<?xml version='1.0' encoding='utf-8'?>
<testsuites tests="41" failures="1" errors="0" skipped="4" time="3904.812"><testsuite name="Kubeflow Trainer E2E Suite" package="/workspace/source/src_code/test/e2e" tests="16" disabled="2" skipped="4" errors="0" failures="1" time="526.302" timestamp="2026-11-03T06:07:12">
          <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="1793685965" />
              <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="0.001556661">
              <system-err>&gt; Enter [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/03/26 06:07:12.462
&lt; Exit [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 11/03/26 06:07:12.464 (2ms)
</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="266.683832168">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:07:12.464
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:07:12.588 (123ms)
&gt; Enter [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/03/26 06:07:12.588
STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/03/26 06:07:12.588
END STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 11/03/26 06:07:12.769 (181ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/03/26 06:07:12.769
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 11/03/26 06:07:13.334 (565ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 11/03/26 06:07:13.334
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 11/03/26 06:11:39.132 (4m25.798s)
&lt; Exit [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 11/03/26 06:11:39.132 (4m26.544s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:11:39.132
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:11:39.148 (16ms)
</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="0.067992936">
              <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 @ 11/03/26 06:11:39.148
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:11:39.19 (41ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/03/26 06:11:39.19
[SKIPPED] MPI runtime image is not available
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:147 @ 11/03/26 06:11:39.19
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 11/03/26 06:11:39.19 (0s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:11:39.19
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:11:39.216 (27ms)
</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="0.20253533">
              <failure message="Expected success, but got an error:&#10;    &lt;*errors.StatusError | 0x2f011bc0b180&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 | 0x2f011bc0b180&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 @ 11/03/26 06:11:39.405
</failure>
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:11:39.216
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:11:39.256 (39ms)
&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 @ 11/03/26 06:11:39.256
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 @ 11/03/26 06:11:39.256
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 @ 11/03/26 06:11:39.404 (149ms)
[FAILED] Expected success, but got an error:
    &lt;*errors.StatusError | 0x2f011bc0b180&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 @ 11/03/26 06:11:39.405
&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 @ 11/03/26 06:11:39.405 (149ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:11:39.405
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:11:39.419 (14ms)
</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="153.282432653">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:11:39.419
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:11:39.454 (35ms)
&gt; Enter [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 11/03/26 06:11:39.454
STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 11/03/26 06:11:39.454
END STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 11/03/26 06:11:39.515 (60ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 11/03/26 06:11:39.515
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 11/03/26 06:11:40.318 (803ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 11/03/26 06:11:40.318
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 11/03/26 06:14:12.687 (2m32.369s)
&lt; Exit [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 11/03/26 06:14:12.687 (2m33.233s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:14:12.687
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:14:12.702 (14ms)
</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="45.162554331">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:14:12.702
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:14:12.731 (30ms)
&gt; Enter [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 11/03/26 06:14:12.731
STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 11/03/26 06:14:12.731
END STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 11/03/26 06:14:12.864 (133ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 11/03/26 06:14:12.864
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 11/03/26 06:14:13.405 (541ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 11/03/26 06:14:13.405
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 11/03/26 06:14:57.85 (44.445s)
&lt; Exit [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 11/03/26 06:14:57.85 (45.119s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:14:57.85
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:14:57.864 (14ms)
</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="31.927383918">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:14:57.865
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:14:57.892 (27ms)
&gt; Enter [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 11/03/26 06:14:57.892
STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 11/03/26 06:14:57.892
END STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 11/03/26 06:14:57.94 (48ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 11/03/26 06:14:57.94
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 11/03/26 06:14:58.481 (540ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 11/03/26 06:14:58.481
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 11/03/26 06:15:29.777 (31.296s)
&lt; Exit [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 11/03/26 06:15:29.777 (31.885s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:29.777
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:29.792 (15ms)
</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="0.110010721">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:29.792
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:29.824 (32ms)
&gt; Enter [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 11/03/26 06:15:29.824
STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 11/03/26 06:15:29.824
END STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 11/03/26 06:15:29.874 (50ms)
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 @ 11/03/26 06:15:29.874
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 @ 11/03/26 06:15:29.886 (12ms)
&lt; Exit [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 11/03/26 06:15:29.886 (62ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:29.886
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:29.902 (16ms)
</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="1.183542899">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:29.902
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:29.928 (26ms)
&gt; Enter [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 11/03/26 06:15:29.928
STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 11/03/26 06:15:29.928
END STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 11/03/26 06:15:29.978 (50ms)
STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 11/03/26 06:15:29.978
END STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 11/03/26 06:15:29.99 (12ms)
STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 11/03/26 06:15:30.99
END STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 11/03/26 06:15:31.059 (69ms)
STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 11/03/26 06:15:31.059
END STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 11/03/26 06:15:31.072 (13ms)
&lt; Exit [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 11/03/26 06:15:31.072 (1.143s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:31.072
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:31.086 (14ms)
</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="15.097544241">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:31.086
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:31.115 (29ms)
&gt; Enter [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 11/03/26 06:15:31.115
STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 11/03/26 06:15:31.115
END STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 11/03/26 06:15:31.169 (54ms)
STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:640 @ 11/03/26 06:15:31.169
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 @ 11/03/26 06:15:46.169 (15s)
&lt; Exit [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 11/03/26 06:15:46.169 (15.054s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:46.169
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:46.183 (14ms)
</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="10.102913026">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:46.183
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:46.214 (31ms)
&gt; Enter [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 11/03/26 06:15:46.214
STEP: Waiting for TrainJob to fail due to deadline - /workspace/source/src_code/test/e2e/e2e_test.go:667 @ 11/03/26 06:15:46.262
STEP: Ensuring the underlying JobSet is deleted - /workspace/source/src_code/test/e2e/e2e_test.go:674 @ 11/03/26 06:15:56.26
&lt; Exit [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 11/03/26 06:15:56.272 (10.058s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:56.272
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:56.286 (14ms)
</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="1.224264246">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:56.286
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:56.318 (31ms)
&gt; Enter [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 11/03/26 06:15:56.318
STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/03/26 06:15:56.318
END STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/03/26 06:15:56.392 (75ms)
STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/03/26 06:15:56.393
END STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/03/26 06:15:56.44 (47ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/03/26 06:15:56.44
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/03/26 06:15:56.714 (275ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/03/26 06:15:56.714
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/03/26 06:15:56.775 (61ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/03/26 06:15:56.775
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/03/26 06:15:57.05 (275ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/03/26 06:15:57.05
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/03/26 06:15:57.095 (45ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/03/26 06:15:57.095
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/03/26 06:15:57.16 (65ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/03/26 06:15:57.16
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/03/26 06:15:57.435 (275ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/03/26 06:15:57.435
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/03/26 06:15:57.477 (42ms)
&lt; Exit [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 11/03/26 06:15:57.477 (1.159s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:57.477
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:57.495 (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 @ 11/03/26 06:15:57.495
&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 @ 11/03/26 06:15:57.511 (15ms)
</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="1.255346122">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:57.511
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 11/03/26 06:15:57.545 (34ms)
&gt; Enter [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 11/03/26 06:15:57.545
STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/03/26 06:15:57.545
END STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 11/03/26 06:15:57.636 (91ms)
STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/03/26 06:15:57.636
END STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 11/03/26 06:15:57.688 (52ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/03/26 06:15:57.688
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 11/03/26 06:15:57.963 (275ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/03/26 06:15:57.963
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 11/03/26 06:15:58.034 (71ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/03/26 06:15:58.034
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 11/03/26 06:15:58.31 (277ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/03/26 06:15:58.311
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 11/03/26 06:15:58.355 (45ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/03/26 06:15:58.355
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 11/03/26 06:15:58.417 (62ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/03/26 06:15:58.417
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 11/03/26 06:15:58.692 (275ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/03/26 06:15:58.692
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 11/03/26 06:15:58.73 (38ms)
&lt; Exit [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 11/03/26 06:15:58.73 (1.185s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:58.73
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 11/03/26 06:15:58.75 (20ms)
&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 @ 11/03/26 06:15:58.75
&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 @ 11/03/26 06:15:58.766 (16ms)
</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="1793685965" />
              <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="1.27" name="trainer" timestamp="2026-11-03T06:17:07Z" 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="1.210000" />
	</testsuite>
<testsuite tests="7" failures="0" time="1125.14" name="trainer" timestamp="2026-11-03T06:17:12Z" 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="455.340000" />
		<testcase classname="tests/trainer" name="TestJobSetWorkflow" time="95.670000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdk" time="174.630000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdkKueueIntegration" time="112.620000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadPreemptionSuspendsTrainJob" time="259.560000" />
		<testcase classname="tests/trainer" name="TestKueueSchedulingReachesTrainJobPods" time="1.510000" />
		<testcase classname="tests/trainer" name="TestMultiNodeOpenMPICpuTrainJob" time="25.810000" />
	</testsuite>
<testsuite tests="15" failures="0" time="2252.1" name="trainer" timestamp="2026-11-03T06:36:00Z" 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="13.510000" />
		<testcase classname="tests/trainer" name="TestRhaiTrainingProgressionCPU" time="494.170000" />
		<testcase classname="tests/trainer" name="TestRhaiJitCheckpointingCPU" time="552.650000" />
		<testcase classname="tests/trainer" name="TestRhaiFeaturesCPU" time="538.550000" />
		<testcase classname="tests/trainer" name="TestRhaiS3CheckpointingCPU" time="528.460000" />
		<testcase classname="tests/trainer" name="TestPyTorchDDPMultiNodeMultiCPUWithTorchCuda28" time="66.330000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadInadmissibleWithNonExistentLocalQueue" time="1.190000" />
		<testcase classname="tests/trainer" name="TestTrainerSecureServing" time="0.680000" />
		<testcase classname="tests/trainer" name="TestTrainerPrometheusScrape" time="0.350000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToMetrics" time="10.390000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToHealth" time="8.330000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToStatusServer" time="8.340000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToUnpublishedPort" time="8.250000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToWorkloadPort" time="9.510000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherWorkloadsToWorkloadPort" time="11.390000" />
	</testsuite>
<testsuite tests="0" failures="0" time="0" name="trainer" timestamp="2026-11-03T07:13:35Z" 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>