('/workspace/source/test/e2e/explainer/test_art_explainer.py', 48, 'Skipped: ODH does not support art explainer at the moment')('/workspace/source/test/e2e/predictor/test_grpc.py', 39, 'Skipped: Not testable in ODH at the moment')('/workspace/source/test/e2e/predictor/test_torchserve.py', 34, 'Skipped: ODH does not support torchserve at the moment')kserve_client = <kserve.api.kserve_client.KServeClient object at 0x7fea3c350ed0> rest_v1_client = <kserve.inference_client.InferenceRESTClient object at 0x7fea3d5a15d0> network_layer = 'openshift-route' @pytest.mark.predictor @pytest.mark.asyncio(scope="session") async def test_batcher_custom_port(kserve_client, rest_v1_client, network_layer): service_name = "isvc-sklearn-batcher-custom" predictor = V1beta1PredictorSpec( batcher=V1beta1Batcher( max_batch_size=32, max_latency=5000, ), min_replicas=1, sklearn=V1beta1SKLearnSpec( args=["--http_port=5000"], storage_uri="gs://kfserving-examples/models/sklearn/1.0/model", resources=V1ResourceRequirements( requests={"cpu": "50m", "memory": "128Mi"}, limits={"cpu": "100m", "memory": "256Mi"}, ), ports=[V1ContainerPort(container_port=5000, protocol="TCP")], ), ) isvc = V1beta1InferenceService( api_version=constants.KSERVE_V1BETA1, kind=constants.KSERVE_KIND_INFERENCESERVICE, metadata=client.V1ObjectMeta( name=service_name, namespace=KSERVE_TEST_NAMESPACE, labels={ constants.KSERVE_LABEL_NETWORKING_VISIBILITY: constants.KSERVE_LABEL_NETWORKING_VISIBILITY_EXPOSED, }, ), spec=V1beta1InferenceServiceSpec(predictor=predictor), ) kserve_client.create(isvc) try: > kserve_client.wait_isvc_ready(service_name, namespace=KSERVE_TEST_NAMESPACE) batcher/test_batcher_custom_port.py:79: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kserve.api.kserve_client.KServeClient object at 0x7fea3c350ed0> name = 'isvc-sklearn-batcher-custom', namespace = 'kserve-ci-e2e-test' watch = False, timeout_seconds = 600, polling_interval = 10, version = 'v1beta1' expected_generation = None def wait_isvc_ready( self, name, namespace=None, # pylint:disable=too-many-arguments watch=False, timeout_seconds=600, polling_interval=10, version=constants.KSERVE_V1BETA1_VERSION, expected_generation=None, ): """ Waiting for inference service ready, print out the inference service if timeout. :param name: inference service name :param namespace: defaults to current or default namespace :param watch: True to watch the service until timeout elapsed or status is ready :param timeout_seconds: timeout seconds for waiting, default to 600s. Print out the InferenceService if timeout. :param polling_interval: The time interval to poll status :param version: api group version :param expected_generation: optional minimum observed generation to consider ready :return: """ if watch: isvc_watch( name=name, namespace=namespace, timeout_seconds=timeout_seconds, generation=expected_generation or 0, ) else: for _ in range(round(timeout_seconds / polling_interval)): time.sleep(polling_interval) if self.is_isvc_ready( name, namespace=namespace, version=version, expected_generation=expected_generation, ): return current_isvc = self.get(name, namespace=namespace, version=version) if expected_generation is None: > raise RuntimeError( "Timeout to start the InferenceService {}. \ The InferenceService is as following: {}".format( name, current_isvc ) ) E RuntimeError: Timeout to start the InferenceService isvc-sklearn-batcher-custom. The InferenceService is as following: {'apiVersion': 'serving.kserve.io/v1beta1', 'kind': 'InferenceService', 'metadata': {'annotations': {'modelFormat': 'sklearn', 'serving.kserve.io/deploymentMode': 'Standard'}, 'creationTimestamp': '2026-09-09T20:22:13Z', '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:labels': {'.': {}, 'f:networking.kserve.io/visibility': {}}}, 'f:spec': {'.': {}, 'f:predictor': {'.': {}, 'f:batcher': {'.': {}, 'f:maxBatchSize': {}, 'f:maxLatency': {}}, 'f:minReplicas': {}, 'f:sklearn': {'.': {}, 'f:args': {}, 'f:name': {}, 'f:ports': {'.': {}, 'k:{"containerPort":5000,"protocol":"TCP"}': {'.': {}, 'f:containerPort': {}, 'f:protocol': {}}}, 'f:resources': {'.': {}, 'f:limits': {'.': {}, 'f:cpu': {}, 'f:memory': {}}, 'f:requests': {'.': {}, 'f:cpu': {}, 'f:memory': {}}}, 'f:storageUri': {}}}}}, 'manager': 'OpenAPI-Generator', 'operation': 'Update', 'time': '2026-09-09T20:22:13Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:metadata': {'f:finalizers': {'.': {}, 'v:"inferenceservice.finalizers"': {}, 'v:"odh.inferenceservice.finalizers"': {}}}}, 'manager': 'manager', 'operation': 'Update', 'time': '2026-09-09T20:22:13Z'}, {'apiVersion': 'serving.kserve.io/v1beta1', 'fieldsType': 'FieldsV1', 'fieldsV1': {'f:status': {'.': {}, 'f:address': {'.': {}, 'f:url': {}}, 'f:components': {'.': {}, 'f:predictor': {}}, 'f:conditions': {}, 'f:deploymentMode': {}, 'f:modelStatus': {'.': {}, 'f:copies': {'.': {}, 'f:failedCopies': {}}, 'f:states': {'.': {}, 'f:activeModelState': {}, 'f:targetModelState': {}}, 'f:transitionStatus': {}}, 'f:observedGeneration': {}, 'f:servingRuntimeName': {}, 'f:url': {}}}, 'manager': 'manager', 'operation': 'Update', 'subresource': 'status', 'time': '2026-09-09T20:22:19Z'}], 'name': 'isvc-sklearn-batcher-custom', 'namespace': 'kserve-ci-e2e-test', 'resourceVersion': '15932', 'uid': '1f761573-8105-4124-ab70-50929283d13f'}, 'spec': {'predictor': {'automountServiceAccountToken': False, 'batcher': {'maxBatchSize': 32, 'maxLatency': 5000}, 'minReplicas': 1, 'model': {'args': ['--http_port=5000'], 'modelFormat': {'name': 'sklearn'}, 'name': '', 'ports': [{'containerPort': 5000, 'protocol': 'TCP'}], 'resources': {'limits': {'cpu': '100m', 'memory': '256Mi'}, 'requests': {'cpu': '50m', 'memory': '128Mi'}}, 'storageUri': 'gs://kfserving-examples/models/sklearn/1.0/model'}}}, 'status': {'address': {'url': 'http://isvc-sklearn-batcher-custom-predictor.kserve-ci-e2e-test.svc.cluster.local'}, 'components': {'predictor': {}}, 'conditions': [{'lastTransitionTime': '2026-09-09T20:22:13Z', 'status': 'True', 'type': 'IngressReady'}, {'lastTransitionTime': '2026-09-09T20:22:13Z', 'message': 'Deployment does not have minimum availability.', 'reason': 'MinimumReplicasUnavailable', 'status': 'False', 'type': 'PredictorReady'}, {'lastTransitionTime': '2026-09-09T20:22:13Z', 'message': 'Deployment does not have minimum availability.', 'reason': 'MinimumReplicasUnavailable', 'status': 'False', 'type': 'Ready'}, {'lastTransitionTime': '2026-09-09T20:22:13Z', 'severity': 'Info', 'status': 'False', 'type': 'Stopped'}], 'deploymentMode': 'Standard', 'modelStatus': {'copies': {'failedCopies': 0}, 'states': {'activeModelState': '', 'targetModelState': 'Pending'}, 'transitionStatus': 'InProgress'}, 'observedGeneration': 1, 'servingRuntimeName': 'kserve-sklearnserver', 'url': 'https://isvc-sklearn-batcher-custom-kserve-ci-e2e-test.apps.53357311-227e-452f-b982-24a032e036be.prod.konfluxeaas.com'}} ../../python/kserve/kserve/api/kserve_client.py:418: RuntimeError During handling of the above exception, another exception occurred: kserve_client = <kserve.api.kserve_client.KServeClient object at 0x7fea3c350ed0> rest_v1_client = <kserve.inference_client.InferenceRESTClient object at 0x7fea3d5a15d0> network_layer = 'openshift-route' @pytest.mark.predictor @pytest.mark.asyncio(scope="session") async def test_batcher_custom_port(kserve_client, rest_v1_client, network_layer): service_name = "isvc-sklearn-batcher-custom" predictor = V1beta1PredictorSpec( batcher=V1beta1Batcher( max_batch_size=32, max_latency=5000, ), min_replicas=1, sklearn=V1beta1SKLearnSpec( args=["--http_port=5000"], storage_uri="gs://kfserving-examples/models/sklearn/1.0/model", resources=V1ResourceRequirements( requests={"cpu": "50m", "memory": "128Mi"}, limits={"cpu": "100m", "memory": "256Mi"}, ), ports=[V1ContainerPort(container_port=5000, protocol="TCP")], ), ) isvc = V1beta1InferenceService( api_version=constants.KSERVE_V1BETA1, kind=constants.KSERVE_KIND_INFERENCESERVICE, metadata=client.V1ObjectMeta( name=service_name, namespace=KSERVE_TEST_NAMESPACE, labels={ constants.KSERVE_LABEL_NETWORKING_VISIBILITY: constants.KSERVE_LABEL_NETWORKING_VISIBILITY_EXPOSED, }, ), spec=V1beta1InferenceServiceSpec(predictor=predictor), ) kserve_client.create(isvc) try: kserve_client.wait_isvc_ready(service_name, namespace=KSERVE_TEST_NAMESPACE) except RuntimeError as e: print( > kserve_client.api_instance.get_namespaced_custom_object( "serving.knative.dev", "v1", KSERVE_TEST_NAMESPACE, "services", service_name + "-predictor", ) ) batcher/test_batcher_custom_port.py:82: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kubernetes.client.api.custom_objects_api.CustomObjectsApi object at 0x7fea3c2d8390> group = 'serving.knative.dev', version = 'v1', namespace = 'kserve-ci-e2e-test' plural = 'services', name = 'isvc-sklearn-batcher-custom-predictor' kwargs = {'_return_http_data_only': True} def get_namespaced_custom_object(self, group, version, namespace, plural, name, **kwargs): # noqa: E501 """get_namespaced_custom_object # noqa: E501 Returns a namespace scoped custom object # noqa: E501 This method makes a synchronous HTTP request by default. To make an asynchronous HTTP request, please pass async_req=True >>> thread = api.get_namespaced_custom_object(group, version, namespace, plural, name, async_req=True) >>> result = thread.get() :param async_req bool: execute request asynchronously :param str group: the custom resource's group (required) :param str version: the custom resource's version (required) :param str namespace: The custom resource's namespace (required) :param str plural: the custom resource's plural name. For TPRs this would be lowercase plural kind. (required) :param str name: the custom object's name (required) :param _preload_content: if False, the urllib3.HTTPResponse object will be returned without reading/decoding response data. Default is True. :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of (connection, read) timeouts. :return: object If the method is called asynchronously, returns the request thread. """ kwargs['_return_http_data_only'] = True > return self.get_namespaced_custom_object_with_http_info(group, version, namespace, plural, name, **kwargs) # noqa: E501 ../../python/kserve/.venv/lib64/python3.11/site-packages/kubernetes/client/api/custom_objects_api.py:1632: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kubernetes.client.api.custom_objects_api.CustomObjectsApi object at 0x7fea3c2d8390> group = 'serving.knative.dev', version = 'v1', namespace = 'kserve-ci-e2e-test' plural = 'services', name = 'isvc-sklearn-batcher-custom-predictor' kwargs = {'_return_http_data_only': True} local_var_params = {'_return_http_data_only': True, 'all_params': ['group', 'version', 'namespace', 'plural', 'name', 'async_req', ...], 'auth_settings': ['BearerToken'], 'body_params': None, ...} all_params = ['group', 'version', 'namespace', 'plural', 'name', 'async_req', ...] key = '_return_http_data_only', val = True, collection_formats = {} path_params = {'group': 'serving.knative.dev', 'name': 'isvc-sklearn-batcher-custom-predictor', 'namespace': 'kserve-ci-e2e-test', 'plural': 'services', ...} query_params = [] def get_namespaced_custom_object_with_http_info(self, group, version, namespace, plural, name, **kwargs): # noqa: E501 """get_namespaced_custom_object # noqa: E501 Returns a namespace scoped custom object # noqa: E501 This method makes a synchronous HTTP request by default. To make an asynchronous HTTP request, please pass async_req=True >>> thread = api.get_namespaced_custom_object_with_http_info(group, version, namespace, plural, name, async_req=True) >>> result = thread.get() :param async_req bool: execute request asynchronously :param str group: the custom resource's group (required) :param str version: the custom resource's version (required) :param str namespace: The custom resource's namespace (required) :param str plural: the custom resource's plural name. For TPRs this would be lowercase plural kind. (required) :param str name: the custom object's name (required) :param _return_http_data_only: response data without head status code and headers :param _preload_content: if False, the urllib3.HTTPResponse object will be returned without reading/decoding response data. Default is True. :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of (connection, read) timeouts. :return: tuple(object, status_code(int), headers(HTTPHeaderDict)) If the method is called asynchronously, returns the request thread. """ local_var_params = locals() all_params = [ 'group', 'version', 'namespace', 'plural', 'name' ] all_params.extend( [ 'async_req', '_return_http_data_only', '_preload_content', '_request_timeout' ] ) for key, val in six.iteritems(local_var_params['kwargs']): if key not in all_params: raise ApiTypeError( "Got an unexpected keyword argument '%s'" " to method get_namespaced_custom_object" % key ) local_var_params[key] = val del local_var_params['kwargs'] # verify the required parameter 'group' is set if self.api_client.client_side_validation and ('group' not in local_var_params or # noqa: E501 local_var_params['group'] is None): # noqa: E501 raise ApiValueError("Missing the required parameter `group` when calling `get_namespaced_custom_object`") # noqa: E501 # verify the required parameter 'version' is set if self.api_client.client_side_validation and ('version' not in local_var_params or # noqa: E501 local_var_params['version'] is None): # noqa: E501 raise ApiValueError("Missing the required parameter `version` when calling `get_namespaced_custom_object`") # noqa: E501 # verify the required parameter 'namespace' is set if self.api_client.client_side_validation and ('namespace' not in local_var_params or # noqa: E501 local_var_params['namespace'] is None): # noqa: E501 raise ApiValueError("Missing the required parameter `namespace` when calling `get_namespaced_custom_object`") # noqa: E501 # verify the required parameter 'plural' is set if self.api_client.client_side_validation and ('plural' not in local_var_params or # noqa: E501 local_var_params['plural'] is None): # noqa: E501 raise ApiValueError("Missing the required parameter `plural` when calling `get_namespaced_custom_object`") # noqa: E501 # verify the required parameter 'name' is set if self.api_client.client_side_validation and ('name' not in local_var_params or # noqa: E501 local_var_params['name'] is None): # noqa: E501 raise ApiValueError("Missing the required parameter `name` when calling `get_namespaced_custom_object`") # noqa: E501 collection_formats = {} path_params = {} if 'group' in local_var_params: path_params['group'] = local_var_params['group'] # noqa: E501 if 'version' in local_var_params: path_params['version'] = local_var_params['version'] # noqa: E501 if 'namespace' in local_var_params: path_params['namespace'] = local_var_params['namespace'] # noqa: E501 if 'plural' in local_var_params: path_params['plural'] = local_var_params['plural'] # noqa: E501 if 'name' in local_var_params: path_params['name'] = local_var_params['name'] # noqa: E501 query_params = [] header_params = {} form_params = [] local_var_files = {} body_params = None # HTTP header `Accept` header_params['Accept'] = self.api_client.select_header_accept( ['application/json']) # noqa: E501 # Authentication setting auth_settings = ['BearerToken'] # noqa: E501 > return self.api_client.call_api( '/apis/{group}/{version}/namespaces/{namespace}/{plural}/{name}', 'GET', path_params, query_params, header_params, body=body_params, post_params=form_params, files=local_var_files, response_type='object', # noqa: E501 auth_settings=auth_settings, async_req=local_var_params.get('async_req'), _return_http_data_only=local_var_params.get('_return_http_data_only'), # noqa: E501 _preload_content=local_var_params.get('_preload_content', True), _request_timeout=local_var_params.get('_request_timeout'), collection_formats=collection_formats) ../../python/kserve/.venv/lib64/python3.11/site-packages/kubernetes/client/api/custom_objects_api.py:1739: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kubernetes.client.api_client.ApiClient object at 0x7fea3c2da3d0> resource_path = '/apis/{group}/{version}/namespaces/{namespace}/{plural}/{name}' method = 'GET' path_params = {'group': 'serving.knative.dev', 'name': 'isvc-sklearn-batcher-custom-predictor', 'namespace': 'kserve-ci-e2e-test', 'plural': 'services', ...} query_params = [] header_params = {'Accept': 'application/json', 'User-Agent': 'OpenAPI-Generator/32.0.1/python'} body = None, post_params = [], files = {}, response_type = 'object' auth_settings = ['BearerToken'], async_req = None, _return_http_data_only = True collection_formats = {}, _preload_content = True, _request_timeout = None _host = None def call_api(self, resource_path, method, path_params=None, query_params=None, header_params=None, body=None, post_params=None, files=None, response_type=None, auth_settings=None, async_req=None, _return_http_data_only=None, collection_formats=None, _preload_content=True, _request_timeout=None, _host=None): """Makes the HTTP request (synchronous) and returns deserialized data. To make an async_req request, set the async_req parameter. :param resource_path: Path to method endpoint. :param method: Method to call. :param path_params: Path parameters in the url. :param query_params: Query parameters in the url. :param header_params: Header parameters to be placed in the request header. :param body: Request body. :param post_params dict: Request post form parameters, for `application/x-www-form-urlencoded`, `multipart/form-data`. :param auth_settings list: Auth Settings names for the request. :param response: Response data type. :param files dict: key -> filename, value -> filepath, for `multipart/form-data`. :param async_req bool: execute request asynchronously :param _return_http_data_only: response data without head status code and headers :param collection_formats: dict of collection formats for path, query, header, and post parameters. :param _preload_content: if False, the urllib3.HTTPResponse object will be returned without reading/decoding response data. Default is True. :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of (connection, read) timeouts. :return: If async_req parameter is True, the request will be called asynchronously. The method will return the request thread. If parameter async_req is False or missing, then the method will return the response directly. """ if not async_req: > return self.__call_api(resource_path, method, path_params, query_params, header_params, body, post_params, files, response_type, auth_settings, _return_http_data_only, collection_formats, _preload_content, _request_timeout, _host) ../../python/kserve/.venv/lib64/python3.11/site-packages/kubernetes/client/api_client.py:348: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kubernetes.client.api_client.ApiClient object at 0x7fea3c2da3d0> resource_path = '/apis/serving.knative.dev/v1/namespaces/kserve-ci-e2e-test/services/isvc-sklearn-batcher-custom-predictor' method = 'GET' path_params = [('group', 'serving.knative.dev'), ('version', 'v1'), ('namespace', 'kserve-ci-e2e-test'), ('plural', 'services'), ('name', 'isvc-sklearn-batcher-custom-predictor')] query_params = [] header_params = {'Accept': 'application/json', 'Content-Type': 'application/json', 'User-Agent': 'OpenAPI-Generator/32.0.1/python'} body = None, post_params = [], files = {}, response_type = 'object' auth_settings = ['BearerToken'], _return_http_data_only = True collection_formats = {}, _preload_content = True, _request_timeout = None _host = None def __call_api( self, resource_path, method, path_params=None, query_params=None, header_params=None, body=None, post_params=None, files=None, response_type=None, auth_settings=None, _return_http_data_only=None, collection_formats=None, _preload_content=True, _request_timeout=None, _host=None): config = self.configuration # header parameters header_params = header_params or {} header_params.update(self.default_headers) if self.cookie: header_params['Cookie'] = self.cookie if header_params: header_params = self.sanitize_for_serialization(header_params) header_params = dict(self.parameters_to_tuples(header_params, collection_formats)) # path parameters if path_params: path_params = self.sanitize_for_serialization(path_params) path_params = self.parameters_to_tuples(path_params, collection_formats) for k, v in path_params: # specified safe chars, encode everything resource_path = resource_path.replace( '{%s}' % k, quote(str(v), safe=config.safe_chars_for_path_param) ) # query parameters if query_params: query_params = self.sanitize_for_serialization(query_params) query_params = self.parameters_to_tuples(query_params, collection_formats) # post parameters if post_params or files: post_params = post_params if post_params else [] post_params = self.sanitize_for_serialization(post_params) post_params = self.parameters_to_tuples(post_params, collection_formats) post_params.extend(self.files_parameters(files)) # auth setting self.update_params_for_auth(header_params, query_params, auth_settings) # body if body: body = self.sanitize_for_serialization(body) # request url if _host is None: url = self.configuration.host + resource_path else: # use server/host defined in path or operation instead url = _host + resource_path # perform request and return response > response_data = self.request( method, url, query_params=query_params, headers=header_params, post_params=post_params, body=body, _preload_content=_preload_content, _request_timeout=_request_timeout) ../../python/kserve/.venv/lib64/python3.11/site-packages/kubernetes/client/api_client.py:180: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kubernetes.client.api_client.ApiClient object at 0x7fea3c2da3d0> method = 'GET' url = 'https://ad0cdfe0e326f45b5aa1b566eebc3a10-76fd29d5fe107923.elb.us-east-1.amazonaws.com:6443/apis/serving.knative.dev/v1/namespaces/kserve-ci-e2e-test/services/isvc-sklearn-batcher-custom-predictor' query_params = [] headers = {'Accept': 'application/json', 'Content-Type': 'application/json', 'User-Agent': 'OpenAPI-Generator/32.0.1/python'} post_params = [], body = None, _preload_content = True, _request_timeout = None def request(self, method, url, query_params=None, headers=None, post_params=None, body=None, _preload_content=True, _request_timeout=None): """Makes the HTTP request using RESTClient.""" if method == "GET": > return self.rest_client.GET(url, query_params=query_params, _preload_content=_preload_content, _request_timeout=_request_timeout, ../../python/kserve/.venv/lib64/python3.11/site-packages/kubernetes/client/api_client.py:373: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kubernetes.client.rest.RESTClientObject object at 0x7fea3c2d8d50> url = 'https://ad0cdfe0e326f45b5aa1b566eebc3a10-76fd29d5fe107923.elb.us-east-1.amazonaws.com:6443/apis/serving.knative.dev/v1/namespaces/kserve-ci-e2e-test/services/isvc-sklearn-batcher-custom-predictor' headers = {'Accept': 'application/json', 'Content-Type': 'application/json', 'User-Agent': 'OpenAPI-Generator/32.0.1/python'} query_params = [], _preload_content = True, _request_timeout = None def GET(self, url, headers=None, query_params=None, _preload_content=True, _request_timeout=None): > return self.request("GET", url, headers=headers, _preload_content=_preload_content, _request_timeout=_request_timeout, query_params=query_params) ../../python/kserve/.venv/lib64/python3.11/site-packages/kubernetes/client/rest.py:244: _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ self = <kubernetes.client.rest.RESTClientObject object at 0x7fea3c2d8d50> method = 'GET' url = 'https://ad0cdfe0e326f45b5aa1b566eebc3a10-76fd29d5fe107923.elb.us-east-1.amazonaws.com:6443/apis/serving.knative.dev/v1/namespaces/kserve-ci-e2e-test/services/isvc-sklearn-batcher-custom-predictor' query_params = [] headers = {'Accept': 'application/json', 'Content-Type': 'application/json', 'User-Agent': 'OpenAPI-Generator/32.0.1/python'} body = None, post_params = {}, _preload_content = True, _request_timeout = None def request(self, method, url, query_params=None, headers=None, body=None, post_params=None, _preload_content=True, _request_timeout=None): """Perform requests. :param method: http request method :param url: http request url :param query_params: query parameters in the url :param headers: http request headers :param body: request json body, for `application/json` :param post_params: request post parameters, `application/x-www-form-urlencoded` and `multipart/form-data` :param _preload_content: if False, the urllib3.HTTPResponse object will be returned without reading/decoding response data. Default is True. :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of (connection, read) timeouts. """ method = method.upper() assert method in ['GET', 'HEAD', 'DELETE', 'POST', 'PUT', 'PATCH', 'OPTIONS'] if post_params and body: raise ApiValueError( "body parameter cannot be used with post_params parameter." ) post_params = post_params or {} headers = headers or {} timeout = None if _request_timeout: if isinstance(_request_timeout, (int, ) if six.PY3 else (int, long)): # noqa: E501,F821 timeout = urllib3.Timeout(total=_request_timeout) elif (isinstance(_request_timeout, tuple) and len(_request_timeout) == 2): timeout = urllib3.Timeout( connect=_request_timeout[0], read=_request_timeout[1]) if 'Content-Type' not in headers: headers['Content-Type'] = 'application/json' try: # For `POST`, `PUT`, `PATCH`, `OPTIONS`, `DELETE` if method in ['POST', 'PUT', 'PATCH', 'OPTIONS', 'DELETE']: if query_params: url += '?' + urlencode(query_params) if (re.search('json', headers['Content-Type'], re.IGNORECASE) or headers['Content-Type'] == 'application/apply-patch+yaml'): if headers['Content-Type'] == 'application/json-patch+json': if not isinstance(body, list): headers['Content-Type'] = \ 'application/strategic-merge-patch+json' request_body = None if body is not None: request_body = json.dumps(body) r = self.pool_manager.request( method, url, body=request_body, preload_content=_preload_content, timeout=timeout, headers=headers) elif headers['Content-Type'] == 'application/x-www-form-urlencoded': # noqa: E501 r = self.pool_manager.request( method, url, fields=post_params, encode_multipart=False, preload_content=_preload_content, timeout=timeout, headers=headers) elif headers['Content-Type'] == 'multipart/form-data': # must del headers['Content-Type'], or the correct # Content-Type which generated by urllib3 will be # overwritten. del headers['Content-Type'] r = self.pool_manager.request( method, url, fields=post_params, encode_multipart=True, preload_content=_preload_content, timeout=timeout, headers=headers) # Pass a `string` parameter directly in the body to support # other content types than Json when `body` argument is # provided in serialized form elif isinstance(body, str) or isinstance(body, bytes): request_body = body r = self.pool_manager.request( method, url, body=request_body, preload_content=_preload_content, timeout=timeout, headers=headers) else: # Cannot generate the request from given parameters msg = """Cannot prepare a request message for provided arguments. Please check that your arguments match declared content type.""" raise ApiException(status=0, reason=msg) # For `GET`, `HEAD` else: r = self.pool_manager.request(method, url, fields=query_params, preload_content=_preload_content, timeout=timeout, headers=headers) except urllib3.exceptions.SSLError as e: msg = "{0}\n{1}".format(type(e).__name__, str(e)) raise ApiException(status=0, reason=msg) if _preload_content: r = RESTResponse(r) # In the python 3, the response.data is bytes. # we need to decode it to string. if six.PY3: r.data = r.data.decode('utf8') # log response body logger.debug("response body: %s", r.data) if not 200 <= r.status <= 299: > raise ApiException(http_resp=r) E kubernetes.client.exceptions.ApiException: (404) E Reason: Not Found E HTTP response headers: HTTPHeaderDict({'Audit-Id': 'f8d0bb66-ee12-4344-b0db-d4f43a4ddf95', 'Cache-Control': 'no-cache, private', 'Content-Type': 'text/plain; charset=utf-8', 'Strict-Transport-Security': 'max-age=31536000; includeSubDomains; preload', 'X-Content-Type-Options': 'nosniff', 'X-Kubernetes-Pf-Flowschema-Uid': '579c8d6a-7a30-4d77-b114-bffb4b116e5e', 'X-Kubernetes-Pf-Prioritylevel-Uid': '3dc12936-a24b-4662-bb0e-1004e15aa598', 'Date': 'Wed, 09 Sep 2026 20:32:13 GMT', 'Content-Length': '19'}) E HTTP response body: 404 page not found ../../python/kserve/.venv/lib64/python3.11/site-packages/kubernetes/client/rest.py:238: ApiException/workspace/source/test/e2e/custom/test_custom_model_grpc.py:56: Not testable in ODH at the moment/workspace/source/test/e2e/custom/test_ray.py:44: Not testable in ODH at the moment/workspace/source/test/e2e/predictor/test_sklearn.py:347: GRPC tests are failing in ODH at the moment/workspace/source/test/e2e/predictor/test_sklearn.py:451: GRPC tests are failing in ODH at the moment/workspace/source/test/e2e/predictor/test_autoscaling.py:53: We do not test anymore with Knative/workspace/source/test/e2e/predictor/test_autoscaling.py:103: We do not test anymore with Knative/workspace/source/test/e2e/predictor/test_canary.py:29: Canary rollouts require Knative Serving and are not supported in RawDeployment mode/workspace/source/test/e2e/predictor/test_canary.py:102: Canary rollouts require Knative Serving and are not supported in RawDeployment mode/workspace/source/test/e2e/predictor/test_xgboost.py:348: Not testable in ODH at the moment/workspace/source/test/e2e/storage/test_oci_modelcar.py:121: SKLEARN_MODELCAR_URI not set/workspace/source/test/e2e/predictor/test_lightgbm.py:270: Not testable in ODH at the moment/workspace/source/test/e2e/predictor/test_paddle.py:206: GRPC tests are failing in ODH at the moment/workspace/source/test/e2e/predictor/test_pmml.py:224: Not testable in ODH at the moment