<?xml version='1.0' encoding='utf-8'?>
<testsuites tests="41" failures="2" errors="0" skipped="4" time="4366.293"><testsuite name="Kubeflow Trainer E2E Suite" package="/workspace/source/src_code/test/e2e" tests="16" disabled="2" skipped="4" errors="0" failures="2" time="892.373" timestamp="2026-10-30T20:12:35">
          <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="1793391084" />
              <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="0.001445297">
              <system-err>&gt; Enter [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 10/30/26 20:12:35.407
&lt; Exit [BeforeSuite] TOP-LEVEL - /workspace/source/src_code/test/e2e/suite_test.go:43 @ 10/30/26 20:12:35.409 (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="failed" time="600.553168536">
              <failure message="Timed out after 600.000s.&#10;The function passed to Eventually failed at /workspace/source/src_code/test/e2e/e2e_test.go:120 with:&#10;Expected object to be comparable, diff:   []v1.Condition(&#10;- &#09;nil,&#10;+ &#09;{&#10;+ &#09;&#09;{&#10;+ &#09;&#09;&#09;Type:    &quot;Complete&quot;,&#10;+ &#09;&#09;&#09;Status:  &quot;True&quot;,&#10;+ &#09;&#09;&#09;Reason:  &quot;AllJobsCompleted&quot;,&#10;+ &#09;&#09;&#09;Message: &quot;jobset completed successfully&quot;,&#10;+ &#09;&#09;},&#10;+ &#09;},&#10;  )&#10;" type="failed">[FAILED] Timed out after 600.000s.
The function passed to Eventually failed at /workspace/source/src_code/test/e2e/e2e_test.go:120 with:
Expected object to be comparable, diff:   []v1.Condition(
- 	nil,
+ 	{
+ 		{
+ 			Type:    "Complete",
+ 			Status:  "True",
+ 			Reason:  "AllJobsCompleted",
+ 			Message: "jobset completed successfully",
+ 		},
+ 	},
  )
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:138 @ 10/30/26 20:22:35.941
</failure>
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:12:35.409
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:12:35.576 (167ms)
&gt; Enter [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 10/30/26 20:12:35.576
STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 10/30/26 20:12:35.577
END STEP: Create a TrainJob with torch-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:93 @ 10/30/26 20:12:35.652 (76ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 10/30/26 20:12:35.652
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:98 @ 10/30/26 20:12:35.94 (288ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 10/30/26 20:12:35.94
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:116 @ 10/30/26 20:22:35.941 (10m0.001s)
[FAILED] Timed out after 600.000s.
The function passed to Eventually failed at /workspace/source/src_code/test/e2e/e2e_test.go:120 with:
Expected object to be comparable, diff:   []v1.Condition(
- 	nil,
+ 	{
+ 		{
+ 			Type:    "Complete",
+ 			Status:  "True",
+ 			Reason:  "AllJobsCompleted",
+ 			Message: "jobset completed successfully",
+ 		},
+ 	},
  )
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:138 @ 10/30/26 20:22:35.941
&lt; Exit [It] should create TrainJob with PyTorch runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:84 @ 10/30/26 20:22:35.941 (10m0.365s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:22:35.941
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:22:35.962 (21ms)
</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="0.059738105">
              <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 @ 10/30/26 20:22:35.962
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:22:36.002 (39ms)
&gt; Enter [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 10/30/26 20:22:36.002
[SKIPPED] MPI runtime image is not available
In [It] at: /workspace/source/src_code/test/e2e/e2e_test.go:147 @ 10/30/26 20:22:36.002
&lt; Exit [It] should create TrainJob with DeepSpeed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:145 @ 10/30/26 20:22:36.002 (0s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:22:36.002
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:22:36.022 (20ms)
</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="0.127570251">
              <failure message="Expected success, but got an error:&#10;    &lt;*errors.StatusError | 0x24215ef16e60&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 | 0x24215ef16e60&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 @ 10/30/26 20:22:36.13
</failure>
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:22:36.022
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:22:36.061 (38ms)
&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 @ 10/30/26 20:22:36.061
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 @ 10/30/26 20:22:36.061
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 @ 10/30/26 20:22:36.129 (69ms)
[FAILED] Expected success, but got an error:
    &lt;*errors.StatusError | 0x24215ef16e60&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 @ 10/30/26 20:22:36.13
&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 @ 10/30/26 20:22:36.13 (69ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:22:36.13
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:22:36.15 (20ms)
</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="116.000596071">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:22:36.15
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:22:36.19 (40ms)
&gt; Enter [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 10/30/26 20:22:36.19
STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 10/30/26 20:22:36.19
END STEP: Create a TrainJob with jax-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:265 @ 10/30/26 20:22:36.216 (27ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 10/30/26 20:22:36.216
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:270 @ 10/30/26 20:22:36.503 (286ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 10/30/26 20:22:36.503
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:288 @ 10/30/26 20:24:32.13 (1m55.627s)
&lt; Exit [It] should create TrainJob with JAX runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:259 @ 10/30/26 20:24:32.13 (1m55.941s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:24:32.13
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:24:32.151 (20ms)
</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="120.249954497">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:24:32.151
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:24:32.191 (40ms)
&gt; Enter [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 10/30/26 20:24:32.191
STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 10/30/26 20:24:32.191
END STEP: Create a TrainJob with xgboost-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:323 @ 10/30/26 20:24:32.265 (74ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 10/30/26 20:24:32.265
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:328 @ 10/30/26 20:24:32.561 (296ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 10/30/26 20:24:32.561
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:346 @ 10/30/26 20:26:32.366 (1m59.805s)
&lt; Exit [It] should create TrainJob with XGBoost runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:317 @ 10/30/26 20:26:32.366 (2m0.175s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:26:32.366
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:26:32.401 (35ms)
</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="27.000096277">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:26:32.402
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:26:32.452 (50ms)
&gt; Enter [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 10/30/26 20:26:32.452
STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 10/30/26 20:26:32.452
END STEP: Create a TrainJob with flux-distributed runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:393 @ 10/30/26 20:26:32.532 (81ms)
STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 10/30/26 20:26:32.533
END STEP: Wait for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:397 @ 10/30/26 20:26:33.086 (554ms)
STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 10/30/26 20:26:33.086
END STEP: Wait for TrainJob to be in Succeeded status with all jobs succeeded - /workspace/source/src_code/test/e2e/e2e_test.go:414 @ 10/30/26 20:26:59.382 (26.296s)
&lt; Exit [It] should create TrainJob with Flux runtime reference - /workspace/source/src_code/test/e2e/e2e_test.go:374 @ 10/30/26 20:26:59.382 (26.931s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:26:59.382
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:26:59.402 (19ms)
</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="0.111006132">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:26:59.402
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:26:59.439 (37ms)
&gt; Enter [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 10/30/26 20:26:59.439
STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 10/30/26 20:26:59.439
END STEP: Create a TrainJob with RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:494 @ 10/30/26 20:26:59.477 (38ms)
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 @ 10/30/26 20:26:59.477
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 @ 10/30/26 20:26:59.494 (18ms)
&lt; Exit [It] should preserve user-provided manager fields - /workspace/source/src_code/test/e2e/e2e_test.go:442 @ 10/30/26 20:26:59.494 (56ms)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:26:59.494
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:26:59.513 (19ms)
</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="1.198082656">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:26:59.513
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:26:59.558 (45ms)
&gt; Enter [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 10/30/26 20:26:59.558
STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 10/30/26 20:26:59.558
END STEP: Create a suspended TrainJob with two RuntimePatches - /workspace/source/src_code/test/e2e/e2e_test.go:566 @ 10/30/26 20:26:59.589 (31ms)
STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 10/30/26 20:26:59.589
END STEP: Record the original Time values and verify user-provided Time is preserved - /workspace/source/src_code/test/e2e/e2e_test.go:571 @ 10/30/26 20:26:59.606 (17ms)
STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 10/30/26 20:27:00.606
END STEP: Update the second RuntimePatch and add two new patches - /workspace/source/src_code/test/e2e/e2e_test.go:588 @ 10/30/26 20:27:00.673 (67ms)
STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 10/30/26 20:27:00.673
END STEP: Verify Time behaviour for all patches after update - /workspace/source/src_code/test/e2e/e2e_test.go:607 @ 10/30/26 20:27:00.69 (17ms)
&lt; Exit [It] should update Time only for the changed patch on update - /workspace/source/src_code/test/e2e/e2e_test.go:512 @ 10/30/26 20:27:00.69 (1.132s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:00.69
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:00.711 (21ms)
</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="15.088994759">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:00.712
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:00.749 (38ms)
&gt; Enter [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 10/30/26 20:27:00.749
STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 10/30/26 20:27:00.749
END STEP: Create a TrainJob managed by MultiKueue - /workspace/source/src_code/test/e2e/e2e_test.go:636 @ 10/30/26 20:27:00.779 (30ms)
STEP: Ensuring the built-in controller neither creates a JobSet nor sets any status - /workspace/source/src_code/test/e2e/e2e_test.go:640 @ 10/30/26 20:27:00.779
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 @ 10/30/26 20:27:15.779 (15s)
&lt; Exit [It] should not be reconciled by the built-in controller - /workspace/source/src_code/test/e2e/e2e_test.go:629 @ 10/30/26 20:27:15.779 (15.03s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:15.779
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:15.801 (21ms)
</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="9.271284138">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:15.801
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:15.84 (39ms)
&gt; Enter [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 10/30/26 20:27:15.84
STEP: Waiting for TrainJob to fail due to deadline - /workspace/source/src_code/test/e2e/e2e_test.go:667 @ 10/30/26 20:27:15.868
STEP: Ensuring the underlying JobSet is deleted - /workspace/source/src_code/test/e2e/e2e_test.go:674 @ 10/30/26 20:27:25.029
&lt; Exit [It] should fail the TrainJob with DeadlineExceeded when active timeout expires - /workspace/source/src_code/test/e2e/e2e_test.go:652 @ 10/30/26 20:27:25.046 (9.206s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:25.046
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:25.072 (27ms)
</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="1.215835755">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:25.072
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:25.109 (37ms)
&gt; Enter [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 10/30/26 20:27:25.109
STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 20:27:25.11
END STEP: Creating a TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 20:27:25.168 (58ms)
STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 20:27:25.168
END STEP: Creating a TrainJob that references the TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 20:27:25.195 (27ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 20:27:25.195
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 20:27:25.482 (286ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 20:27:25.482
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 20:27:25.532 (50ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 20:27:25.532
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 20:27:25.818 (286ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 20:27:25.818
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 20:27:25.862 (45ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 20:27:25.863
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 20:27:25.91 (47ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 20:27:25.91
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 20:27:26.195 (285ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 20:27:26.195
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 20:27:26.249 (54ms)
&lt; Exit [It] TrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:905 @ 10/30/26 20:27:26.249 (1.139s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:26.249
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:26.268 (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 @ 10/30/26 20:27:26.268
&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 @ 10/30/26 20:27:26.288 (20ms)
</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="1.495067867">
              <system-err>&gt; Enter [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:26.288
&lt; Exit [BeforeEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:61 @ 10/30/26 20:27:26.325 (36ms)
&gt; Enter [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 10/30/26 20:27:26.325
STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 20:27:26.325
END STEP: Creating a ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:797 @ 10/30/26 20:27:26.374 (49ms)
STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 20:27:26.374
END STEP: Creating a TrainJob that references the ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:810 @ 10/30/26 20:27:26.403 (29ms)
STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 20:27:26.403
END STEP: Waiting for TrainJob jobs to become active - /workspace/source/src_code/test/e2e/e2e_test.go:814 @ 10/30/26 20:27:26.687 (284ms)
STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 20:27:26.687
END STEP: Pausing the TrainJob - /workspace/source/src_code/test/e2e/e2e_test.go:825 @ 10/30/26 20:27:26.735 (47ms)
STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 20:27:26.735
END STEP: Waiting for TrainJob to be suspended - /workspace/source/src_code/test/e2e/e2e_test.go:834 @ 10/30/26 20:27:27.02 (285ms)
STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 20:27:27.02
END STEP: Updating the runtime with a new container image - /workspace/source/src_code/test/e2e/e2e_test.go:847 @ 10/30/26 20:27:27.063 (43ms)
STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 20:27:27.063
END STEP: Restarting the TrainJob by unpausing it - /workspace/source/src_code/test/e2e/e2e_test.go:868 @ 10/30/26 20:27:27.11 (47ms)
STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 20:27:27.11
END STEP: Verifying the TrainJob jobs become active after resuming - /workspace/source/src_code/test/e2e/e2e_test.go:879 @ 10/30/26 20:27:27.396 (286ms)
STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 20:27:27.396
END STEP: Verifying the Runtime snapshot is garbage collected - /workspace/source/src_code/test/e2e/e2e_test.go:891 @ 10/30/26 20:27:27.738 (342ms)
&lt; Exit [It] ClusterTrainingRuntime - /workspace/source/src_code/test/e2e/e2e_test.go:917 @ 10/30/26 20:27:27.738 (1.413s)
&gt; Enter [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:27.738
&lt; Exit [AfterEach] TrainJob e2e - /workspace/source/src_code/test/e2e/e2e_test.go:76 @ 10/30/26 20:27:27.758 (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 @ 10/30/26 20:27:27.758
&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 @ 10/30/26 20:27:27.783 (25ms)
</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="1793391084" />
              <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="1.34" name="trainer" timestamp="2026-10-30T20:28:26Z" 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="0.040000" />
		<testcase classname="tests/trainer" name="TestDefaultTrainingHubRuntimesMatchDefaultClusterRuntimes" time="0.030000" />
		<testcase classname="tests/trainer" name="TestDraFieldsOnTrainJobReachPods" time="1.270000" />
	</testsuite>
<testsuite tests="7" failures="0" time="1183.3" name="trainer" timestamp="2026-10-30T20:28:30Z" 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="907.230000" />
		<testcase classname="tests/trainer" name="TestJobSetWorkflow" time="90.820000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdk" time="49.040000" />
		<testcase classname="tests/trainer" name="TestKubeflowSdkKueueIntegration" time="48.400000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadPreemptionSuspendsTrainJob" time="3.550000" />
		<testcase classname="tests/trainer" name="TestKueueSchedulingReachesTrainJobPods" time="1.350000" />
		<testcase classname="tests/trainer" name="TestMultiNodeOpenMPICpuTrainJob" time="82.910000" />
	</testsuite>
<testsuite tests="15" failures="0" time="2289.28" name="trainer" timestamp="2026-10-30T20:48:18Z" 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="14.510000" />
		<testcase classname="tests/trainer" name="TestRhaiTrainingProgressionCPU" time="510.390000" />
		<testcase classname="tests/trainer" name="TestRhaiJitCheckpointingCPU" time="537.360000" />
		<testcase classname="tests/trainer" name="TestRhaiFeaturesCPU" time="548.640000" />
		<testcase classname="tests/trainer" name="TestRhaiS3CheckpointingCPU" time="554.140000" />
		<testcase classname="tests/trainer" name="TestPyTorchDDPMultiNodeMultiCPUWithTorchCuda28" time="65.680000" />
		<testcase classname="tests/trainer" name="TestKueueWorkloadInadmissibleWithNonExistentLocalQueue" time="1.230000" />
		<testcase classname="tests/trainer" name="TestTrainerSecureServing" time="0.550000" />
		<testcase classname="tests/trainer" name="TestTrainerPrometheusScrape" time="0.470000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToMetrics" time="10.380000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToHealth" time="6.340000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToStatusServer" time="10.380000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToUnpublishedPort" time="8.290000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherNamespacesToWorkloadPort" time="9.480000" />
		<testcase classname="tests/trainer" name="TestTrainerNetworkPolicyBlocksIngressFromOtherWorkloadsToWorkloadPort" time="11.440000" />
	</testsuite>
<testsuite tests="0" failures="0" time="0" name="trainer" timestamp="2026-10-30T21:26:30Z" 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>