xpk 0.17.2__tar.gz → 1.0.0__tar.gz

{xpk-0.17.2 → xpk-1.0.0}/.github/actions/setup-test-env/action.yml

@@ -44,7 +44,6 @@ runs:
       run: gcloud auth configure-docker --quiet
       shell: bash
     - uses: ./.github/actions/install-kueue
-    - uses: ./.github/actions/install-kjob
     - name: Install XPK
       run: pip install dist/xpk-*.whl
       shell: bash

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/build_tests.yaml

@@ -49,14 +49,13 @@ jobs:
         lookup-only: true
     - name: install dependencies
       if : steps.check-cache.outputs.cache-hit != 'true'
-      run: make install-dev && cp ./bin/kubectl-kueue /usr/local/bin/kubectl-kueue && cp ./bin/kubectl-kjob /usr/local/bin/kubectl-kjob
+      run: make install-dev && cp ./bin/kubectl-kueue /usr/local/bin/kubectl-kueue
     - name: Cache dependencies
       if : steps.check-cache.outputs.cache-hit != 'true'
       uses: actions/cache/save@v3
       with:
         path: |
           /usr/local/bin/kubectl-kueue
-          /usr/local/bin/kubectl-kjob
           ~/.cache/pip
           ${{env.pythonLocation}}
         key: xpk-deps-${{ matrix.python-version }}-${{github.run_id}}-${{github.run_attempt}}

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/integration_basic_cluster_create.yaml

@@ -152,62 +152,6 @@ jobs:
               run: xpk info --cluster $TPU_CLUSTER_NAME --zone=us-central2-b
             - name: Delete the workload on the cluster
               run: xpk workload delete --workload $WORKLOAD_NAME --cluster $TPU_CLUSTER_NAME --zone=us-central2-b
-            - name: Create test script to execute in batch
-              run: echo -e '#!/bin/bash \n#SBATCH --unknown-flag=value\n echo "Hello world from a test script!"' > batch.sh
-            - name: Run a batch job on the cluster
-              run: xpk batch --cluster $TPU_CLUSTER_NAME --zone=us-central2-b batch.sh --ignore-unknown-flags --array 1-5 --nodes 2 --ntasks 3
-            - name: List out the jobs on the cluster
-              run: xpk job ls --cluster $TPU_CLUSTER_NAME --zone=us-central2-b | grep 'xpk-def-app-profile-slurm-'
-            - name: Get created job name
-              run: |
-                  JOB_NAME=$(xpk job ls --cluster $TPU_CLUSTER_NAME --zone=us-central2-b | grep 'xpk-def-app-profile-slurm-' | grep 'multislice-queue' | head -1 | awk '{print $1}')
-                  echo "JOB_NAME=${JOB_NAME}" >> $GITHUB_ENV
-            - name: Check job spec
-              run: |
-                  job_spec=$(kubectl get job ${JOB_NAME} -o jsonpath='{.spec}')
-                  echo "$job_spec" | grep '"completions":2'
-                  echo "$job_spec" | grep '"parallelism":2'
-                  echo "$job_spec" | jq '.template.spec.containers | length' | grep 3
-            - name: Get job info for the last job created on the cluster
-              run: xpk job info ${JOB_NAME} --cluster $TPU_CLUSTER_NAME --zone=us-central2-b | grep -e "Entrypoint environment variables template:" -e "Job name:" -e "Labels:" -e "Mounts:" -e "Pods:" -e "Profile:" -e "Script name:" | wc -l | grep "7"
-            - name: Cancel the batch job on the cluster
-              run: xpk job cancel ${JOB_NAME} --cluster $TPU_CLUSTER_NAME --zone=us-central2-b | grep "job.batch/${JOB_NAME} deleted"
-            - name: Create shell and exit it immediately
-              run: |
-                  cat <<EOF > create-shell.exp
-                  #!/usr/bin/expect
-                  set timeout 180
-                  spawn sh -c "xpk shell --cluster $TPU_CLUSTER_NAME --zone=us-central2-b | tee shell.log"
-                  send "\n"
-                  expect {
-                    "/ # " {
-                        send "exit\n"
-                        # Wait for EOF after exit
-                        expect eof
-                        exit 0
-                    }
-                    timeout {
-                        puts "Timed out waiting for pod to be running"
-                        exit 1
-                    }
-                    eof {
-                        puts "Unexpected EOF before getting prompt"
-                        exit 1
-                    }
-                  }
-                  EOF
-                  chmod +x ./create-shell.exp
-                  expect ./create-shell.exp
-            - name: Check if shell exists and is running
-              run: |
-                  pod_name=$(grep 'waiting for pod' shell.log | awk -F'"' '{print $2}')
-                  kubectl wait --for='jsonpath={.status.conditions[?(@.type=="Ready")].status}=True' --timeout=1m pod/${pod_name}
-            - name: Stop the shell
-              run: xpk shell stop --cluster $TPU_CLUSTER_NAME --zone=us-central2-b
-            - name: Delete create-shell.exp file
-              run: rm create-shell.exp
-            - name: Delete shell.log file
-              run: rm shell.log
             - name: Delete the cluster created
               if: always()
               run: xpk cluster delete --cluster $TPU_CLUSTER_NAME --zone=us-central2-b --force

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/integration_legacy_tests.yaml

@@ -47,14 +47,13 @@ jobs:
                   lookup-only: true
             - name: install dependencies
               if: steps.check-cache.outputs.cache-hit != 'true'
-              run: make install-dev && cp ./bin/kubectl-kueue /usr/local/bin/kubectl-kueue && cp ./bin/kubectl-kjob /usr/local/bin/kubectl-kjob
+              run: make install-dev && cp ./bin/kubectl-kueue /usr/local/bin/kubectl-kueue
             - name: Cache dependencies
               if: steps.check-cache.outputs.cache-hit != 'true'
               uses: actions/cache/save@v3
               with:
                   path: |
                       /usr/local/bin/kubectl-kueue
-                      /usr/local/bin/kubectl-kjob
                       ~/.cache/pip
                       ${{env.pythonLocation}}
                   key: xpk-deps-${{ matrix.python-version }}-${{github.run_id}}-${{github.run_attempt}}

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/label-validation.yaml

@@ -36,8 +36,8 @@ jobs:
       with:
         mode: minimum
         count: 1
-        labels: "release-improvements, release-bugfix, release-features"
-        message: "This PR is being prevented from merging because it is not labeled.  Please add a label to this PR.  Accepted labels: release-improvements, release-bugfix, release-features"
+        labels: "release-improvements, release-bugfix, release-features, release-breaking"
+        message: "This PR is being prevented from merging because it is not labeled.  Please add a label to this PR.  Accepted labels: release-improvements, release-bugfix, release-features, release-breaking"
     - id: do-not-merge
       uses: mheap/github-action-required-labels@v5
       with:

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/nightly_tests.yaml

@@ -23,31 +23,29 @@ permissions:
   contents: read
 
 jobs:
-  build_kjob:
-    uses: ./.github/workflows/reusable_build_kjob.yaml
   build_wheel:
     uses: ./.github/workflows/reusable_build_wheel.yaml
   build_actions:
     uses: ./.github/workflows/reusable_build_scripts.yaml
   basic_cluster_create:
-    needs: [build_kjob, build_actions, build_wheel]
+    needs: [build_actions, build_wheel]
     uses: ./.github/workflows/integration_basic_cluster_create.yaml
     secrets: inherit
 
   pathways_cluster_create:
-    needs: [build_kjob, build_actions, build_wheel]
+    needs: [build_actions, build_wheel]
     uses: ./.github/workflows/integration_pathways_cluster_create.yaml
     secrets: inherit
 
   ray_cluster_create:
-    needs: [build_kjob, build_actions, build_wheel]
+    needs: [build_actions, build_wheel]
     uses: ./.github/workflows/integration_ray_cluster_create.yaml
     secrets: inherit
   legacy_integration:
-    needs: [build_kjob, build_actions, build_wheel]
+    needs: [build_actions, build_wheel]
     uses: ./.github/workflows/integration_legacy_tests.yaml
     secrets: inherit
   storage-tests:
-    needs: [build_kjob, build_actions, build_wheel]
+    needs: [build_actions, build_wheel]
     uses: ./.github/workflows/integration_storage_tests.yaml
     secrets: inherit

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/reusable_goldens.yaml

@@ -33,7 +33,6 @@ jobs:
       with:
         path: |
           /usr/local/bin/kubectl-kueue
-          /usr/local/bin/kubectl-kjob
           ~/.cache/pip
           ${{env.pythonLocation}}
         key: xpk-deps-3.10-${{github.run_id}}-${{github.run_attempt}}

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/reusable_integration_tests.yaml

@@ -42,7 +42,6 @@ jobs:
         with:
           path: |
             /usr/local/bin/kubectl-kueue
-            /usr/local/bin/kubectl-kjob
             ~/.cache/pip
             ${{env.pythonLocation}}
           key: xpk-deps-3.10-${{github.run_id}}-${{github.run_attempt}}

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/reusable_lint_and_format.yml

@@ -39,7 +39,6 @@ jobs:
       with:
         path: |
           /usr/local/bin/kubectl-kueue
-          /usr/local/bin/kubectl-kjob
           ~/.cache/pip
           ${{env.pythonLocation}}
         key: xpk-deps-${{matrix.python-version}}-${{github.run_id}}-${{github.run_attempt}}

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/reusable_storage_create.yaml

@@ -92,8 +92,6 @@ jobs:
         --auto-mount=true --vol=vol1 --mount-point='/${{inputs.storage-type}}-test-mount-point' --readonly=false
     - name: List and verify existing Storages
       run: xpk storage list --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}} | tee output.txt | grep ${{inputs.storage-name}} || (echo 'No storage found' && exit 143)
-    - name: Verify VolumeBundle created
-      run: kubectl get volumebundle ${{inputs.storage-name}} -o jsonpath='{.spec.containerVolumeMounts[0].mountPath}' | grep '/${{inputs.storage-type}}-test-mount-point'
     - name: Verify Persistent Volume mount options
       if: inputs.storage-command == 'attach' && inputs.storage-type == 'gcsfuse'
       run: kubectl get pv ${{inputs.storage-name}}-pv -oyaml | grep rename-dir-limit=10000 || (echo 'Invalid storage mount options' && exit 143)
@@ -114,45 +112,6 @@ jobs:
       run: xpk workload list --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}} --wait-for-job-completion $STORAGE_READ_WORKLOAD --timeout 300
     - name: Delete the reader workload on the cluster
       run: xpk workload delete --workload $STORAGE_READ_WORKLOAD --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}}
-    - name: Create batch-read.sh script
-      run: |
-        cat <<EOF > batch-read.sh
-        #!/bin/bash
-        grep 'Test text message' /${{inputs.storage-type}}-test-mount-point/$RANDOM_SEED/test.txt || (echo 'Reading from filestore failed' && exit 143)
-        EOF
-    - name: Run a batch-read job on the cluster
-      run: xpk batch --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}} batch-read.sh | tee batch-read.log
-    - name: Get job name
-      run: |
-        cat batch-read.log | grep 'xpk-def-app-profile-slurm-'
-        READ_JOB_NAME=$(grep 'Job name: xpk-def-app-profile-slurm-' batch-read.log | awk -F': ' '{print $2}')
-        echo "READ_JOB_NAME=${READ_JOB_NAME}" >> $GITHUB_ENV
-    - name: Wait for the batch-read job to finish
-      run: kubectl wait job.batch/$READ_JOB_NAME --for=condition=Complete --timeout=1m
-    - name: Cancel the batch-read job
-      run: xpk job cancel $READ_JOB_NAME --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}} | grep "job.batch/$READ_JOB_NAME deleted"
-    - name: Delete batch-read.log file
-      run: rm batch-read.log
-    - name: Run a run-read job on the cluster
-      run: xpk run --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}} batch-read.sh --timeout 60
-    - name: Delete batch-read.sh file
-      run: rm batch-read.sh
-    - name: Create shell and exit it immediately
-      run: |
-        cat <<EOF >> create-shell.exp
-        ##!/usr/bin/expect
-        spawn xpk shell --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}}
-        expect "/ # "
-        send "cat /${{inputs.storage-type}}-test-mount-point/$RANDOM_SEED/test.txt\n"
-        expect "Test text message"
-        send "exit\n"
-        EOF
-        chmod +x ./create-shell.exp
-        expect ./create-shell.exp
-    - name: Stop the shell
-      run: xpk shell stop --cluster ${{inputs.cluster-name}} --zone=${{inputs.zone}}
-    - name: Delete create-shell.exp file
-      run: rm create-shell.exp
     - name: Run workload to delete file on filestore
       run : xpk workload create --workload $STORAGE_DELETE_WORKLOAD --command "rm -rf /${{inputs.storage-type}}-test-mount-point/$RANDOM_SEED/test.txt || exit 143" --num-slices=1 --cluster ${{inputs.cluster-name}} --device-type=${{inputs.device-type}} --zone ${{inputs.zone}}
     - name: Wait for delete workload completion and confirm it succeeded

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/reusable_storage_delete.yaml

@@ -61,9 +61,6 @@ jobs:
     - name: Detach storage volumes
       if: always()
       run: xpk storage detach ${{inputs.storage-name}} --cluster=${{inputs.cluster-name}} --zone=${{inputs.zone}}
-    - name: Verify VolumeBundle deleted
-      run: |
-        ! kubectl get volumebundle | grep ${{inputs.storage-name}}
     - name: Delete GCP Filestore Storage instance
       if: always() && inputs.storage-command == 'delete'
       run: xpk storage delete ${{inputs.storage-name}} --cluster=${{inputs.cluster-name}} --zone=${{inputs.zone}}

{xpk-0.17.2 → xpk-1.0.0}/.github/workflows/reusable_unit_tests.yaml

@@ -33,7 +33,6 @@ jobs:
       with:
         path: |
           /usr/local/bin/kubectl-kueue
-          /usr/local/bin/kubectl-kjob
           ~/.cache/pip
           ${{env.pythonLocation}}
         key: xpk-deps-3.10-${{github.run_id}}-${{github.run_attempt}}

{xpk-0.17.2 → xpk-1.0.0}/Makefile

@@ -2,25 +2,21 @@ KUEUE_REPO=https://github.com/kubernetes-sigs/kueue.git
 
 KUBECTL_VERSION := $(shell curl -L -s https://dl.k8s.io/release/stable.txt)
 KUEUE_VERSION=v0.14.3
-KJOB_VERSION=v0.1.0
 
 OS := $(shell uname -s | tr A-Z a-z)
 PLATFORM := $(shell uname -m | sed -e 's/aarch64/arm64/' | sed -e 's/x86_64/amd64/')
 
 KUBECTL_URL = "https://dl.k8s.io/release/$(KUBECTL_VERSION)/bin/$(OS)/$(PLATFORM)/kubectl"
 KUEUECTL_URL = "https://github.com/kubernetes-sigs/kueue/releases/download/$(KUEUE_VERSION)/kubectl-kueue-$(OS)-$(PLATFORM)"
-KJOBCTL_URL = "https://github.com/kubernetes-sigs/kjob/releases/download/$(KJOB_VERSION)/kubectl-kjob-$(OS)-$(PLATFORM)"
 
 PROJECT_DIR := $(realpath $(shell dirname $(firstword $(MAKEFILE_LIST))))
-KJOB_DOCKER_IMG := xpk_kjob
-KJOB_DOCKER_CONTAINER := xpk_kjob_container
 BIN_PATH=$(PROJECT_DIR)/bin
 
 .PHONY: install
-install: check-python check-gcloud install-gcloud-auth-plugin install-kueuectl install-kjobctl pip-install
+install: check-python check-gcloud install-gcloud-auth-plugin install-kueuectl pip-install
 
 .PHONY: install-dev
-install-dev: check-python check-gcloud mkdir-bin install-kueuectl install-kjobctl pip-install pip-install-dev install-pytest install-lint
+install-dev: check-python check-gcloud mkdir-bin install-kueuectl pip-install pip-install-dev install-pytest install-lint
 
 .PHONY: pip-install-dev
 pip-install-dev:
@@ -54,16 +50,6 @@ install-kueuectl: mkdir-bin
 	curl -Lo $(BIN_PATH)/kubectl-kueue $(KUEUECTL_URL);
 	chmod +x $(BIN_PATH)/kubectl-kueue;
 
-.PHONY: install-kjobctl
-install-kjobctl: mkdir-bin
-	#curl -Lo $(BIN_PATH)/kubectl-kjob $(KJOBCTL_URL)
-	#chmod +x $(BIN_PATH)/kubectl-kjob
-	# TODO: Switch to kjob release-based installation once version >=0.2.0 is available.
-	chmod +x tools/build-kjob.sh
-	./tools/build-kjob.sh
-	mv kubectl-kjob $(BIN_PATH)/kubectl-kjob
-	chmod +x $(BIN_PATH)/kubectl-kjob
-
 .PHONY: install-gcloud-auth-plugin
 install-gcloud-auth-plugin:
 	chmod +x tools/install-gke-auth-plugin.sh

{xpk-0.17.2/src/xpk.egg-info → xpk-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xpk
-Version: 0.17.2
+Version: 1.0.0
 Summary: xpk helps Cloud developers to orchestrate training jobs on accelerators on GKE.
 Author-email: XPK team <xpk-code-reviewers@google.com>
 License: Apache-2.0
@@ -114,10 +114,21 @@ XPK also supports the following [Google Cloud Storage solutions](./docs/usage/st
   * [Storage](./docs/usage/storage.md)
   * [Advanced](./docs/usage/advanced.md)
   * [Inspector](./docs/usage/inspector.md)
-  * [Run](./docs/usage/run.md)
-  * [Job](./docs/usage/job.md)
 * [Troubleshooting](./docs/troubleshooting.md)
-* [Local Testing](./docs/local_testing.md)
+
+# Privacy notice
+
+To help improve XPK, feature usage statistics are collected and sent to Google. You can opt-out at any time by executing
+the following shell command:
+
+```shell
+xpk config set send-telemetry <true/false>
+```
+
+XPK telemetry overall is handled in accordance with the [Google Privacy Policy](https://policies.google.com/privacy). When
+you use XPK to interact with or utilize GCP Services, your information is handled in accordance with the
+[Google Cloud Privacy Notice](https://cloud.google.com/terms/cloud-privacy-notice).
+
 
 # Contributing
 

{xpk-0.17.2 → xpk-1.0.0}/README.md

@@ -73,10 +73,21 @@ XPK also supports the following [Google Cloud Storage solutions](./docs/usage/st
   * [Storage](./docs/usage/storage.md)
   * [Advanced](./docs/usage/advanced.md)
   * [Inspector](./docs/usage/inspector.md)
-  * [Run](./docs/usage/run.md)
-  * [Job](./docs/usage/job.md)
 * [Troubleshooting](./docs/troubleshooting.md)
-* [Local Testing](./docs/local_testing.md)
+
+# Privacy notice
+
+To help improve XPK, feature usage statistics are collected and sent to Google. You can opt-out at any time by executing
+the following shell command:
+
+```shell
+xpk config set send-telemetry <true/false>
+```
+
+XPK telemetry overall is handled in accordance with the [Google Privacy Policy](https://policies.google.com/privacy). When
+you use XPK to interact with or utilize GCP Services, your information is handled in accordance with the
+[Google Cloud Privacy Notice](https://cloud.google.com/terms/cloud-privacy-notice).
+
 
 # Contributing
 

{xpk-0.17.2 → xpk-1.0.0}/docs/installation.md

@@ -44,7 +44,6 @@ Depending on your chosen installation method, you may need these additional tool
 | Install Method | Tool | Notes |
 | :--- | :--- | :--- |
 | **Pip** | **kueuectl** | [Installation instructions](https://kueue.sigs.k8s.io/docs/reference/kubectl-kueue/installation/) |
-| **Pip** | **kjob** | [Installation instructions](https://github.com/kubernetes-sigs/kjob/blob/main/docs/installation.md) |
 | **Source** | **git** | Install via your package manager (e.g., `sudo apt-get install git` on Debian/Ubuntu) |
 | **Source** | **make** | Install via your package manager (e.g., `sudo apt-get install make` on Debian/Ubuntu) |
 

{xpk-0.17.2 → xpk-1.0.0}/docs/troubleshooting.md

@@ -38,7 +38,7 @@ Some XPK cluster configuration might be missing, if workload creation fails with
 
 `[XPK] b'error: the server doesn\'t have a resource type "workloads"\n'`
 
-Mitigate this error by re-running your `xpk.py cluster create ...` command, to refresh the cluster configurations.
+Mitigate this error by re-running your `xpk cluster create ...` command, to refresh the cluster configurations.
 
 ## Permission Issues: `requires one of ["permission_name"] permission(s)`.
 

{xpk-0.17.2 → xpk-1.0.0}/docs/usage/clusters.md

@@ -254,6 +254,35 @@ xpk cluster create \
 
 will fail the cluster creation process because Vertex AI Tensorboard is not supported in `us-central2`.
 
+### Create Cluster With Google Cloud ML Diagnostics Enabled
+
+Google Cloud ML Diagnostics is an end-to-end managed platform for ML Engineers to optimize and diagnose their AI/ML workloads on Google Cloud. The product allows ML Engineers to collect and visualize all their workload metrics, configs and profiles with one single platform, all within the same UI. The current product offering focuses on workloads running on XLA-based frameworks (JAX, Pytorch XLA, Tensorflow/Keras) on Google Cloud TPUs and GPUs. Current support is for JAX on Google Cloud TPUs only.
+
+Enabling ML Diagnostics is streamlined and simplified through XPK cluster creation commands.
+
+By adding the **--managed-mldiagnostics** flag during the execution of either **xpk cluster create** or **xpk cluster create-pathways**, the ML Diagnostics functionality is enabled. This flag ensures the necessary supporting components (such as the injection-webhook and connection-operator) are automatically configured, allowing the feature to function seamlessly in both Pathways and non-Pathways execution environments.
+
+**Example Usage:**
+
+* Cluster Create for Pathways with flag **--managed-mldiagnostics**:
+
+```shell
+xpk cluster create-pathways \
+--cluster xpk-pw-test \
+--num-slices=4 --spot \
+--tpu-type=v5litepod-16 \
+--managed-mldiagnostics
+```
+
+* Cluster Create (provision spot / preemptable capacity) with flag **--managed-mldiagnostics**:
+
+```shell
+xpk cluster create \
+--cluster xpk-test --tpu-type=v5litepod-16 \
+--num-slices=4 --spot \
+--managed-mldiagnostics
+```
+
 ## Cluster Delete
 *   Cluster Delete (deprovision capacity):
 

{xpk-0.17.2 → xpk-1.0.0}/goldens/Basic_cluster_create.txt

@@ -9,7 +9,7 @@ gcloud container get-server-config --project=golden-project --region=us-central1
 [XPK] Task: `Find if Cluster Exists` is implemented by the following command not running since it is a dry run. 
 gcloud container clusters list --project=golden-project --filter=location~"us-central1.*" --format="csv[no-heading](name)"
 [XPK] Task: `GKE Cluster Create` is implemented by the following command not running since it is a dry run. 
-gcloud beta container clusters create golden-cluster --project=golden-project --region=us-central1 --node-locations=us-central1-a --cluster-version=0 --machine-type=e2-standard-16 --enable-autoscaling --total-min-nodes 1 --total-max-nodes 1000 --num-nodes 6 --enable-dns-access --autoscaling-profile=optimize-utilization --labels=gke_product_type=xpk --release-channel=rapid --location-policy=BALANCED --scopes=storage-full,gke-default
+gcloud beta container clusters create golden-cluster --project=golden-project --region=us-central1 --node-locations=us-central1-a --cluster-version=0 --machine-type=e2-standard-16 --enable-autoscaling --total-min-nodes 1 --total-max-nodes 1000 --num-nodes 6 --enable-dns-access --autoscaling-profile=optimize-utilization --labels=gke_product_type=xpk --release-channel=rapid --enable-ip-alias --enable-dataplane-v2 --enable-multi-networking --location-policy=BALANCED --scopes=storage-full,gke-default
 [XPK] Task: `Find cluster region or zone` is implemented by the following command not running since it is a dry run. 
 gcloud container clusters list --project=golden-project --filter=name=golden-cluster --format="value(location)"
 [XPK] Task: `Check if Private Nodes is enabled in cluster.` is implemented by the following command not running since it is a dry run. 
@@ -37,11 +37,11 @@ kubectl wait deployment/coredns --for=condition=Available=true --namespace=kube-
 [XPK] Task: `Determine current gke master version` is implemented by the following command not running since it is a dry run. 
 gcloud beta container clusters describe golden-cluster --location us-central1 --project golden-project --format="value(currentMasterVersion)"
 [XPK] Creating 1 node pool or pools of tpu7x-8
-We assume that the underlying system is: SystemCharacteristics(topology='2x2x1', vms_per_slice=1, gke_accelerator='tpu7x', gce_machine_type='tpu7x-standard-4t', chips_per_vm=4, accelerator_type=TPU, device_type='tpu7x-8', supports_sub_slicing=False, supports_super_slicing=False, docker_platform=<DockerPlatform.AMD: 'linux/amd64'>, requires_workload_policy=False, gpu_config=None)
+We assume that the underlying system is: SystemCharacteristics(topology='2x2x1', vms_per_slice=1, gke_accelerator='tpu7x', gce_machine_type='tpu7x-standard-4t', chips_per_vm=4, accelerator_type=TPU, device_type='tpu7x-8', supports_sub_slicing=False, supports_super_slicing=False, supports_accelerator_network_profile=False, docker_platform=<DockerPlatform.AMD: 'linux/amd64'>, requires_workload_policy=False, gpu_config=None)
 [XPK] Task: `Get All Node Pools` is implemented by the following command not running since it is a dry run. 
 gcloud beta container node-pools list --cluster golden-cluster --project=golden-project --location=us-central1 --format="csv[no-heading](name)"
 [XPK] Creating 1 node pool or pools of tpu7x-8
-Underlyingly, we assume that means: SystemCharacteristics(topology='2x2x1', vms_per_slice=1, gke_accelerator='tpu7x', gce_machine_type='tpu7x-standard-4t', chips_per_vm=4, accelerator_type=TPU, device_type='tpu7x-8', supports_sub_slicing=False, supports_super_slicing=False, docker_platform=<DockerPlatform.AMD: 'linux/amd64'>, requires_workload_policy=False, gpu_config=None)
+Underlyingly, we assume that means: SystemCharacteristics(topology='2x2x1', vms_per_slice=1, gke_accelerator='tpu7x', gce_machine_type='tpu7x-standard-4t', chips_per_vm=4, accelerator_type=TPU, device_type='tpu7x-8', supports_sub_slicing=False, supports_super_slicing=False, supports_accelerator_network_profile=False, docker_platform=<DockerPlatform.AMD: 'linux/amd64'>, requires_workload_policy=False, gpu_config=None)
 [XPK] Task: `Get Node Pool Zone` is implemented by the following command not running since it is a dry run. 
 gcloud beta container node-pools describe 0 --cluster golden-cluster --project=golden-project --location=us-central1 --format="value(locations)"
 [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run. 
@@ -261,91 +261,6 @@ kubectl get node --no-headers | wc -l
 [XPK] Try 1: Updating Kueue Controller Manager resources
 [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run. 
 kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
-[XPK] Verifying kjob installation
-[XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run. 
-kubectl-kjob help
-[XPK] kjob found
-[XPK] Applying kjob CDRs
-[XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run. 
-kubectl kjob printcrds | kubectl apply --server-side -f -
-[XPK] Creating kjob CRDs succeeded
-[XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run. 
-kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
-[XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content: 
-
-  apiVersion: kjobctl.x-k8s.io/v1alpha1
-  kind: JobTemplate
-  metadata:
-    name: xpk-def-batch
-    namespace: default
-  template:
-    spec:
-      parallelism: 1
-      completions: 1
-      completionMode: Indexed
-      template:
-        spec:
-          dnsPolicy: ClusterFirstWithHostNet
-          tolerations:
-            - operator: "Exists"
-              key: nvidia.com/gpu
-          containers:
-            - name: xpk-batch-container
-              image: ubuntu:22.04
-              workingDir: /
-              
-          
-          priorityClassName: medium
-          restartPolicy: OnFailure
-          serviceAccountName: 
-
-[XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run. 
-kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
-[XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content: 
-
-apiVersion: v1
-kind: PodTemplate
-metadata:
-  name: xpk-def-pod
-  namespace: default
-template:
-  spec:
-    tolerations:
-      - effect: NoSchedule
-        key: components.gke.io/gke-managed-components
-        operator: Equal
-        value: "true"
-    containers:
-      - name: xpk-interactive-container
-        image: busybox:1.28
-        command: [/bin/sh]
-        workingDir: /
-    initContainers:
-      - name: init
-        image: busybox:1.28
-        command: ['/bin/mkdir', '-p', '/']
-    serviceAccountName: 
-
-[XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run. 
-kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
-[XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content: 
-
-apiVersion: kjobctl.x-k8s.io/v1alpha1
-kind: ApplicationProfile
-metadata:
-  name: xpk-def-app-profile
-  namespace: default
-spec:
-  supportedModes:
-    - name: Slurm
-      template: xpk-def-batch
-      requiredFlags: []
-    - name: Interactive
-      template: xpk-def-pod
-  volumeBundles: []
-
-[XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run. 
-kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
 [XPK] GKE commands done! Resources are created.
 [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster/details?project=golden-project
 [XPK] Exiting XPK cleanly