xpk 0.17.3__tar.gz → 1.1.0__tar.gz

{xpk-0.17.3 → xpk-1.1.0}/.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-0.17.3 → xpk-1.1.0}/.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-0.17.3 → xpk-1.1.0}/.github/workflows/integration_basic_cluster_create.yaml

@@ -31,7 +31,7 @@ jobs:
           group: nightly-test-cluster-group-empty
           cancel-in-progress: false
       env:
-          EMPTY_CLUSTER_NAME: nightly-xpk-zero-nodepools
+          EMPTY_CLUSTER_NAME: nightly-xpk-zero
       steps:
           - uses: actions/download-artifact@v4
             with:
@@ -59,7 +59,7 @@ jobs:
           group: nightly-test-cluster-group-private
           cancel-in-progress: false
       env:
-          PRIVATE_CLUSTER_NAME: nightly-xpk-private-2-v4-8-nodepools
+          PRIVATE_CLUSTER_NAME: nightly-xpk-private-2-v4-8
       steps:
           - uses: actions/download-artifact@v4
             with:
@@ -83,38 +83,6 @@ jobs:
             with:
                 name: empty-private-cluster-nodepool-log-${{github.run_id}}
                 path: /tmp/NodepoolCreate-${{ env.PRIVATE_CLUSTER_NAME }}-np-*
-    dws_flex_cluster:
-      runs-on: [ubuntu-22.04]
-      concurrency: # We support one build test to run at a time currently.
-          group: nightly-test-cluster-group-flex
-          cancel-in-progress: false
-      env:
-          DWS_FLEX_CLUSTER_NAME: xpk-dws-nightly-test-2-v4-8
-      steps:
-          - uses: actions/download-artifact@v4
-            with:
-                name: custom-scripts
-          - name: Setup environment
-            uses: ./.github/actions/setup-test-env
-            with:
-                credentials_json: "${{ secrets.GCP_SA_KEY }}"
-          - name: Check xpk installation
-            run: xpk version
-          - name: Create a DWS flex queued xpk cluster
-            run: xpk cluster create --cluster ${DWS_FLEX_CLUSTER_NAME} --tpu-type=v5p-8  --num-slices=1 --zone=us-east5-a --default-pool-cpu-num-nodes=2 --flex --custom-cluster-arguments="${CLUSTER_NETWORK_ARGUMENTS_DWS}"
-          - name: Run dws flex queued TPU workload
-            run: xpk workload create --workload xpktest-build-${{ github.run_attempt }}-dws --cluster ${DWS_FLEX_CLUSTER_NAME} --zone=us-east5-a --tpu-type=v5p-8  --flex --command "echo foo" --num-slices=1
-          - name: Wait for workload completion and confirm it succeeded
-            run: xpk workload list --cluster ${DWS_FLEX_CLUSTER_NAME} --zone=us-east5-a --wait-for-job-completion xpktest-build-${{ github.run_attempt }}-dws --timeout 1000
-          - name: Delete the DWS flex queued cluster
-            if: always()
-            run: xpk cluster delete --cluster ${DWS_FLEX_CLUSTER_NAME} --zone=us-east5-a --force
-          - name: Upload DWS cluster nodepool creation log
-            if: always()
-            uses: actions/upload-artifact@v4
-            with:
-                name: empty-dws-cluster-nodepool-log-${{github.run_id}}
-                path: /tmp/NodepoolCreate-${{ env.DWS_FLEX_CLUSTER_NAME }}-np-*
 
     cluster-create-and-delete:
         runs-on: [ubuntu-22.04]
@@ -122,7 +90,7 @@ jobs:
             group: nightly-test-cluster-group-tpu
             cancel-in-progress: false
         env:
-            TPU_CLUSTER_NAME: nightly-xpk-2-v5p-8-nodepools
+            TPU_CLUSTER_NAME: nightly-xpk-2-v5p-8
             WORKLOAD_NAME: xpktest-nightly-${{ github.run_attempt }}
         steps:
             - uses: actions/download-artifact@v4
@@ -152,62 +120,6 @@ 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-1.1.0/.github/workflows/integration_gpu_cluster_create.yaml

@@ -0,0 +1,78 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License
+
+name: Basic GPU cluster create
+
+on:
+    workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+    gpu-cluster-create-and-delete:
+        runs-on: [ubuntu-22.04]
+        concurrency:
+            group: nightly-test-cluster-group-gpu
+            cancel-in-progress: false
+        env:
+            GPU_CLUSTER_NAME: nightly-xpk-b200
+            WORKLOAD_NAME: xpktest-gpu-nightly-${{ github.run_attempt }}
+        steps:
+            - uses: actions/download-artifact@v4
+              with:
+                  name: custom-scripts
+            - name: Setup environment
+              uses: ./.github/actions/setup-test-env
+              with:
+                  credentials_json: "${{ secrets.GCP_SA_KEY }}"
+            - name: Check xpk installation
+              run: xpk version
+            - name: 'Setup Service Account for XPK'
+              run: |
+                # 1. Clear any existing WIF configurations to avoid conflicts
+                rm -rf $HOME/.config/gcloud
+                mkdir -p $HOME/.config/gcloud
+
+                # 2. Write the Key File
+                echo '${{ secrets.GCP_SA_KEY }}' > $HOME/.config/gcloud/application_default_credentials.json
+
+                # 3. Activate the Service Account
+                # This updates the internal config files to point to the key file.
+                # When Docker mounts the directory, it will now see "Active Account: Service Account"
+                gcloud auth activate-service-account --key-file=$HOME/.config/gcloud/application_default_credentials.json --project=cloud-tpu-multipod-dev
+
+                # 4. Set Env Var for the host (GitHub Runner)
+                echo "GOOGLE_APPLICATION_CREDENTIALS=$HOME/.config/gcloud/application_default_credentials.json" >> $GITHUB_ENV
+            - name: Create an XPK Cluster with 1 x b200 GPU
+              run: xpk cluster create --cluster $GPU_CLUSTER_NAME --device-type=b200-8 --zone=asia-northeast1-b --default-pool-cpu-machine-type=n1-standard-16 --spot
+            - name: Authenticate Docker
+              run: gcloud auth configure-docker --quiet
+            - name: Run a base-docker-image workload
+              run: xpk workload create --cluster $GPU_CLUSTER_NAME --workload $WORKLOAD_NAME --docker-image='nvidia/cuda:12.1.0-base-ubuntu22.04' --command "nvidia-smi" --zone=asia-northeast1-b --device-type=b200-8
+            - name: List out the workloads on the cluster
+              run: xpk workload list --cluster $GPU_CLUSTER_NAME --zone=asia-northeast1-b
+            - name: Wait for workload completion and confirm it succeeded
+              run: xpk workload list --cluster $GPU_CLUSTER_NAME --zone=asia-northeast1-b --wait-for-job-completion $WORKLOAD_NAME --timeout 600
+            - name: Delete the workload on the cluster
+              run: xpk workload delete --workload $WORKLOAD_NAME --cluster $GPU_CLUSTER_NAME --zone=asia-northeast1-b
+            - name: Delete the cluster created
+              if: always()
+              run: xpk cluster delete --cluster $GPU_CLUSTER_NAME --zone=asia-northeast1-b --force
+            - name: Upload cluster nodepool creation log
+              if: always()
+              uses: actions/upload-artifact@v4
+              with:
+                  name: gpu-cluster-nodepool-log-${{github.run_id}}
+                  path: /tmp/NodepoolCreate-${{ env.GPU_CLUSTER_NAME }}-np-*

{xpk-0.17.3 → xpk-1.1.0}/.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-0.17.3 → xpk-1.1.0}/.github/workflows/nightly_tests.yaml

@@ -16,38 +16,37 @@ name: Nightly Tests
 
 on:
   workflow_dispatch:
-  schedule: # Schedule the job run at 12AM PST daily.
-    - cron: "0 8 * * *"
+  schedule: # Schedule the job run at 6AM UTC daily.
+    - cron: "0 6 * * *"
 
 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
 
+  gpu_cluster_create:
+    needs: [build_actions, build_wheel]
+    uses: ./.github/workflows/integration_gpu_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]
-    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-0.17.3 → xpk-1.1.0}/.github/workflows/reusable_goldens.yaml

@@ -33,13 +33,12 @@ 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}}
         restore-keys: xpk-deps-3.10-
     - name: Verify goldens
-      run: ./golden_buddy.sh verify goldens.yaml goldens
+      run: python3 tools/recipes.py golden recipes/*.md
       env:
         UPDATE_GOLDEN_COMMAND: make goldens
         XPK_VERSION_OVERRIDE: v0.0.0

{xpk-0.17.3 → xpk-1.1.0}/.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-0.17.3 → xpk-1.1.0}/.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-0.17.3 → xpk-1.1.0}/.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-0.17.3 → xpk-1.1.0}/.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-0.17.3 → xpk-1.1.0}/.github/workflows/stale.yaml

@@ -12,11 +12,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License
 
-
-name: 'Close stale issues and PRs'
+name: "Close stale issues and PRs"
 on:
   schedule:
-    - cron: '30 1 * * *'
+    - cron: "30 1 * * *"
 
 jobs:
   stale:
@@ -24,7 +23,8 @@ jobs:
     steps:
       - uses: actions/stale@5f858e3efba33a5ca4407a664cc011ad407f2008 # v10.1.0
         with:
-          stale-pr-message: 'This pull request is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
+          days-before-issue-stale: -1
+          stale-pr-message: "This pull request is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 7 days."
           days-before-pr-stale: 30
           days-before-pr-close: 7
           operations-per-run: 100

{xpk-0.17.3 → xpk-1.1.0}/Makefile

@@ -1,26 +1,17 @@
-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)/$(PLATFORM)/kubectl"
+KUEUE_VERSION=v0.15.2
 KUEUECTL_URL = "https://github.com/kubernetes-sigs/kueue/releases/download/$(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:
@@ -38,12 +29,9 @@ install-pytest:
 run-unittests:
 	XPK_TESTER=false XPK_VERSION_OVERRIDE=v0.0.0 pytest  -vv src/xpk/
 
-run-integrationtests:
-	XPK_TESTER=false XPK_VERSION_OVERRIDE=v0.0.0 pytest src/integration/
-
 .PHONY: goldens
 goldens:
-	XPK_TESTER=false XPK_VERSION_OVERRIDE=v0.0.0 ./golden_buddy.sh update goldens.yaml goldens
+	XPK_TESTER=false XPK_VERSION_OVERRIDE=v0.0.0 python3 tools/recipes.py update recipes/*.md
 
 .PHONY: mkdir-bin
 mkdir-bin:
@@ -54,16 +42,6 @@ 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-0.17.3/src/xpk.egg-info → xpk-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xpk
-Version: 0.17.3
+Version: 1.1.0
 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
@@ -93,36 +93,63 @@ XPK supports a variety of hardware accelerators.
 
 XPK also supports the following [Google Cloud Storage solutions](./docs/usage/storage.md):
 
-| Storage Type                               | Documentation                                                                            |
-|--------------------------------------------|------------------------------------------------------------------------------------------|
-| Cloud Storage FUSE                         | [docs](./docs/usage/storage.md#fuse)                                                     |
-| Filestore                                  | [docs](./docs/usage/storage.md#filestore)                                                |
-| Parallelstore                              | [docs](./docs/usage/storage.md#parallelstore)                                            |
-| Block storage (Persistent Disk, Hyperdisk) | [docs](./docs/usage/storage.md#block-storage-persistent-disk-hyperdisk)                  |
+| Storage Type                               | Documentation                                                           |
+| ------------------------------------------ | ----------------------------------------------------------------------- |
+| Cloud Storage FUSE                         | [docs](./docs/usage/storage.md#fuse)                                    |
+| Filestore                                  | [docs](./docs/usage/storage.md#filestore)                               |
+| Parallelstore                              | [docs](./docs/usage/storage.md#parallelstore)                           |
+| Block storage (Persistent Disk, Hyperdisk) | [docs](./docs/usage/storage.md#block-storage-persistent-disk-hyperdisk) |
 
 # Documentation
 
-* [Permissions](./docs/permissions.md)
-* [Installation](./docs/installation.md)
-* Usage:
-  * [Clusters](./docs/usage/clusters.md)
-    * [GPU](./docs/usage/gpu.md)
-    * [CPU](./docs/usage/cpu.md)
-    * [Autoprovisioning](./docs/usage/autoprovisioning.md)
-  * [Workloads](./docs/usage/workloads.md)
-    * [Docker](./docs/usage/docker.md)
-  * [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)
+- [Permissions](./docs/permissions.md)
+- [Installation](./docs/installation.md)
+- Usage:
+  - [Clusters](./docs/usage/clusters.md)
+    - [GPU](./docs/usage/gpu.md)
+    - [CPU](./docs/usage/cpu.md)
+    - [Autoprovisioning](./docs/usage/autoprovisioning.md)
+  - [Workloads](./docs/usage/workloads.md)
+    - [Docker](./docs/usage/docker.md)
+  - [Storage](./docs/usage/storage.md)
+  - [Advanced](./docs/usage/advanced.md)
+  - [Inspector](./docs/usage/inspector.md)
+- [Troubleshooting](./docs/troubleshooting.md)
+
+# Dependencies
+
+| Dependency                                                                                                   | When used                   |
+| ------------------------------------------------------------------------------------------------------------ | --------------------------- |
+| [Google Cloud SDK (gcloud)](https://cloud.google.com/sdk/docs/install)                                       | _always_                    |
+| [kubectl](https://cloud.google.com/kubernetes-engine/docs/how-to/cluster-access-for-kubectl#install_kubectl) | _always_                    |
+| [ClusterToolkit](https://github.com/GoogleCloudPlatform/cluster-toolkit)                                     | Provisioning GPU clusters   |
+| [Kueue](https://github.com/kubernetes-sigs/kueue)                                                            | Scheduling workloads        |
+| [JobSet](https://github.com/kubernetes-sigs/jobset)                                                          | Workload creation           |
+| [Docker](https://docs.docker.com/engine/install/)                                                            | Building workload container |
+| [CoreDNS](https://github.com/coredns/deployment/tree/master/kubernetes)                                      | Cluster set up              |
+| [PathwaysJob](https://github.com/google/pathways-job)                                                        | Running Pathways workloads  |
+
+# 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
 
 Please read [`contributing.md`](./docs/contributing.md) for details on our code of conduct, and the process for submitting pull requests to us.
 
+# Get involved
+
+We'd love to hear from you! If you have questions or want to discuss ideas, join us on [GitHub Discussions](https://github.com/AI-Hypercomputer/xpk/discussions). Found a bug or have a feature request? Please let us know on [GitHub Issues](https://github.com/AI-Hypercomputer/xpk/issues).
+
 # License
 
 This project is licensed under the Apache License 2.0 - see the [`LICENSE`](./LICENSE) file for details