets': [{'name': 'models-bucket-secret'}, {'name': 'models-bucket-sa-dockercfg-lb499'}], 'imagePullSecrets': [{'name': 'models-bucket-sa-dockercfg-lb499'}]} [ocp_resources ServiceAccount] 2026-07-07T12:24:00.993758Z [info ] Wait until ServiceAccount models-bucket-sa is deleted [ocp_resources ServiceAccount] 2026-07-07T12:24:00.993911Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:24:01.012469Z [info ] Elapsed time: 8.320808410644531e-05 [0:00:00.000083] [timeout_sampler] 2026-07-07T12:24:01.012597Z [info ] Delete Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:24:01.054410Z [info ] Deleting {'kind': 'Secret', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-secret', 'namespace': 'opt-125m-raw-cpu', 'uid': 'd70d4435-b1d5-47d9-aa1a-dbbb4940cda2', 'resourceVersion': '18736200', 'creationTimestamp': '2026-07-07T12:22:51Z', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-usehttps': '1', 'serving.kserve.io/s3-verifyssl': '0'}, 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:22:51Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:data': {'.': {}, 'f:AWS_ACCESS_KEY_ID': {}, 'f:AWS_SECRET_ACCESS_KEY': {}}, 'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/s3-endpoint': {}, 'f:serving.kserve.io/s3-region': {}, 'f:serving.kserve.io/s3-useanoncredential': {}, 'f:serving.kserve.io/s3-usehttps': {}, 'f:serving.kserve.io/s3-verifyssl': {}}}, 'f:type': {}}}]}, 'data': '*******', 'type': 'Opaque'} [ocp_resources Secret] 2026-07-07T12:24:01.084861Z [info ] Wait until Secret models-bucket-secret is deleted [ocp_resources Secret] 2026-07-07T12:24:01.085022Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:24:01.104768Z [info ] Elapsed time: 3.457069396972656e-05 [0:00:00.000035] [timeout_sampler] 2026-07-07T12:24:01.178330Z [info ] Delete Namespace opt-125m-raw-cpu [ocp_resources Namespace] 2026-07-07T12:24:01.217033Z [info ] Deleting {'kind': 'Namespace', 'apiVersion': 'v1', 'metadata': {'name': 'opt-125m-raw-cpu', 'uid': '556c1d58-8ea1-4fe7-b16e-38090d8c6d26', 'resourceVersion': '18736168', 'creationTimestamp': '2026-07-07T12:22:51Z', 'labels': {'kubernetes.io/metadata.name': 'opt-125m-raw-cpu', 'pod-security.kubernetes.io/audit': 'restricted', 'pod-security.kubernetes.io/audit-version': 'latest', 'pod-security.kubernetes.io/warn': 'restricted', 'pod-security.kubernetes.io/warn-version': 'latest'}, 'annotations': {'openshift.io/sa.scc.mcs': 's0:c32,c9', 'openshift.io/sa.scc.supplemental-groups': '1001010000/10000', 'openshift.io/sa.scc.uid-range': '1001010000/10000', 'security.openshift.io/MinimallySufficientPodSecurityStandard': 'restricted'}, 'managedFields': [{'manager': 'cluster-policy-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:22:51Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:openshift.io/sa.scc.mcs': {}, 'f:openshift.io/sa.scc.supplemental-groups': {}, 'f:openshift.io/sa.scc.uid-range': {}}}}}, {'manager': 'pod-security-admission-label-synchronization-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:22:51Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:security.openshift.io/MinimallySufficientPodSecurityStandard': {}}, 'f:labels': {'f:pod-security.kubernetes.io/audit': {}, 'f:pod-security.kubernetes.io/audit-version': {}, 'f:pod-security.kubernetes.io/warn': {}, 'f:pod-security.kubernetes.io/warn-version': {}}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:22:51Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:kubernetes.io/metadata.name': {}}}}}]}, 'spec': {'finalizers': ['kubernetes']}, 'status': {'phase': 'Active'}} [ocp_resources Namespace] 2026-07-07T12:24:01.244251Z [info ] Wait until Namespace opt-125m-raw-cpu is deleted [ocp_resources Namespace] 2026-07-07T12:24:01.244404Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] _ 6 of 9 completed, 5 Pass, 1 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/vllm/cpu/cpu_x86/test_vllm_cpu_s3_inference.py::TestVllmCpuX86S3Inference::test_vllm_cpu_x86_inference[tinyllama-1-1b-chat-raw-cpu] 2026-07-07T12:24:09.423234Z [info ] Elapsed time: 8.156286716461182 [0:00:08.156287] [timeout_sampler]  ------------------------------- test_vllm_cpu_x86_inference[tinyllama-1-1b-chat-raw-cpu] ------------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:24:09.423668Z [info ] Executing session fixture: s3_models_storage_uri [conftest] 2026-07-07T12:24:09.423786Z [info ] Executing class fixture: model_namespace [conftest] 2026-07-07T12:24:09.423900Z [info ] Create Namespace tinyllama-raw-cpu [ocp_resources Namespace] 2026-07-07T12:24:09.424016Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Namespace', 'metadata': {'name': 'tinyllama-raw-cpu'}, 'spec': {}} [ocp_resources Namespace] 2026-07-07T12:24:09.484914Z [info ] Wait for Namespace tinyllama-raw-cpu status to be Active [ocp_resources Namespace] 2026-07-07T12:24:09.485070Z [info ] Waiting for 120 seconds [0:02:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:24:09.515461Z [info ] Status of Namespace tinyllama-raw-cpu is Active [ocp_resources Namespace] 2026-07-07T12:24:09.515631Z [info ] Elapsed time: 6.508827209472656e-05 [0:00:00.000065] [timeout_sampler] 2026-07-07T12:24:09.515848Z [info ] Executing class fixture: cpu_x86_serving_runtime [conftest] 2026-07-07T12:24:09.515968Z [info ] kind: Template api version: template.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:24:09.574567Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:24:09.574731Z [info ] Create ServingRuntime vllm-runtime [ocp_resources ServingRuntime] 2026-07-07T12:24:09.574899Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': 'v0.19.1', 'openshift.io/display-name': 'vLLM CPU (x86) ServingRuntime for KServe'}, 'labels': {'opendatahub.io/dashboard': 'true'}, 'name': 'vllm-runtime', 'namespace': 'tinyllama-raw-cpu'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'vllm', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8080'}, 'containers': [{'args': ['--port=8080', '--model=/mnt/models', '--served-model-name={{.Name}}'], 'command': ['python', '-m', 'vllm.entrypoints.openai.api_server'], 'env': [{'name': 'HF_HOME', 'value': '/tmp/hf_home'}], 'image': 'registry.redhat.io/rhaii-early-access/vllm-cpu-rhel9@sha256:139e070c2e4e2bc0254aa852b436c35ec2659e8424e228cc4c77a3bc2ddf50b6', 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}]}], 'multiModel': False, 'supportedModelFormats': [{'autoSelect': True, 'name': 'vLLM'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:24:09.623897Z [info ] Executing class fixture: kserve_endpoint_s3_secret [conftest] 2026-07-07T12:24:09.624069Z [info ] Create Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:24:09.624306Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Secret', 'metadata': {'name': 'models-bucket-secret', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-verifyssl': '0', 'serving.kserve.io/s3-usehttps': '1'}, 'namespace': 'tinyllama-raw-cpu'}, 'stringData': '*******'} [ocp_resources Secret] 2026-07-07T12:24:09.669575Z [info ] Wait until Secret models-bucket-secret is created [ocp_resources Secret] 2026-07-07T12:24:09.669758Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:24:09.687865Z [info ] Elapsed time: 6.532669067382812e-05 [0:00:00.000065] [timeout_sampler] 2026-07-07T12:24:09.688035Z [info ] Executing class fixture: vllm_model_service_account [conftest] 2026-07-07T12:24:09.688211Z [info ] Create ServiceAccount models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:24:09.688418Z [info ] Posting {'apiVersion': 'v1', 'kind': 'ServiceAccount', 'metadata': {'name': 'models-bucket-sa', 'namespace': 'tinyllama-raw-cpu'}, 'secrets': [{'name': 'models-bucket-secret'}]} [ocp_resources ServiceAccount] 2026-07-07T12:24:09.731065Z [info ] Executing class fixture: kserve_registry_pull_secret [conftest] 2026-07-07T12:24:09.731268Z [info ] Executing class fixture: cpu_x86_inference_service [conftest] 2026-07-07T12:24:09.752604Z [info ] kind: InferenceService api version: serving.kserve.io/v1beta1 [ocp_resources.resource] 2026-07-07T12:24:09.752781Z [info ] Create InferenceService tinyllama-raw-cpu [ocp_resources InferenceService] 2026-07-07T12:24:09.752945Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'name': 'tinyllama-raw-cpu', 'labels': {'networking.kserve.io/visibility': 'exposed'}, 'annotations': {'serving.kserve.io/deploymentMode': 'RawDeployment'}, 'namespace': 'tinyllama-raw-cpu'}, 'spec': {'predictor': {'model': {'modelFormat': {'name': 'vLLM'}, 'version': None, 'runtime': 'vllm-runtime', 'storageUri': 's3://ods-ci-wisdom/TinyLlama/tinyllama-1.1b-chat-v1.0/', 'args': ['--model=/mnt/models', '--uvicorn-log-level=debug', '--enforce-eager', '--max-model-len=256', '--max-num-seqs=20'], 'resources': {'requests': {'cpu': '8', 'memory': '10Gi'}, 'limits': {'cpu': '16', 'memory': '16Gi'}}, 'volumeMounts': [{'name': 'shared-memory', 'mountPath': '/dev/shm'}, {'name': 'tmp', 'mountPath': '/tmp'}, {'name': 'home', 'mountPath': '/home/vllm'}], 'env': [{'name': 'VLLM_CPU_KVCACHE_SPACE', 'value': '4'}, {'name': 'VLLM_WORKER_MULTIPROC_METHOD', 'value': 'spawn'}, {'name': 'OMP_NUM_THREADS', 'value': '8'}]}, 'minReplicas': 1, 'serviceAccountName': 'models-bucket-sa', 'volumes': [{'name': 'shared-memory', 'emptyDir': {'medium': 'Memory', 'sizeLimit': '32Gi'}}, {'name': 'tmp', 'emptyDir': {}}, {'name': 'home', 'emptyDir': {}}]}}} [ocp_resources InferenceService] 2026-07-07T12:24:09.831949Z [info ] Waiting for 30 seconds [0:00:30], retry every 1 seconds. (Function: utilities.infra.wait_for_isvc_pods Kwargs: {'client': , 'isvc': , 'runtime_name': 'vllm-runtime'}) [timeout_sampler] 2026-07-07T12:24:09.831346Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:24:10.868925Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:24:10.924581Z [info ] Elapsed time: 1.037647008895874 [0:00:01.037647] [timeout_sampler] 2026-07-07T12:24:10.943419Z [info ] Verifying no failed pods  [utilities.infra] name=utilities.infra 2026-07-07T12:24:10.944131Z [info ] Waiting for 1199.999998807907 seconds [0:19:59.999999], retry every 10 seconds. (Function: utilities.infra.get_pods_by_isvc_label Kwargs: {'client': , 'isvc': , 'runtime_name': 'vllm-runtime'}) [timeout_sampler] 2026-07-07T12:25:01.517665Z [info ] Elapsed time: 50.48028087615967 [0:00:50.480281] [timeout_sampler] 2026-07-07T12:25:01.537930Z [info ] Waiting for 1148.293804883957 seconds [0:19:08.293805], retry every 5 seconds. (Function: ocp_resources.resource.get Kwargs: {'label_selector': 'serving.kserve.io/inferenceservice=tinyllama-raw-cpu', 'client': , 'namespace': 'tinyllama-raw-cpu'}) [timeout_sampler] 2026-07-07T12:25:01.557019Z [info ] Elapsed time: 6.246566772460938e-05 [0:00:00.000062] [timeout_sampler] 2026-07-07T12:25:01.556560Z [info ] Waiting for inference deployment replicas to complete [utilities.infra] name=utilities.infra 2026-07-07T12:25:01.614088Z [info ] Waiting for 1148.217585325241 seconds [0:19:08.217585], retry every 5 seconds. (Function: utilities.infra..lambda: deployment.instance) [timeout_sampler] 2026-07-07T12:25:01.633331Z [info ] Elapsed time: 6.008148193359375e-05 [0:00:00.000060] [timeout_sampler] 2026-07-07T12:25:01.633498Z [info ] Wait for Deployment tinyllama-raw-cpu-predictor to be deployed: True [ocp_resources Deployment] 2026-07-07T12:25:01.633653Z [info ] Waiting for 1148.1984686851501 seconds [0:19:08.198469], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:01.651720Z [info ] Elapsed time: 3.170967102050781e-05 [0:00:00.000032] [timeout_sampler] 2026-07-07T12:25:01.651886Z [info ] Waiting for 1148.18004322052 seconds [0:19:08.180043], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.instance) [timeout_sampler] 2026-07-07T12:25:01.670609Z [info ] Elapsed time: 4.696846008300781e-05 [0:00:00.000047] [timeout_sampler] 2026-07-07T12:25:01.670822Z [info ] Wait for InferenceService/tinyllama-raw-cpu's 'Ready' condition to be 'True' [ocp_resources InferenceService] 2026-07-07T12:25:01.671021Z [info ] Wait until InferenceService tinyllama-raw-cpu is created [ocp_resources InferenceService] 2026-07-07T12:25:01.671290Z [info ] Waiting for 1148.1611816883087 seconds [0:19:08.161182], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:01.689838Z [info ] Elapsed time: 3.0040740966796875e-05 [0:00:00.000030] [timeout_sampler] 2026-07-07T12:25:01.690021Z [info ] Waiting for 1148.1418244838715 seconds [0:19:08.141824], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_condition.lambda: self.instance) [timeout_sampler] 2026-07-07T12:25:01.708894Z [info ] Elapsed time: 3.24249267578125e-05 [0:00:00.000032] [timeout_sampler] 2026-07-07T12:25:01.728827Z [info ] Waiting for 1148.1027102470398 seconds [0:19:08.102710], retry every 5 seconds. (Function: utilities.inference_utils._is_model_loaded) [timeout_sampler] 2026-07-07T12:25:01.747502Z [info ] Elapsed time: 4.6253204345703125e-05 [0:00:00.000046] [timeout_sampler] 2026-07-07T12:25:01.766755Z [info ] Executing function fixture: skip_if_not_cpu_x86_raw_deployment [conftest] 2026-07-07T12:25:01.786422Z [info ] Executing function fixture: inference_request [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- 2026-07-07T12:25:01.824292Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:25:01.904239Z [info ] Sending chat completions request [tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils] name=tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils payload={'model': 'tinyllama-raw-cpu', 'messages': [{'role': 'user', 'content': 'What is the capital of Italy?'}], 'max_tokens': 50} url=https://tinyllama-raw-cpu-tinyllama-raw-cpu.apps.rosa.nmanos-konflux1.durx.p3.openshiftapps.com/v1/chat/completions PASSED2026-07-07T12:25:20.732740Z [info ] Chat completions response  [tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils] body_length=764 name=tests.model_serving.model_runtime.vllm.cpu.cpu_x86.utils status_code=200  TEST: TestVllmCpuX86S3Inference.test_vllm_cpu_x86_inference[tinyllama-1-1b-chat-raw-cpu] STATUS: PASSED ------------------------------------------------------- TEARDOWN ------------------------------------------------------- 2026-07-07T12:25:20.741954Z [info ] Delete InferenceService tinyllama-raw-cpu [ocp_resources InferenceService] 2026-07-07T12:25:20.808034Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'vLLM', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-07-07T12:24:09Z', 'finalizers': ['inferenceservice.finalizers', 'odh.inferenceservice.finalizers'], 'generation': 1, 'labels': {'networking.kserve.io/visibility': 'exposed'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/deploymentMode': {}}, 'f:labels': {'.': {}, 'f:networking.kserve.io/visibility': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:minReplicas': {}, 'f:model': {'.': {}, 'f:args': {}, 'f:env': {'.': {}, 'k:{"name":"OMP_NUM_THREADS"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"VLLM_CPU_KVCACHE_SPACE"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"VLLM_WORKER_MULTIPROC_METHOD"}': {'.': {}, 'f:name': {}, 'f:value': {}}}, 'f:modelFormat': {'.': {}, 'f:name': {}}, 'f:resources': {'.': {}, 'f:limits': {'.': {}, 'f:cpu': {}, 'f:memory': {}}, 'f:requests': {'.': {}, 'f:cpu': {}, 'f:memory': {}}}, 'f:runtime': {}, 'f:storageUri': {}, 'f:volumeMounts': {'.': {}, 'k:{"mountPath":"/dev/shm"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}, 'k:{"mountPath":"/home/vllm"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}, 'k:{"mountPath":"/tmp"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}}}, 'f:serviceAccountName': {}, 'f:volumes': {}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:24:09Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-07-07T12:24:10Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {'.': {}, 'f:url': {}}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}, 'f:totalCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-07-07T12:24:59Z'}], 'name': 'tinyllama-raw-cpu', 'namespace': 'tinyllama-raw-cpu', 'resourceVersion': '18738591', 'uid': '40c1d25d-d8c9-45bf-8240-1bd0d02817cc'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'minReplicas': 1, 'model': {'args': ['--model=/mnt/models', '--uvicorn-log-level=debug', '--enforce-eager', '--max-model-len=256', '--max-num-seqs=20'], 'env': [{'name': 'VLLM_CPU_KVCACHE_SPACE', 'value': '4'}, {'name': 'VLLM_WORKER_MULTIPROC_METHOD', 'value': 'spawn'}, {'name': 'OMP_NUM_THREADS', 'value': '8'}], 'modelFormat': {'name': 'vLLM'}, 'name': '', 'resources': {'limits': {'cpu': '16', 'memory': '16Gi'}, 'requests': {'cpu': '8', 'memory': '10Gi'}}, 'runtime': 'vllm-runtime', 'storageUri': 's3://ods-ci-wisdom/TinyLlama/tinyllama-1.1b-chat-v1.0/', 'volumeMounts': [{'mountPath': '/dev/shm', 'name': 'shared-memory'}, {'mountPath': '/tmp', 'name': 'tmp'}, {'mountPath': '/home/vllm', 'name': 'home'}]}, 'serviceAccountName': 'models-bucket-sa', 'volumes': [{'emptyDir': {'medium': 'Memory', 'sizeLimit': '32Gi'}, 'name': 'shared-memory'}, {'emptyDir': {}, 'name': 'tmp'}, {'emptyDir': {}, 'name': 'home'}]}}, 'status': {'address': {'url': 'http://tinyllama-raw-cpu-predictor.tinyllama-raw-cpu.svc.cluster.local:8080'}, 'components': {'predictor': {'url': 'http://tinyllama-raw-cpu-predictor-tinyllama-raw-cpu.example.com'}}, 'conditions': [{'lastTransitionTime': '2026-07-07T12:24:10Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-07-07T12:24:59Z', 'message': 'ReplicaSet "tinyllama-raw-cpu-predictor-5c955f5549" has successfully progressed.', 'reason': 'NewReplicaSetAvailable', 'status': 'True', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-07-07T12:24:59Z', 'status': 'True', 'type': 'Ready'}, {'lastTransitionTime': '2026-07-07T12:24:10Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0, 'totalCopies': 1}, 'states': {'activeModelState': 'Loaded', 'targetModelState': 'Loaded'}, 'transitionStatus': 'UpToDate'}, 'observedGeneration': 1, 'servingRuntimeName': 'vllm-runtime', 'url': 'https://tinyllama-raw-cpu-tinyllama-raw-cpu.apps.rosa.nmanos-konflux1.durx.p3.openshiftapps.com'}} [ocp_resources InferenceService] 2026-07-07T12:25:20.835336Z [info ] Wait until InferenceService tinyllama-raw-cpu is deleted [ocp_resources InferenceService] 2026-07-07T12:25:20.835478Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:21.874637Z [info ] Elapsed time: 1.0188384056091309 [0:00:01.018838] [timeout_sampler] 2026-07-07T12:25:21.874864Z [info ] Delete ServingRuntime vllm-runtime [ocp_resources ServingRuntime] 2026-07-07T12:25:21.913822Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': 'v0.19.1', 'openshift.io/display-name': 'vLLM CPU (x86) ServingRuntime for KServe'}, 'creationTimestamp': '2026-07-07T12:24:09Z', 'generation': 1, 'labels': {'opendatahub.io/dashboard': 'true'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:opendatahub.io/runtime-version': {}, 'f:openshift.io/display-name': {}}, 'f:labels': {'.': {}, 'f:opendatahub.io/dashboard': {}}}, 'f:spec': {'.': {}, 'f:annotations': {'.': {}, 'f:opendatahub.io/kserve-runtime': {}, 'f:prometheus.io/path': {}, 'f:prometheus.io/port': {}}, 'f:containers': {}, 'f:multiModel': {}, 'f:supportedModelFormats': {}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:24:09Z'}], 'name': 'vllm-runtime', 'namespace': 'tinyllama-raw-cpu', 'resourceVersion': '18737658', 'uid': '68085deb-7fbc-4f3e-929f-c3d311486855'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'vllm', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8080'}, 'containers': [{'args': ['--port=8080', '--model=/mnt/models', '--served-model-name={{.Name}}'], 'command': ['python', '-m', 'vllm.entrypoints.openai.api_server'], 'env': [{'name': 'HF_HOME', 'value': '/tmp/hf_home'}], 'image': 'registry.redhat.io/rhaii-early-access/vllm-cpu-rhel9@sha256:139e070c2e4e2bc0254aa852b436c35ec2659e8424e228cc4c77a3bc2ddf50b6', 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}]}], 'multiModel': False, 'supportedModelFormats': [{'autoSelect': True, 'name': 'vLLM'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:25:21.934829Z [info ] Wait until ServingRuntime vllm-runtime is deleted [ocp_resources ServingRuntime] 2026-07-07T12:25:21.934966Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:21.954360Z [info ] Elapsed time: 4.1961669921875e-05 [0:00:00.000042] [timeout_sampler] 2026-07-07T12:25:21.954566Z [info ] Delete ServiceAccount models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:25:21.992014Z [info ] Deleting {'kind': 'ServiceAccount', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-sa', 'namespace': 'tinyllama-raw-cpu', 'uid': 'a0202df2-1e23-4706-85fb-546096501ce9', 'resourceVersion': '18737671', 'creationTimestamp': '2026-07-07T12:24:09Z', 'annotations': {'openshift.io/internal-registry-pull-secret-ref': 'models-bucket-sa-dockercfg-585z8'}, 'managedFields': [{'manager': 'openshift.io/image-registry-pull-secrets_service-account-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:24:09Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:imagePullSecrets': {}, 'f:metadata': {'f:annotations': {'f:openshift.io/internal-registry-pull-secret-ref': {}}}, 'f:secrets': {'k:{"name":"models-bucket-sa-dockercfg-585z8"}': {}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:24:09Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:secrets': {'.': {}, 'k:{"name":"models-bucket-secret"}': {}}}}]}, 'secrets': [{'name': 'models-bucket-secret'}, {'name': 'models-bucket-sa-dockercfg-585z8'}], 'imagePullSecrets': [{'name': 'models-bucket-sa-dockercfg-585z8'}]} [ocp_resources ServiceAccount] 2026-07-07T12:25:22.014565Z [info ] Wait until ServiceAccount models-bucket-sa is deleted [ocp_resources ServiceAccount] 2026-07-07T12:25:22.014698Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:22.034762Z [info ] Elapsed time: 3.790855407714844e-05 [0:00:00.000038] [timeout_sampler] 2026-07-07T12:25:22.034926Z [info ] Delete Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:25:22.077041Z [info ] Deleting {'kind': 'Secret', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-secret', 'namespace': 'tinyllama-raw-cpu', 'uid': 'af01f6cb-5fc8-4b3a-82e3-e341805adf9b', 'resourceVersion': '18737664', 'creationTimestamp': '2026-07-07T12:24:09Z', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-usehttps': '1', 'serving.kserve.io/s3-verifyssl': '0'}, 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:24:09Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:data': {'.': {}, 'f:AWS_ACCESS_KEY_ID': {}, 'f:AWS_SECRET_ACCESS_KEY': {}}, 'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/s3-endpoint': {}, 'f:serving.kserve.io/s3-region': {}, 'f:serving.kserve.io/s3-useanoncredential': {}, 'f:serving.kserve.io/s3-usehttps': {}, 'f:serving.kserve.io/s3-verifyssl': {}}}, 'f:type': {}}}]}, 'data': '*******', 'type': 'Opaque'} [ocp_resources Secret] 2026-07-07T12:25:22.103815Z [info ] Wait until Secret models-bucket-secret is deleted [ocp_resources Secret] 2026-07-07T12:25:22.103958Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:22.122749Z [info ] Elapsed time: 4.100799560546875e-05 [0:00:00.000041] [timeout_sampler] 2026-07-07T12:25:22.194227Z [info ] Delete Namespace tinyllama-raw-cpu [ocp_resources Namespace] 2026-07-07T12:25:22.232654Z [info ] Deleting {'kind': 'Namespace', 'apiVersion': 'v1', 'metadata': {'name': 'tinyllama-raw-cpu', 'uid': '27777729-e156-4d76-8145-3bb9c39af5a2', 'resourceVersion': '18737639', 'creationTimestamp': '2026-07-07T12:24:09Z', 'labels': {'kubernetes.io/metadata.name': 'tinyllama-raw-cpu', 'pod-security.kubernetes.io/audit': 'restricted', 'pod-security.kubernetes.io/audit-version': 'latest', 'pod-security.kubernetes.io/warn': 'restricted', 'pod-security.kubernetes.io/warn-version': 'latest'}, 'annotations': {'openshift.io/sa.scc.mcs': 's0:c32,c14', 'openshift.io/sa.scc.supplemental-groups': '1001020000/10000', 'openshift.io/sa.scc.uid-range': '1001020000/10000', 'security.openshift.io/MinimallySufficientPodSecurityStandard': 'restricted'}, 'managedFields': [{'manager': 'cluster-policy-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:24:09Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:openshift.io/sa.scc.mcs': {}, 'f:openshift.io/sa.scc.supplemental-groups': {}, 'f:openshift.io/sa.scc.uid-range': {}}}}}, {'manager': 'pod-security-admission-label-synchronization-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:24:09Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:security.openshift.io/MinimallySufficientPodSecurityStandard': {}}, 'f:labels': {'f:pod-security.kubernetes.io/audit': {}, 'f:pod-security.kubernetes.io/audit-version': {}, 'f:pod-security.kubernetes.io/warn': {}, 'f:pod-security.kubernetes.io/warn-version': {}}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:24:09Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:kubernetes.io/metadata.name': {}}}}}]}, 'spec': {'finalizers': ['kubernetes']}, 'status': {'phase': 'Active'}} [ocp_resources Namespace] 2026-07-07T12:25:22.261540Z [info ] Wait until Namespace tinyllama-raw-cpu is deleted [ocp_resources Namespace] 2026-07-07T12:25:22.261725Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] _ 7 of 9 completed, 6 Pass, 1 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/vllm/probes/test_vllm_probes.py::TestVllmProbeHealth::test_vllm_readiness_probe[test_vllm_opt_125m_raw_cpu_probes] 2026-07-07T12:25:31.476326Z [info ] Elapsed time: 9.172627449035645 [0:00:09.172627] [timeout_sampler]  ----------------------------- test_vllm_readiness_probe[test_vllm_opt_125m_raw_cpu_probes] ----------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:25:31.478868Z [info ] Executing session fixture: s3_models_storage_uri [conftest] 2026-07-07T12:25:31.479031Z [info ] Executing class fixture: model_namespace [conftest] 2026-07-07T12:25:31.479214Z [info ] Create Namespace opt-125m-probes [ocp_resources Namespace] 2026-07-07T12:25:31.479512Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Namespace', 'metadata': {'name': 'opt-125m-probes'}, 'spec': {}} [ocp_resources Namespace] 2026-07-07T12:25:31.542126Z [info ] Wait for Namespace opt-125m-probes status to be Active [ocp_resources Namespace] 2026-07-07T12:25:31.542342Z [info ] Waiting for 120 seconds [0:02:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_status.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:31.572967Z [info ] Status of Namespace opt-125m-probes is Active [ocp_resources Namespace] 2026-07-07T12:25:31.573137Z [info ] Elapsed time: 4.649162292480469e-05 [0:00:00.000046] [timeout_sampler] 2026-07-07T12:25:31.573380Z [info ] Executing class fixture: probes_serving_runtime [conftest] 2026-07-07T12:25:31.573497Z [info ] kind: Template api version: template.openshift.io/v1 [ocp_resources.resource] 2026-07-07T12:25:31.665902Z [info ] kind: ServingRuntime api version: serving.kserve.io/v1alpha1 [ocp_resources.resource] 2026-07-07T12:25:31.666089Z [info ] Create ServingRuntime vllm-runtime [ocp_resources ServingRuntime] 2026-07-07T12:25:31.666303Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': 'v0.19.1', 'openshift.io/display-name': 'vLLM CPU (x86) ServingRuntime for KServe'}, 'labels': {'opendatahub.io/dashboard': 'true'}, 'name': 'vllm-runtime', 'namespace': 'opt-125m-probes'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'vllm', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8080'}, 'containers': [{'args': ['--port=8080', '--model=/mnt/models', '--served-model-name={{.Name}}'], 'command': ['python', '-m', 'vllm.entrypoints.openai.api_server'], 'env': [{'name': 'HF_HOME', 'value': '/tmp/hf_home'}], 'image': 'registry.redhat.io/rhaii-early-access/vllm-cpu-rhel9@sha256:139e070c2e4e2bc0254aa852b436c35ec2659e8424e228cc4c77a3bc2ddf50b6', 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}], 'readinessProbe': {'httpGet': {'path': '/health', 'port': 8080, 'scheme': 'HTTP'}, 'initialDelaySeconds': 120, 'periodSeconds': 10, 'timeoutSeconds': 10, 'failureThreshold': 12}, 'livenessProbe': {'httpGet': {'path': '/health', 'port': 8080, 'scheme': 'HTTP'}, 'initialDelaySeconds': 180, 'periodSeconds': 30, 'timeoutSeconds': 10, 'failureThreshold': 10}}], 'multiModel': False, 'supportedModelFormats': [{'autoSelect': True, 'name': 'vLLM'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:25:31.736518Z [info ] Executing class fixture: kserve_endpoint_s3_secret [conftest] 2026-07-07T12:25:31.736688Z [info ] Create Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:25:31.736858Z [info ] Posting {'apiVersion': 'v1', 'kind': 'Secret', 'metadata': {'name': 'models-bucket-secret', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-verifyssl': '0', 'serving.kserve.io/s3-usehttps': '1'}, 'namespace': 'opt-125m-probes'}, 'stringData': '*******'} [ocp_resources Secret] 2026-07-07T12:25:31.814408Z [info ] Wait until Secret models-bucket-secret is created [ocp_resources Secret] 2026-07-07T12:25:31.814557Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:25:31.847893Z [info ] Elapsed time: 4.458427429199219e-05 [0:00:00.000045] [timeout_sampler] 2026-07-07T12:25:31.848055Z [info ] Executing class fixture: vllm_model_service_account [conftest] 2026-07-07T12:25:31.848227Z [info ] Create ServiceAccount models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:25:31.848401Z [info ] Posting {'apiVersion': 'v1', 'kind': 'ServiceAccount', 'metadata': {'name': 'models-bucket-sa', 'namespace': 'opt-125m-probes'}, 'secrets': [{'name': 'models-bucket-secret'}]} [ocp_resources ServiceAccount] 2026-07-07T12:25:31.901420Z [info ] Executing class fixture: kserve_registry_pull_secret [conftest] 2026-07-07T12:25:31.902123Z [info ] Executing class fixture: vllm_probes_inference_service [conftest] 2026-07-07T12:25:31.925937Z [info ] kind: InferenceService api version: serving.kserve.io/v1beta1 [ocp_resources.resource] 2026-07-07T12:25:31.926094Z [info ] Create InferenceService opt-125m-probes [ocp_resources InferenceService] 2026-07-07T12:25:31.926276Z [info ] Posting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'name': 'opt-125m-probes', 'labels': {'networking.kserve.io/visibility': 'exposed'}, 'annotations': {'serving.kserve.io/deploymentMode': 'RawDeployment'}, 'namespace': 'opt-125m-probes'}, 'spec': {'predictor': {'model': {'modelFormat': {'name': 'vLLM'}, 'version': None, 'runtime': 'vllm-runtime', 'storageUri': 's3://ods-ci-wisdom/opt-125m/', 'args': ['--model=/mnt/models', '--uvicorn-log-level=debug', '--enforce-eager', '--max-model-len=256', '--max-num-seqs=20'], 'resources': {'requests': {'cpu': '8', 'memory': '10Gi'}, 'limits': {'cpu': '16', 'memory': '16Gi'}}, 'volumeMounts': [{'name': 'shared-memory', 'mountPath': '/dev/shm'}, {'name': 'tmp', 'mountPath': '/tmp'}, {'name': 'home', 'mountPath': '/home/vllm'}], 'env': [{'name': 'VLLM_CPU_KVCACHE_SPACE', 'value': '4'}, {'name': 'VLLM_WORKER_MULTIPROC_METHOD', 'value': 'spawn'}, {'name': 'OMP_NUM_THREADS', 'value': '8'}]}, 'minReplicas': 1, 'serviceAccountName': 'models-bucket-sa', 'volumes': [{'name': 'shared-memory', 'emptyDir': {'medium': 'Memory', 'sizeLimit': '32Gi'}}, {'name': 'tmp', 'emptyDir': {}}, {'name': 'home', 'emptyDir': {}}]}}} [ocp_resources InferenceService] 2026-07-07T12:25:32.039750Z [info ] Waiting for 30 seconds [0:00:30], retry every 1 seconds. (Function: utilities.infra.wait_for_isvc_pods Kwargs: {'client': , 'isvc': , 'runtime_name': 'vllm-runtime'}) [timeout_sampler] 2026-07-07T12:25:32.038041Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:25:33.091831Z [info ] Waiting for pods to be created [utilities.infra] name=utilities.infra 2026-07-07T12:25:33.145899Z [info ] Elapsed time: 1.0539131164550781 [0:00:01.053913] [timeout_sampler] 2026-07-07T12:25:33.164152Z [info ] Verifying no failed pods  [utilities.infra] name=utilities.infra 2026-07-07T12:25:33.165041Z [info ] Waiting for 1199.999998807907 seconds [0:19:59.999999], retry every 10 seconds. (Function: utilities.infra.get_pods_by_isvc_label Kwargs: {'client': , 'isvc': , 'runtime_name': 'vllm-runtime'}) [timeout_sampler] 2026-07-07T12:27:54.589423Z [info ] Elapsed time: 141.33235669136047 [0:02:21.332357] [timeout_sampler] 2026-07-07T12:27:54.608893Z [info ] Waiting for 1057.429574728012 seconds [0:17:37.429575], retry every 5 seconds. (Function: ocp_resources.resource.get Kwargs: {'label_selector': 'serving.kserve.io/inferenceservice=opt-125m-probes', 'client': , 'namespace': 'opt-125m-probes'}) [timeout_sampler] 2026-07-07T12:27:54.628475Z [info ] Elapsed time: 8.153915405273438e-05 [0:00:00.000082] [timeout_sampler] 2026-07-07T12:27:54.627977Z [info ] Waiting for inference deployment replicas to complete [utilities.infra] name=utilities.infra 2026-07-07T12:27:54.685040Z [info ] Waiting for 1057.353500366211 seconds [0:17:37.353500], retry every 5 seconds. (Function: utilities.infra..lambda: deployment.instance) [timeout_sampler] 2026-07-07T12:27:54.704415Z [info ] Elapsed time: 0.0001347064971923828 [0:00:00.000135] [timeout_sampler] 2026-07-07T12:27:54.704579Z [info ] Wait for Deployment opt-125m-probes-predictor to be deployed: True [ocp_resources Deployment] 2026-07-07T12:27:54.704737Z [info ] Waiting for 1057.333862543106 seconds [0:17:37.333863], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.exists) [timeout_sampler] 2026-07-07T12:27:54.724060Z [info ] Elapsed time: 3.409385681152344e-05 [0:00:00.000034] [timeout_sampler] 2026-07-07T12:27:54.724298Z [info ] Waiting for 1057.3143303394318 seconds [0:17:37.314330], retry every 1 seconds. (Function: ocp_resources.deployment.wait_for_replicas.lambda: self.instance) [timeout_sampler] 2026-07-07T12:27:54.743018Z [info ] Elapsed time: 4.5299530029296875e-05 [0:00:00.000045] [timeout_sampler] 2026-07-07T12:27:54.743258Z [info ] Wait for InferenceService/opt-125m-probes's 'Ready' condition to be 'True' [ocp_resources InferenceService] 2026-07-07T12:27:54.743391Z [info ] Wait until InferenceService opt-125m-probes is created [ocp_resources InferenceService] 2026-07-07T12:27:54.743530Z [info ] Waiting for 1057.2953124046326 seconds [0:17:37.295312], retry every 1 seconds. (Function: ocp_resources.resource.wait.lambda: self.exists) [timeout_sampler] 2026-07-07T12:27:54.761828Z [info ] Elapsed time: 3.0279159545898438e-05 [0:00:00.000030] [timeout_sampler] 2026-07-07T12:27:54.761989Z [info ] Waiting for 1057.2765197753906 seconds [0:17:37.276520], retry every 1 seconds. (Function: ocp_resources.resource.wait_for_condition.lambda: self.instance) [timeout_sampler] 2026-07-07T12:27:54.781276Z [info ] Elapsed time: 5.412101745605469e-05 [0:00:00.000054] [timeout_sampler] 2026-07-07T12:27:54.800700Z [info ] Waiting for 1057.2376444339752 seconds [0:17:37.237644], retry every 5 seconds. (Function: utilities.inference_utils._is_model_loaded) [timeout_sampler] 2026-07-07T12:27:54.819415Z [info ] Elapsed time: 8.654594421386719e-05 [0:00:00.000087] [timeout_sampler] 2026-07-07T12:27:54.838423Z [info ] Executing function fixture: skip_if_not_probes_raw_deployment [conftest] 2026-07-07T12:27:54.857170Z [info ] Executing function fixture: vllm_probes_pod_resource [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- 2026-07-07T12:27:54.954083Z [info ] Execute ['curl', '-s', '-o', '/dev/null', '-w', '%{http_code}', '--max-time', '15', 'http://localhost:8080/health'] on opt-125m-probes-predictor-75d4c45cc7-4s22x (ip-10-0-1-76.us-east-2.compute.internal) [ocp_resources Pod] PASSED _ 8 of 9 completed, 7 Pass, 1 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ tests/model_serving/model_runtime/vllm/probes/test_vllm_probes.py::TestVllmProbeHealth::test_vllm_liveness_probe[test_vllm_opt_125m_raw_cpu_probes]  TEST: TestVllmProbeHealth.test_vllm_readiness_probe[test_vllm_opt_125m_raw_cpu_probes] STATUS: PASSED ------------------------------------------------------- TEARDOWN -------------------------------------------------------  ----------------------------- test_vllm_liveness_probe[test_vllm_opt_125m_raw_cpu_probes] ----------------------------- -------------------------------------------------------- SETUP -------------------------------------------------------- 2026-07-07T12:27:55.104136Z [info ] Executing function fixture: skip_if_not_probes_raw_deployment [conftest] 2026-07-07T12:27:55.123213Z [info ] Executing function fixture: vllm_probes_pod_resource [conftest] --------------------------------------------------------- CALL --------------------------------------------------------- PASSED TEST: TestVllmProbeHealth.test_vllm_liveness_probe[test_vllm_opt_125m_raw_cpu_probes] STATUS: PASSED ------------------------------------------------------- TEARDOWN ------------------------------------------------------- 2026-07-07T12:27:55.350692Z [info ] Delete InferenceService opt-125m-probes [ocp_resources InferenceService] 2026-07-07T12:27:55.394718Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'vLLM', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-07-07T12:25:31Z', 'finalizers': ['inferenceservice.finalizers', 'odh.inferenceservice.finalizers'], 'generation': 1, 'labels': {'networking.kserve.io/visibility': 'exposed'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/deploymentMode': {}}, 'f:labels': {'.': {}, 'f:networking.kserve.io/visibility': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:minReplicas': {}, 'f:model': {'.': {}, 'f:args': {}, 'f:env': {'.': {}, 'k:{"name":"OMP_NUM_THREADS"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"VLLM_CPU_KVCACHE_SPACE"}': {'.': {}, 'f:name': {}, 'f:value': {}}, 'k:{"name":"VLLM_WORKER_MULTIPROC_METHOD"}': {'.': {}, 'f:name': {}, 'f:value': {}}}, 'f:modelFormat': {'.': {}, 'f:name': {}}, 'f:resources': {'.': {}, 'f:limits': {'.': {}, 'f:cpu': {}, 'f:memory': {}}, 'f:requests': {'.': {}, 'f:cpu': {}, 'f:memory': {}}}, 'f:runtime': {}, 'f:storageUri': {}, 'f:volumeMounts': {'.': {}, 'k:{"mountPath":"/dev/shm"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}, 'k:{"mountPath":"/home/vllm"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}, 'k:{"mountPath":"/tmp"}': {'.': {}, 'f:mountPath': {}, 'f:name': {}}}}, 'f:serviceAccountName': {}, 'f:volumes': {}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:25:31Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-07-07T12:25:32Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {'.': {}, 'f:url': {}}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}, 'f:totalCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-07-07T12:27:47Z'}], 'name': 'opt-125m-probes', 'namespace': 'opt-125m-probes', 'resourceVersion': '18741501', 'uid': 'd1775ca9-6d59-4215-a9e3-9a9f5ea0f738'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'minReplicas': 1, 'model': {'args': ['--model=/mnt/models', '--uvicorn-log-level=debug', '--enforce-eager', '--max-model-len=256', '--max-num-seqs=20'], 'env': [{'name': 'VLLM_CPU_KVCACHE_SPACE', 'value': '4'}, {'name': 'VLLM_WORKER_MULTIPROC_METHOD', 'value': 'spawn'}, {'name': 'OMP_NUM_THREADS', 'value': '8'}], 'modelFormat': {'name': 'vLLM'}, 'name': '', 'resources': {'limits': {'cpu': '16', 'memory': '16Gi'}, 'requests': {'cpu': '8', 'memory': '10Gi'}}, 'runtime': 'vllm-runtime', 'storageUri': 's3://ods-ci-wisdom/opt-125m/', 'volumeMounts': [{'mountPath': '/dev/shm', 'name': 'shared-memory'}, {'mountPath': '/tmp', 'name': 'tmp'}, {'mountPath': '/home/vllm', 'name': 'home'}]}, 'serviceAccountName': 'models-bucket-sa', 'volumes': [{'emptyDir': {'medium': 'Memory', 'sizeLimit': '32Gi'}, 'name': 'shared-memory'}, {'emptyDir': {}, 'name': 'tmp'}, {'emptyDir': {}, 'name': 'home'}]}}, 'status': {'address': {'url': 'http://opt-125m-probes-predictor.opt-125m-probes.svc.cluster.local:8080'}, 'components': {'predictor': {'url': 'http://opt-125m-probes-predictor-opt-125m-probes.example.com'}}, 'conditions': [{'lastTransitionTime': '2026-07-07T12:25:32Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-07-07T12:27:47Z', 'message': 'ReplicaSet "opt-125m-probes-predictor-75d4c45cc7" has successfully progressed.', 'reason': 'NewReplicaSetAvailable', 'status': 'True', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-07-07T12:27:47Z', 'status': 'True', 'type': 'Ready'}, {'lastTransitionTime': '2026-07-07T12:25:32Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0, 'totalCopies': 1}, 'states': {'activeModelState': 'Loaded', 'targetModelState': 'Loaded'}, 'transitionStatus': 'UpToDate'}, 'observedGeneration': 1, 'servingRuntimeName': 'vllm-runtime', 'url': 'https://opt-125m-probes-opt-125m-probes.apps.rosa.nmanos-konflux1.durx.p3.openshiftapps.com'}} [ocp_resources InferenceService] 2026-07-07T12:27:55.420383Z [info ] Wait until InferenceService opt-125m-probes is deleted [ocp_resources InferenceService] 2026-07-07T12:27:55.420538Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:27:56.459021Z [info ] Elapsed time: 1.0184495449066162 [0:00:01.018450] [timeout_sampler] 2026-07-07T12:27:56.459238Z [info ] Delete ServiceAccount models-bucket-sa [ocp_resources ServiceAccount] 2026-07-07T12:27:56.496705Z [info ] Deleting {'kind': 'ServiceAccount', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-sa', 'namespace': 'opt-125m-probes', 'uid': '4094552d-02e7-4f23-b098-f7022c8f0122', 'resourceVersion': '18739264', 'creationTimestamp': '2026-07-07T12:25:31Z', 'annotations': {'openshift.io/internal-registry-pull-secret-ref': 'models-bucket-sa-dockercfg-z2q4k'}, 'managedFields': [{'manager': 'openshift.io/image-registry-pull-secrets_service-account-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:25:31Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:imagePullSecrets': {}, 'f:metadata': {'f:annotations': {'f:openshift.io/internal-registry-pull-secret-ref': {}}}, 'f:secrets': {'k:{"name":"models-bucket-sa-dockercfg-z2q4k"}': {}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:25:31Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:secrets': {'.': {}, 'k:{"name":"models-bucket-secret"}': {}}}}]}, 'secrets': [{'name': 'models-bucket-secret'}, {'name': 'models-bucket-sa-dockercfg-z2q4k'}], 'imagePullSecrets': [{'name': 'models-bucket-sa-dockercfg-z2q4k'}]} [ocp_resources ServiceAccount] 2026-07-07T12:27:56.533680Z [info ] Wait until ServiceAccount models-bucket-sa is deleted [ocp_resources ServiceAccount] 2026-07-07T12:27:56.533843Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:27:56.553066Z [info ] Elapsed time: 4.2438507080078125e-05 [0:00:00.000042] [timeout_sampler] 2026-07-07T12:27:56.553336Z [info ] Delete Secret models-bucket-secret [ocp_resources Secret] 2026-07-07T12:27:56.595871Z [info ] Deleting {'kind': 'Secret', 'apiVersion': 'v1', 'metadata': {'name': 'models-bucket-secret', 'namespace': 'opt-125m-probes', 'uid': '93ccaf45-9dd5-4808-bf4e-cd8bdde68cd7', 'resourceVersion': '18739255', 'creationTimestamp': '2026-07-07T12:25:31Z', 'annotations': {'serving.kserve.io/s3-endpoint': 's3.us-east-2.amazonaws.com/', 'serving.kserve.io/s3-region': 'us-east-2', 'serving.kserve.io/s3-useanoncredential': 'false', 'serving.kserve.io/s3-usehttps': '1', 'serving.kserve.io/s3-verifyssl': '0'}, 'managedFields': [{'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:25:31Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:data': {'.': {}, 'f:AWS_ACCESS_KEY_ID': {}, 'f:AWS_SECRET_ACCESS_KEY': {}}, 'f:metadata': {'f:annotations': {'.': {}, 'f:serving.kserve.io/s3-endpoint': {}, 'f:serving.kserve.io/s3-region': {}, 'f:serving.kserve.io/s3-useanoncredential': {}, 'f:serving.kserve.io/s3-usehttps': {}, 'f:serving.kserve.io/s3-verifyssl': {}}}, 'f:type': {}}}]}, 'data': '*******', 'type': 'Opaque'} [ocp_resources Secret] 2026-07-07T12:27:56.621782Z [info ] Wait until Secret models-bucket-secret is deleted [ocp_resources Secret] 2026-07-07T12:27:56.622018Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:27:56.641159Z [info ] Elapsed time: 4.8160552978515625e-05 [0:00:00.000048] [timeout_sampler] 2026-07-07T12:27:56.641404Z [info ] Delete ServingRuntime vllm-runtime [ocp_resources ServingRuntime] 2026-07-07T12:27:56.681425Z [info ] Deleting {'apiVersion': 'serving.kserve.io/v1alpha1', 'kind': 'ServingRuntime', 'metadata': {'annotations': {'opendatahub.io/runtime-version': 'v0.19.1', 'openshift.io/display-name': 'vLLM CPU (x86) ServingRuntime for KServe'}, 'creationTimestamp': '2026-07-07T12:25:31Z', 'generation': 1, 'labels': {'opendatahub.io/dashboard': 'true'}, 'managedFields': [{'apiVersion': 'serving.kserve.io/v1alpha1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'.': {}, 'f:opendatahub.io/runtime-version': {}, 'f:openshift.io/display-name': {}}, 'f:labels': {'.': {}, 'f:opendatahub.io/dashboard': {}}}, 'f:spec': {'.': {}, 'f:annotations': {'.': {}, 'f:opendatahub.io/kserve-runtime': {}, 'f:prometheus.io/path': {}, 'f:prometheus.io/port': {}}, 'f:containers': {}, 'f:multiModel': {}, 'f:supportedModelFormats': {}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-07-07T12:25:31Z'}], 'name': 'vllm-runtime', 'namespace': 'opt-125m-probes', 'resourceVersion': '18739245', 'uid': '09519498-d201-42f6-b3b1-27317c57e402'}, 'spec': {'annotations': {'opendatahub.io/kserve-runtime': 'vllm', 'prometheus.io/path': '/metrics', 'prometheus.io/port': '8080'}, 'containers': [{'args': ['--port=8080', '--model=/mnt/models', '--served-model-name={{.Name}}'], 'command': ['python', '-m', 'vllm.entrypoints.openai.api_server'], 'env': [{'name': 'HF_HOME', 'value': '/tmp/hf_home'}], 'image': 'registry.redhat.io/rhaii-early-access/vllm-cpu-rhel9@sha256:139e070c2e4e2bc0254aa852b436c35ec2659e8424e228cc4c77a3bc2ddf50b6', 'livenessProbe': {'failureThreshold': 10, 'httpGet': {'path': '/health', 'port': 8080, 'scheme': 'HTTP'}, 'initialDelaySeconds': 180, 'periodSeconds': 30, 'timeoutSeconds': 10}, 'name': 'kserve-container', 'ports': [{'containerPort': 8080, 'protocol': 'TCP'}], 'readinessProbe': {'failureThreshold': 12, 'httpGet': {'path': '/health', 'port': 8080, 'scheme': 'HTTP'}, 'initialDelaySeconds': 120, 'periodSeconds': 10, 'timeoutSeconds': 10}}], 'multiModel': False, 'supportedModelFormats': [{'autoSelect': True, 'name': 'vLLM'}]}} [ocp_resources ServingRuntime] 2026-07-07T12:27:56.709175Z [info ] Wait until ServingRuntime vllm-runtime is deleted [ocp_resources ServingRuntime] 2026-07-07T12:27:56.709375Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:27:56.731852Z [info ] Elapsed time: 0.0001499652862548828 [0:00:00.000150] [timeout_sampler] 2026-07-07T12:27:56.750334Z [info ] Delete Namespace opt-125m-probes [ocp_resources Namespace] 2026-07-07T12:27:56.789078Z [info ] Deleting {'kind': 'Namespace', 'apiVersion': 'v1', 'metadata': {'name': 'opt-125m-probes', 'uid': '777666bd-62e3-4c33-bd46-56f690656691', 'resourceVersion': '18739228', 'creationTimestamp': '2026-07-07T12:25:31Z', 'labels': {'kubernetes.io/metadata.name': 'opt-125m-probes', 'pod-security.kubernetes.io/audit': 'restricted', 'pod-security.kubernetes.io/audit-version': 'latest', 'pod-security.kubernetes.io/warn': 'restricted', 'pod-security.kubernetes.io/warn-version': 'latest'}, 'annotations': {'openshift.io/sa.scc.mcs': 's0:c32,c19', 'openshift.io/sa.scc.supplemental-groups': '1001030000/10000', 'openshift.io/sa.scc.uid-range': '1001030000/10000', 'security.openshift.io/MinimallySufficientPodSecurityStandard': 'restricted'}, 'managedFields': [{'manager': 'cluster-policy-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:25:31Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:openshift.io/sa.scc.mcs': {}, 'f:openshift.io/sa.scc.supplemental-groups': {}, 'f:openshift.io/sa.scc.uid-range': {}}}}}, {'manager': 'pod-security-admission-label-synchronization-controller', 'operation': 'Apply', 'apiVersion': 'v1', 'time': '2026-07-07T12:25:31Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:annotations': {'f:security.openshift.io/MinimallySufficientPodSecurityStandard': {}}, 'f:labels': {'f:pod-security.kubernetes.io/audit': {}, 'f:pod-security.kubernetes.io/audit-version': {}, 'f:pod-security.kubernetes.io/warn': {}, 'f:pod-security.kubernetes.io/warn-version': {}}}}}, {'manager': 'OpenAPI-Generator', 'operation': 'Update', 'apiVersion': 'v1', 'time': '2026-07-07T12:25:31Z', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:labels': {'.': {}, 'f:kubernetes.io/metadata.name': {}}}}}]}, 'spec': {'finalizers': ['kubernetes']}, 'status': {'phase': 'Active'}} [ocp_resources Namespace] 2026-07-07T12:27:56.817004Z [info ] Wait until Namespace opt-125m-probes is deleted [ocp_resources Namespace] 2026-07-07T12:27:56.817174Z [info ] Waiting for 240 seconds [0:04:00], retry every 1 seconds. (Function: ocp_resources.resource.wait_deleted.lambda: self.exists) [timeout_sampler] 2026-07-07T12:28:07.279359Z [info ] Elapsed time: 10.286395072937012 [0:00:10.286395] [timeout_sampler] _ 9 of 9 completed, 8 Pass, 1 Fail, 0 Skip, 0 XPass, 0 XFail, 0 Error, 0 ReRun _ ============ 1 failed, 8 passed, 48 deselected in 479.44s (0:07:59) ============ =================================== FAILURES =================================== _ TestTensorflowModel.test_tensorflow_inference[tensorflow-standard-grpc-deployment] _ Traceback (most recent call last): File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 353, in from_call result: TResult | None = func() ~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 245, in lambda: runtest_hook(item=item, **kwds), ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_hooks.py", line 512, in __call__ return self._hookexec(self.name, self._hookimpls.copy(), kwargs, firstresult) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_manager.py", line 120, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 167, in _multicall raise exception File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/capture.py", line 900, in pytest_runtest_call return (yield) ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 53, in run_old_style_hookwrapper return result.get_result() ~~~~~~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_result.py", line 103, in get_result raise exc.with_traceback(tb) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 38, in run_old_style_hookwrapper res = yield ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/skipping.py", line 268, in pytest_runtest_call return (yield) ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 121, in _multicall res = hook_impl.function(*args) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/runner.py", line 179, in pytest_runtest_call item.runtest() ~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/python.py", line 1720, in runtest self.ihook.pytest_pyfunc_call(pyfuncitem=self) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_hooks.py", line 512, in __call__ return self._hookexec(self.name, self._hookimpls.copy(), kwargs, firstresult) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_manager.py", line 120, in _hookexec return self._inner_hookexec(hook_name, methods, kwargs, firstresult) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 167, in _multicall raise exception File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 139, in _multicall teardown.throw(exception) ~~~~~~~~~~~~~~^^^^^^^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 53, in run_old_style_hookwrapper return result.get_result() ~~~~~~~~~~~~~~~~~^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_result.py", line 103, in get_result raise exc.with_traceback(tb) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 38, in run_old_style_hookwrapper res = yield ^^^^^ File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/pluggy/_callers.py", line 121, in _multicall res = hook_impl.function(*args) File "/home/odh/opendatahub-tests/.venv/lib64/python3.14/site-packages/_pytest/python.py", line 166, in pytest_pyfunc_call result = testfunction(**testargs) File "/home/odh/opendatahub-tests/tests/model_serving/model_runtime/triton/basic_model_deployment/test_tensorflow_model.py", line 97, in test_tensorflow_inference validate_inference_request( ~~~~~~~~~~~~~~~~~~~~~~~~~~^ pod_name=triton_pod_resource.name, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<5 lines>... root_dir=root_dir, ^^^^^^^^^^^^^^^^^^ ) ^ File "/home/odh/opendatahub-tests/tests/model_serving/model_runtime/triton/basic_model_deployment/utils.py", line 149, in validate_inference_request assert isinstance(response, dict), f"Response is not a dict: {response}" ~~~~~~~~~~^^^^^^^^^^^^^^^^ AssertionError: Response is not a dict: gRPC request (stdin) failed: STDOUT: STDERR: Failed to dial target host "localhost:9000": context deadline exceeded - generated xml file: /workspace/tests-shared/tests-payload/results/model_runtime-smoke.xml - =========================== short test summary info ============================ FAILED tests/model_serving/model_runtime/triton/basic_model_deployment/test_tensorflow_model.py::TestTensorflowModel::test_tensorflow_inference[tensorflow-standard-grpc-deployment] - AssertionError: Response is not a dict: gRPC request (stdin) failed: STDOUT: STDERR: Failed to dial target host "localhost:9000": context deadline exceeded ============ 1 failed, 8 passed, 48 deselected in 479.45s (0:07:59) ============