<?xml version='1.0' encoding='utf-8'?>
<testsuites tests="41" failures="1" errors="0" skipped="4" time="4124.196"><testsuite name="Kubeflow Trainer E2E Suite" package="/workspace/source/src_code/test/e2e" tests="16" disabled="2" skipped="4" errors="0" failures="1" time="527.236" timestamp="2026-11-02T22:35:05">
          <properties>
              <property name="SuiteSucceeded" value="false" />
              <property name="SuiteHasProgrammaticFocus" value="false" />
              <property name="SpecialSuiteFailureReason" value="" />
              <property name="SuiteLabels" value="[]" />
              <property name="SuiteSemVerConstraints" value="[]" />
              <property name="SuiteComponentSemVerConstraints" value="[]" />
              <property name="RandomSeed" value="1793658850" />
              <property name="RandomizeAllSpecs" value="false" />
              <property name="LabelFilter" value="" />
              <property name="SemVerFilter" value="" />
              <property name="FocusStrings" value="" />
              <property name="SkipStrings" value="runtime status server instrumentation" />
              <property name="FocusFiles" value="" />
              <property name="SkipFiles" value="" />
              <property name="FailOnPending" value="false" />
              <property name="FailOnEmpty" value="false" />
              <property name="FailFast" value="false" />
              <property name="FlakeAttempts" value="0" />
              <property name="DryRun" value="false" />
              <property name="ParallelTotal" value="1" />
              <property name="OutputInterceptorMode" value="" />
          </properties>
          <testcase name="[BeforeSuite]" classname="Kubeflow Trainer E2E Suite" status="passed" time="0.000893828">
              <system-err>&gt; Enter [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/02/26 22:35:05.834
&lt; Exit [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/02/26 22:35:05.834 (1ms)
</system-err>
          </testcase>
          <testcase name="[It] OptimizationJob e2e when Creating OptimizationJob with random search algorithm should provision algorithm service, run trials to completion, record best result, and perform cleanup" classname="Kubeflow Trainer E2E Suite" status="pending" time="0">
              <skipped message="pending" />
          </testcase>
          <testcase name="[It] OptimizationJob e2e when Creating OptimizationJob with random search algorithm should fail if unsupported search algorithm is configured" classname="Kubeflow Trainer E2E Suite" status="pending" time="0">
              <skipped message="pending" />
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform the PyTorch workload should create TrainJob with PyTorch runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="255.972687882">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:35:05.835
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:35:05.981 (146ms)
&gt; Enter [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/02/26 22:35:05.981
STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/02/26 22:35:05.981
END STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/02/26 22:35:06.329 (348ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/02/26 22:35:06.329
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/02/26 22:35:07.41 (1.081s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 11/02/26 22:35:07.41
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 11/02/26 22:39:21.788 (4m14.378s)
&lt; Exit [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/02/26 22:39:21.788 (4m15.807s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:39:21.788
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:39:21.807 (19ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform DeepSpeed workload should create TrainJob with DeepSpeed runtime reference" classname="Kubeflow Trainer E2E Suite" status="skipped" time="0.050234908">
              <skipped message="skipped - MPI runtime image is not available" />
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:39:21.807
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:39:21.84 (32ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/02/26 22:39:21.84
[SKIPPED] MPI runtime image is not available
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:147 @ 11/02/26 22:39:21.84
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/02/26 22:39:21.84 (0s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:39:21.84
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:39:21.858 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform OpenMPI 4.0 workload should create TrainJob with DeepSpeed runtime reference and OpenMPI 4.0 image" classname="Kubeflow Trainer E2E Suite" status="failed" time="0.38371797">
              <failure message="Expected success, but got an error:&#10;    &lt;*errors.StatusError | 0x1b5095914500&gt;: &#10;    admission webhook &quot;validator.trainjob.trainer.kubeflow.org&quot; denied the request: spec.runtimeRef: Invalid value: {&quot;name&quot;:&quot;deepspeed-distributed&quot;,&quot;apiGroup&quot;:&quot;trainer.kubeflow.org&quot;,&quot;kind&quot;:&quot;ClusterTrainingRuntime&quot;}: ClusterTrainingRuntime.trainer.kubeflow.org &quot;deepspeed-distributed&quot; not found: specified clusterTrainingRuntime must be created before the TrainJob is created&#10;    {&#10;        ErrStatus: {&#10;            TypeMeta: {Kind: &quot;&quot;, APIVersion: &quot;&quot;},&#10;            ListMeta: {&#10;                SelfLink: &quot;&quot;,&#10;                ResourceVersion: &quot;&quot;,&#10;                Continue: &quot;&quot;,&#10;                RemainingItemCount: nil,&#10;                ShardInfo: nil,&#10;            },&#10;            Status: &quot;Failure&quot;,&#10;            Message: &quot;admission webhook \&quot;validator.trainjob.trainer.kubeflow.org\&quot; denied the request: spec.runtimeRef: Invalid value: {\&quot;name\&quot;:\&quot;deepspeed-distributed\&quot;,\&quot;apiGroup\&quot;:\&quot;trainer.kubeflow.org\&quot;,\&quot;kind\&quot;:\&quot;ClusterTrainingRuntime\&quot;}: ClusterTrainingRuntime.trainer.kubeflow.org \&quot;deepspeed-distributed\&quot; not found: specified clusterTrainingRuntime must be created before the TrainJob is created&quot;,&#10;            Reason: &quot;Forbidden&quot;,&#10;            Details: nil,&#10;            Code: 403,&#10;        },&#10;    }" type="failed">[FAILED] Expected success, but got an error:
    &lt;*errors.StatusError | 0x1b5095914500&gt;: 
    admission webhook "validator.trainjob.trainer.kubeflow.org" denied the request: spec.runtimeRef: Invalid value: {"name":"deepspeed-distributed","apiGroup":"trainer.kubeflow.org","kind":"ClusterTrainingRuntime"}: ClusterTrainingRuntime.trainer.kubeflow.org "deepspeed-distributed" not found: specified clusterTrainingRuntime must be created before the TrainJob is created
    {
        ErrStatus: {
            TypeMeta: {Kind: "", APIVersion: ""},
            ListMeta: {
                SelfLink: "",
                ResourceVersion: "",
                Continue: "",
                RemainingItemCount: nil,
                ShardInfo: nil,
            },
            Status: "Failure",
            Message: "admission webhook \"validator.trainjob.trainer.kubeflow.org\" denied the request: spec.runtimeRef: Invalid value: {\"name\":\"deepspeed-distributed\",\"apiGroup\":\"trainer.kubeflow.org\",\"kind\":\"ClusterTrainingRuntime\"}: ClusterTrainingRuntime.trainer.kubeflow.org \"deepspeed-distributed\" not found: specified clusterTrainingRuntime must be created before the TrainJob is created",
            Reason: "Forbidden",
            Details: nil,
            Code: 403,
        },
    }
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:216 @ 11/02/26 22:39:22.224
</failure>
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:39:21.858
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:39:21.891 (33ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference and OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:203 @ 11/02/26 22:39:21.891
STEP: Create a TrainJob with deepspeed-distributed runtime reference and the OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:215 @ 11/02/26 22:39:21.891
END STEP: Create a TrainJob with deepspeed-distributed runtime reference and the OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:215 @ 11/02/26 22:39:22.224 (333ms)
[FAILED] Expected success, but got an error:
    &lt;*errors.StatusError | 0x1b5095914500&gt;: 
    admission webhook "validator.trainjob.trainer.kubeflow.org" denied the request: spec.runtimeRef: Invalid value: {"name":"deepspeed-distributed","apiGroup":"trainer.kubeflow.org","kind":"ClusterTrainingRuntime"}: ClusterTrainingRuntime.trainer.kubeflow.org "deepspeed-distributed" not found: specified clusterTrainingRuntime must be created before the TrainJob is created
    {
        ErrStatus: {
            TypeMeta: {Kind: "", APIVersion: ""},
            ListMeta: {
                SelfLink: "",
                ResourceVersion: "",
                Continue: "",
                RemainingItemCount: nil,
                ShardInfo: nil,
            },
            Status: "Failure",
            Message: "admission webhook \"validator.trainjob.trainer.kubeflow.org\" denied the request: spec.runtimeRef: Invalid value: {\"name\":\"deepspeed-distributed\",\"apiGroup\":\"trainer.kubeflow.org\",\"kind\":\"ClusterTrainingRuntime\"}: ClusterTrainingRuntime.trainer.kubeflow.org \"deepspeed-distributed\" not found: specified clusterTrainingRuntime must be created before the TrainJob is created",
            Reason: "Forbidden",
            Details: nil,
            Code: 403,
        },
    }
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:216 @ 11/02/26 22:39:22.224
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference and OpenMPI 4.0 image - /workspace/source/src_code/test/e2e/e2e_test.go:203 @ 11/02/26 22:39:22.224 (333ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:39:22.224
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:39:22.241 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform JAX workload should create TrainJob with JAX runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="140.27196178">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:39:22.242
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:39:22.274 (33ms)
&gt; Enter [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 11/02/26 22:39:22.274
STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 11/02/26 22:39:22.275
END STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 11/02/26 22:39:22.393 (118ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 11/02/26 22:39:22.393
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 11/02/26 22:39:23.743 (1.35s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 11/02/26 22:39:23.743
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 11/02/26 22:41:42.496 (2m18.752s)
&lt; Exit [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 11/02/26 22:41:42.496 (2m20.221s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:41:42.496
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:41:42.513 (18ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform XGBoost workload should create TrainJob with XGBoost runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="69.433521726">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:41:42.514
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:41:42.549 (35ms)
&gt; Enter [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 11/02/26 22:41:42.549
STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 11/02/26 22:41:42.549
END STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 11/02/26 22:41:42.91 (361ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 11/02/26 22:41:42.91
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 11/02/26 22:41:43.991 (1.081s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 11/02/26 22:41:43.991
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 11/02/26 22:42:51.93 (1m7.939s)
&lt; Exit [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 11/02/26 22:42:51.93 (1m9.381s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:42:51.93
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:42:51.947 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob to perform Flux workload should create TrainJob with Flux runtime reference" classname="Kubeflow Trainer E2E Suite" status="passed" time="28.701658611">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:42:51.948
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:42:51.982 (34ms)
&gt; Enter [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 11/02/26 22:42:51.982
STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 11/02/26 22:42:51.982
END STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 11/02/26 22:42:52.1 (118ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 11/02/26 22:42:52.1
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 11/02/26 22:42:53.18 (1.08s)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 11/02/26 22:42:53.18
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 11/02/26 22:43:20.633 (27.452s)
&lt; Exit [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 11/02/26 22:43:20.633 (28.651s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:20.633
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:20.649 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob with RuntimePatches should preserve user-provided manager fields" classname="Kubeflow Trainer E2E Suite" status="passed" time="0.194373766">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:20.649
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:20.687 (37ms)
&gt; Enter [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 11/02/26 22:43:20.687
STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 11/02/26 22:43:20.687
END STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 11/02/26 22:43:20.811 (124ms)
STEP: Verify user-provided Time is preserved for test.io/manager-one and Time is set for kueue.k8s.io/manager - /workspace/source/src_code/test/e2e/e2e_test.go:498 @ 11/02/26 22:43:20.811
END STEP: Verify user-provided Time is preserved for test.io/manager-one and Time is set for kueue.k8s.io/manager - /workspace/source/src_code/test/e2e/e2e_test.go:498 @ 11/02/26 22:43:20.827 (16ms)
&lt; Exit [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 11/02/26 22:43:20.827 (140ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:20.827
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:20.844 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob with RuntimePatches should update Time only for the changed patch on update" classname="Kubeflow Trainer E2E Suite" status="passed" time="1.345626731">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:20.844
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:20.878 (34ms)
&gt; Enter [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 11/02/26 22:43:20.878
STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 11/02/26 22:43:20.878
END STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 11/02/26 22:43:21 (122ms)
STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 11/02/26 22:43:21
END STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 11/02/26 22:43:21.016 (15ms)
STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 11/02/26 22:43:22.016
END STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 11/02/26 22:43:22.157 (141ms)
STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 11/02/26 22:43:22.157
END STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 11/02/26 22:43:22.172 (15ms)
&lt; Exit [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 11/02/26 22:43:22.172 (1.295s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:22.172
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:22.189 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob managed by an external controller should not be reconciled by the built-in controller" classname="Kubeflow Trainer E2E Suite" status="passed" time="15.171398878">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:22.189
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:22.223 (33ms)
&gt; Enter [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 11/02/26 22:43:22.223
STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 11/02/26 22:43:22.223
END STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 11/02/26 22:43:22.341 (118ms)
STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:640 @ 11/02/26 22:43:22.341
END STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:640 @ 11/02/26 22:43:37.342 (15.001s)
&lt; Exit [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 11/02/26 22:43:37.342 (15.119s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:37.342
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:37.361 (19ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating a TrainJob with Resource Timeouts should fail the TrainJob with DeadlineExceeded when active timeout expires" classname="Kubeflow Trainer E2E Suite" status="passed" time="10.051183184">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:37.361
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:37.393 (32ms)
&gt; Enter [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 11/02/26 22:43:37.393
STEP: Waiting for TrainJob to fail due to deadline - /workspace/source/src_code/test/e2e/e2e_test.go:667 @ 11/02/26 22:43:37.514
STEP: Ensuring the underlying JobSet is deleted - /workspace/source/src_code/test/e2e/e2e_test.go:674 @ 11/02/26 22:43:47.38
&lt; Exit [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 11/02/26 22:43:47.395 (10.002s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:47.395
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:47.412 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Creating TrainJob with runtime status server instrumentation should inject runtime configuration which allows the runtime status endpoint to be called" classname="Kubeflow Trainer E2E Suite" status="skipped" time="0">
              <skipped message="skipped" />
          </testcase>
          <testcase name="[It] TrainJob e2e when Updating a runtime a suspended TrainJob should use the original runtime configuration and not pick up the new configuration TrainingRuntime" classname="Kubeflow Trainer E2E Suite" status="passed" time="2.697111149">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:47.412
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:47.447 (35ms)
&gt; Enter [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 11/02/26 22:43:47.447
STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 22:43:47.447
END STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 22:43:47.629 (182ms)
STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 22:43:47.63
END STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 22:43:47.75 (120ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 22:43:47.75
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 22:43:48.564 (814ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 22:43:48.564
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 22:43:48.701 (137ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 22:43:48.701
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 22:43:49.249 (548ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 22:43:49.249
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 22:43:49.336 (87ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 22:43:49.336
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 22:43:49.474 (138ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 22:43:49.474
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 22:43:50.023 (549ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 22:43:50.023
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 22:43:50.073 (50ms)
&lt; Exit [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 11/02/26 22:43:50.073 (2.626s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:50.073
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:50.092 (19ms)
&gt; Enter [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 22:43:50.092
&lt; Exit [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 22:43:50.109 (17ms)
</system-err>
          </testcase>
          <testcase name="[It] TrainJob e2e when Updating a runtime a suspended TrainJob should use the original runtime configuration and not pick up the new configuration ClusterTrainingRuntime" classname="Kubeflow Trainer E2E Suite" status="passed" time="2.961536716">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:50.109
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/02/26 22:43:50.145 (35ms)
&gt; Enter [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 11/02/26 22:43:50.145
STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 22:43:50.145
END STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/02/26 22:43:50.317 (172ms)
STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 22:43:50.317
END STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/02/26 22:43:50.436 (118ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 22:43:50.436
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/02/26 22:43:51.249 (813ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 22:43:51.249
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/02/26 22:43:51.384 (135ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 22:43:51.384
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/02/26 22:43:51.931 (547ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 22:43:51.931
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/02/26 22:43:52.015 (83ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 22:43:52.015
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/02/26 22:43:52.149 (135ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 22:43:52.149
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/02/26 22:43:52.964 (815ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 22:43:52.964
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/02/26 22:43:53.012 (48ms)
&lt; Exit [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 11/02/26 22:43:53.012 (2.867s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:53.012
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/02/26 22:43:53.045 (33ms)
&gt; Enter [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 22:43:53.045
&lt; Exit [DeferCleanup (Each)] a suspended TrainJob should use the original runtime configuration and not pick up the new configuration - /workspace/source/src_code/test/e2e/e2e_test.go:801 @ 11/02/26 22:43:53.071 (26ms)
</system-err>
          </testcase>
      </testsuite>
      <testsuite name="" package="/workspace/source/src_code/test/e2e/rhai" tests="0" disabled="0" skipped="0" errors="0" failures="0" time="0" timestamp="0001-01-01T00:00:00">
          <properties>
              <property name="SuiteSucceeded" value="false" />
              <property name="SuiteHasProgrammaticFocus" value="false" />
              <property name="SpecialSuiteFailureReason" value="Suite did not run because prior suites failed and --keep-going is not set" />
              <property name="SuiteLabels" value="[]" />
              <property name="SuiteSemVerConstraints" value="[]" />
              <property name="SuiteComponentSemVerConstraints" value="[]" />
              <property name="RandomSeed" value="1793658850" />
              <property name="RandomizeAllSpecs" value="false" />
              <property name="LabelFilter" value="" />
              <property name="SemVerFilter" value="" />
              <property name="FocusStrings" value="" />
              <property name="SkipStrings" value="runtime status server instrumentation" />
              <property name="FocusFiles" value="" />
              <property name="SkipFiles" value="" />
              <property name="FailOnPending" value="false" />
              <property name="FailOnEmpty" value="false" />
              <property name="FailFast" value="false" />
              <property name="FlakeAttempts" value="0" />
              <property name="DryRun" value="false" />
              <property name="ParallelTotal" value="1" />
              <property name="OutputInterceptorMode" value="" />
          </properties>
      </testsuite>
  <testsuite tests="3" failures="0" time="1.44" name="trainer" timestamp="2026-11-02T22:44:40Z" errors="0" skipped="0">
		<properties>
			<property name="go.version" value="go1.26.7 (Red Hat 1.26.7-1.el9_8) linux/amd64" />
		</properties>
		<testcase classname="tests/trainer" name="TestOpenMPICudaClusterTrainingRuntime" time="0.030000" />
		<testcase classname="tests/trainer" name="TestDefaultTrainingHubRuntimesMatchDefaultClusterRuntimes" time="0.030000" />
		<testcase classname="tests/trainer" name="TestDraFieldsOnTrainJobReachPods" time="1.380000" />
	</testsuite>
<testsuite tests="7" failures="0" time="912.12" name="trainer" timestamp="2026-11-02T22:44:44Z" errors="0" skipped="0">
		<properties>
			<property name="go.version" value="go1.26.7 (Red Hat 1.26.7-1.el9_8) linux/amd64" />
		</properties>
		<testcase classname="tests/trainer" name="TestRunTrainJobWithDefaultClusterTrainingRuntimes" time="527.830000" />
		<testcase classname="tests/trainer" name="TestJobSetWorkflow" time="123.100000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdk" time="57.190000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdkKueueIntegration" time="59.620000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadPreemptionSuspendsTrainJob" time="5.880000" />
		<testcase classname="tests/trainer" name="TestKueueSchedulingReachesTrainJobPods" time="2.670000" />
		<testcase classname="tests/trainer" name="TestMultiNodeOpenMPICpuTrainJob" time="135.830000" />
	</testsuite>
<testsuite tests="15" failures="0" time="2683.4" name="trainer" timestamp="2026-11-02T23:00:10Z" errors="0" skipped="0">
		<properties>
			<property name="go.version" value="go1.26.7 (Red Hat 1.26.7-1.el9_8) linux/amd64" />
		</properties>
		<testcase classname="tests/trainer" name="TestFailedJobSetWorkflow" time="11.950000" />
		<testcase classname="tests/trainer" name="TestRhaiTrainingProgressionCPU" time="545.450000" />
		<testcase classname="tests/trainer" name="TestRhaiJitCheckpointingCPU" time="627.420000" />
		<testcase classname="tests/trainer" name="TestRhaiFeaturesCPU" time="632.560000" />
		<testcase classname="tests/trainer" name="TestRhaiS3CheckpointingCPU" time="642.250000" />
		<testcase classname="tests/trainer" name="TestPyTorchDDPMultiNodeMultiCPUWithTorchCuda28" time="152.760000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadInadmissibleWithNonExistentLocalQueue" time="1.660000" />
		<testcase classname="tests/trainer" name="TestTrainerSecureServing" time="1.400000" />
		<testcase classname="tests/trainer" name="TestTrainerPrometheusScrape" time="0.960000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToMetrics" time="16.490000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToHealth" time="6.390000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToStatusServer" time="8.410000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToUnpublishedPort" time="8.340000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToWorkloadPort" time="11.650000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherWorkloadsToWorkloadPort" time="15.710000" />
	</testsuite>
<testsuite tests="0" failures="0" time="0" name="trainer" timestamp="2026-11-02T23:44:56Z" errors="0" skipped="0">
		<properties>
			<property name="go.version" value="go1.26.7 (Red Hat 1.26.7-1.el9_8) linux/amd64" />
		</properties>
	</testsuite>
</testsuites>