xpk 0.17.1__tar.gz → 0.17.3__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (293) hide show
  1. {xpk-0.17.1/src/xpk.egg-info → xpk-0.17.3}/PKG-INFO +1 -1
  2. {xpk-0.17.1 → xpk-0.17.3}/goldens/Basic_cluster_create.txt +0 -85
  3. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_for_multi-host_nodepool.txt +0 -85
  4. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_private.txt +0 -85
  5. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_sub-slicing.txt +0 -85
  6. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_super-slicing.txt +0 -85
  7. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_with_CPU_and_memory_limits_above_capacity.txt +0 -85
  8. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_with_CPU_and_memory_limits_below_capacity.txt +0 -85
  9. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_with_Managed_Lustre_driver.txt +0 -85
  10. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_with_Managed_Lustre_driver_and_legacy_port.txt +0 -85
  11. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_with_gb200-4.txt +37 -122
  12. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_with_shared_reservation.txt +0 -85
  13. {xpk-0.17.1 → xpk-0.17.3}/goldens/NAP_cluster-create.txt +0 -85
  14. {xpk-0.17.1 → xpk-0.17.3}/goldens/NAP_cluster-create_with_pathways.txt +0 -85
  15. {xpk-0.17.1 → xpk-0.17.3}/goldens.yaml +0 -8
  16. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/cluster.py +0 -22
  17. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/cluster_gcluster.py +1 -13
  18. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/cluster_gcluster_test.py +0 -10
  19. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/cluster_test.py +0 -4
  20. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/kind.py +0 -21
  21. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/storage.py +0 -25
  22. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/cluster.py +1 -3
  23. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/config.py +0 -15
  24. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/system_characteristics.py +1 -16
  25. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload_decorators/rdma_decorator.py +0 -15
  26. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload_decorators/tcpx_decorator.py +0 -8
  27. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload_decorators/tcpx_decorator_test.py +0 -78
  28. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload_decorators/tcpxo_decorator.py +0 -16
  29. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/common.py +0 -151
  30. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/core.py +0 -31
  31. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/validation.py +0 -8
  32. {xpk-0.17.1 → xpk-0.17.3/src/xpk.egg-info}/PKG-INFO +1 -1
  33. {xpk-0.17.1 → xpk-0.17.3}/src/xpk.egg-info/SOURCES.txt +0 -15
  34. xpk-0.17.1/goldens/Batch.txt +0 -19
  35. xpk-0.17.1/goldens/Job_cancel.txt +0 -14
  36. xpk-0.17.1/goldens/Job_info.txt +0 -21
  37. xpk-0.17.1/goldens/Job_list.txt +0 -14
  38. xpk-0.17.1/src/xpk/commands/batch.py +0 -144
  39. xpk-0.17.1/src/xpk/commands/job.py +0 -244
  40. xpk-0.17.1/src/xpk/commands/kjob_common.py +0 -60
  41. xpk-0.17.1/src/xpk/commands/run.py +0 -140
  42. xpk-0.17.1/src/xpk/commands/shell.py +0 -142
  43. xpk-0.17.1/src/xpk/core/kjob.py +0 -473
  44. xpk-0.17.1/src/xpk/parser/batch.py +0 -43
  45. xpk-0.17.1/src/xpk/parser/job.py +0 -147
  46. xpk-0.17.1/src/xpk/parser/run.py +0 -47
  47. xpk-0.17.1/src/xpk/parser/shell.py +0 -59
  48. xpk-0.17.1/src/xpk/templates/volume_bundle.yaml +0 -7
  49. {xpk-0.17.1 → xpk-0.17.3}/.dockerignore +0 -0
  50. {xpk-0.17.1 → xpk-0.17.3}/.github/CODEOWNERS +0 -0
  51. {xpk-0.17.1 → xpk-0.17.3}/.github/PULL_REQUEST_TEMPLATE.md +0 -0
  52. {xpk-0.17.1 → xpk-0.17.3}/.github/actions/install-kjob/action.yml +0 -0
  53. {xpk-0.17.1 → xpk-0.17.3}/.github/actions/install-kueue/action.yml +0 -0
  54. {xpk-0.17.1 → xpk-0.17.3}/.github/actions/setup-test-env/action.yml +0 -0
  55. {xpk-0.17.1 → xpk-0.17.3}/.github/release.yaml +0 -0
  56. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/README.md +0 -0
  57. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/build_tests.yaml +0 -0
  58. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/build_wheels.yaml +0 -0
  59. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/cleanup.yaml +0 -0
  60. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/gemini-dispatch.yml +0 -0
  61. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/gemini-invoke.yml +0 -0
  62. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/gemini-review.yml +0 -0
  63. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/gemini-scheduled-triage.yml +0 -0
  64. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/gemini-triage.yml +0 -0
  65. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/integration_basic_cluster_create.yaml +0 -0
  66. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/integration_legacy_tests.yaml +0 -0
  67. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/integration_pathways_cluster_create.yaml +0 -0
  68. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/integration_ray_cluster_create.yaml +0 -0
  69. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/integration_storage_tests.yaml +0 -0
  70. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/label-validation.yaml +0 -0
  71. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/nightly_tests.yaml +0 -0
  72. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/periodic_release.yaml +0 -0
  73. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/release_branch_versioning.yaml +0 -0
  74. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_build_kjob.yaml +0 -0
  75. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_build_scripts.yaml +0 -0
  76. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_build_wheel.yaml +0 -0
  77. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_goldens.yaml +0 -0
  78. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_integration_tests.yaml +0 -0
  79. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_lint_and_format.yml +0 -0
  80. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_storage_create.yaml +0 -0
  81. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_storage_delete.yaml +0 -0
  82. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/reusable_unit_tests.yaml +0 -0
  83. {xpk-0.17.1 → xpk-0.17.3}/.github/workflows/stale.yaml +0 -0
  84. {xpk-0.17.1 → xpk-0.17.3}/.gitignore +0 -0
  85. {xpk-0.17.1 → xpk-0.17.3}/.pre-commit-config.yaml +0 -0
  86. {xpk-0.17.1 → xpk-0.17.3}/LICENSE +0 -0
  87. {xpk-0.17.1 → xpk-0.17.3}/Makefile +0 -0
  88. {xpk-0.17.1 → xpk-0.17.3}/README.md +0 -0
  89. {xpk-0.17.1 → xpk-0.17.3}/backoff_retry.sh +0 -0
  90. {xpk-0.17.1 → xpk-0.17.3}/data/Dockerfile +0 -0
  91. {xpk-0.17.1 → xpk-0.17.3}/docs/code-of-conduct.md +0 -0
  92. {xpk-0.17.1 → xpk-0.17.3}/docs/contributing.md +0 -0
  93. {xpk-0.17.1 → xpk-0.17.3}/docs/installation.md +0 -0
  94. {xpk-0.17.1 → xpk-0.17.3}/docs/local_testing.md +0 -0
  95. {xpk-0.17.1 → xpk-0.17.3}/docs/permissions.md +0 -0
  96. {xpk-0.17.1 → xpk-0.17.3}/docs/testing.md +0 -0
  97. {xpk-0.17.1 → xpk-0.17.3}/docs/troubleshooting.md +0 -0
  98. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/advanced.md +0 -0
  99. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/autoprovisioning.md +0 -0
  100. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/clusters.md +0 -0
  101. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/cpu.md +0 -0
  102. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/docker.md +0 -0
  103. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/gpu.md +0 -0
  104. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/inspector.md +0 -0
  105. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/job.md +0 -0
  106. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/run.md +0 -0
  107. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/storage.md +0 -0
  108. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/tpu7x/clusters.md +0 -0
  109. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/tpu7x/recipes/flex_filestore_recipe.md +0 -0
  110. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/tpu7x/recipes/flex_lustre_recipe.md +0 -0
  111. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/tpu7x/recipes/reservation_gcs_bucket_recipe.md +0 -0
  112. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/tpu7x/workloads.md +0 -0
  113. {xpk-0.17.1 → xpk-0.17.3}/docs/usage/workloads.md +0 -0
  114. {xpk-0.17.1 → xpk-0.17.3}/examples/batch.md +0 -0
  115. {xpk-0.17.1 → xpk-0.17.3}/examples/fake_training.py +0 -0
  116. {xpk-0.17.1 → xpk-0.17.3}/examples/job.sh +0 -0
  117. {xpk-0.17.1 → xpk-0.17.3}/examples/llama-3.1-finetuning/check_cuda.sh +0 -0
  118. {xpk-0.17.1 → xpk-0.17.3}/examples/llama-3.1-finetuning/requirements.txt +0 -0
  119. {xpk-0.17.1 → xpk-0.17.3}/examples/llama-3.1-finetuning/train.py +0 -0
  120. {xpk-0.17.1 → xpk-0.17.3}/examples/llama-3.1-finetuning/train.slurm +0 -0
  121. {xpk-0.17.1 → xpk-0.17.3}/examples/llama-3.1-finetuning/training_data.jsonl +0 -0
  122. {xpk-0.17.1 → xpk-0.17.3}/examples/nccl/nccl-a3mega.sh +0 -0
  123. {xpk-0.17.1 → xpk-0.17.3}/examples/nccl/nccl-a3ultra.sh +0 -0
  124. {xpk-0.17.1 → xpk-0.17.3}/examples/nccl/nccl.md +0 -0
  125. {xpk-0.17.1 → xpk-0.17.3}/examples/storage/filestore-manifest-attach.yaml +0 -0
  126. {xpk-0.17.1 → xpk-0.17.3}/examples/storage/gcsfuse-manifest.yaml +0 -0
  127. {xpk-0.17.1 → xpk-0.17.3}/examples/storage/lustre-manifest-attach.yaml +0 -0
  128. {xpk-0.17.1 → xpk-0.17.3}/examples/storage/parallelstore-manifest-attach.yaml +0 -0
  129. {xpk-0.17.1 → xpk-0.17.3}/examples/storage/pd-manifest-attach.yaml +0 -0
  130. {xpk-0.17.1 → xpk-0.17.3}/golden_buddy.sh +0 -0
  131. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_create_for_single-host_single-slice_TPU.txt +0 -0
  132. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_delete.txt +0 -0
  133. {xpk-0.17.1 → xpk-0.17.3}/goldens/Cluster_delete_force.txt +0 -0
  134. {xpk-0.17.1 → xpk-0.17.3}/goldens/Storage_list.txt +0 -0
  135. {xpk-0.17.1 → xpk-0.17.3}/goldens/Workload_create.txt +0 -0
  136. {xpk-0.17.1 → xpk-0.17.3}/goldens/Workload_create_pathways.txt +0 -0
  137. {xpk-0.17.1 → xpk-0.17.3}/goldens/Workload_create_sub-slicing.txt +0 -0
  138. {xpk-0.17.1 → xpk-0.17.3}/goldens/Workload_create_super-slicing.txt +0 -0
  139. {xpk-0.17.1 → xpk-0.17.3}/goldens/Workload_create_with_output-manifest-file.txt +0 -0
  140. {xpk-0.17.1 → xpk-0.17.3}/goldens/Workload_delete.txt +0 -0
  141. {xpk-0.17.1 → xpk-0.17.3}/goldens/Workload_list.txt +0 -0
  142. {xpk-0.17.1 → xpk-0.17.3}/pylintrc +0 -0
  143. {xpk-0.17.1 → xpk-0.17.3}/pyproject.toml +0 -0
  144. {xpk-0.17.1 → xpk-0.17.3}/setup.cfg +0 -0
  145. {xpk-0.17.1 → xpk-0.17.3}/src/integration/README.md +0 -0
  146. {xpk-0.17.1 → xpk-0.17.3}/src/integration/__init__.py +0 -0
  147. {xpk-0.17.1 → xpk-0.17.3}/src/integration/docker_manager_test.py +0 -0
  148. {xpk-0.17.1 → xpk-0.17.3}/src/integration/gcluster_a3mega_test.py +0 -0
  149. {xpk-0.17.1 → xpk-0.17.3}/src/integration/gcluster_a3ultra_test.py +0 -0
  150. {xpk-0.17.1 → xpk-0.17.3}/src/integration/gcluster_a4_test.py +0 -0
  151. {xpk-0.17.1 → xpk-0.17.3}/src/integration/gcluster_test.py +0 -0
  152. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/__init__.py +0 -0
  153. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/api/__init__.py +0 -0
  154. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/api/storage_crd.yaml +0 -0
  155. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a3mega/config-map.yaml.tftpl +0 -0
  156. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a3mega/storage_crd.yaml +0 -0
  157. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a3ultra/config-map.yaml.tftpl +0 -0
  158. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a3ultra/mlgru-disable.yaml +0 -0
  159. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a3ultra/nccl-installer.yaml +0 -0
  160. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a3ultra/storage_crd.yaml +0 -0
  161. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a4/config-map.yaml.tftpl +0 -0
  162. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a4/nccl-rdma-installer-a4.yaml +0 -0
  163. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/blueprints/a4/storage_crd.yaml +0 -0
  164. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/__init__.py +0 -0
  165. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/common.py +0 -0
  166. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/config.py +0 -0
  167. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/info.py +0 -0
  168. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/inspector.py +0 -0
  169. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/managed_ml_diagnostics.py +0 -0
  170. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/managed_ml_diagnostics_test.py +0 -0
  171. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/version.py +0 -0
  172. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/workload.py +0 -0
  173. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/commands/workload_test.py +0 -0
  174. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/__init__.py +0 -0
  175. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/__init__.py +0 -0
  176. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/blueprint_definitions.py +0 -0
  177. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/blueprint_generator.py +0 -0
  178. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/blueprint_test.py +0 -0
  179. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/testing/__init__.py +0 -0
  180. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/testing/data/a3_mega.yaml +0 -0
  181. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/testing/data/a3_mega_spot.yaml +0 -0
  182. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/testing/data/a3_ultra.yaml +0 -0
  183. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/blueprint/testing/data/a4.yaml +0 -0
  184. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/capacity.py +0 -0
  185. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/capacity_test.py +0 -0
  186. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/cluster_private.py +0 -0
  187. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/cluster_test.py +0 -0
  188. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/commands.py +0 -0
  189. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/config_test.py +0 -0
  190. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/docker_container.py +0 -0
  191. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/docker_image.py +0 -0
  192. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/docker_manager.py +0 -0
  193. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/docker_resources.py +0 -0
  194. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/filestore.py +0 -0
  195. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/gcloud_context.py +0 -0
  196. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/gcloud_context_test.py +0 -0
  197. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/gcluster_manager.py +0 -0
  198. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/gcsfuse.py +0 -0
  199. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/jobset.py +0 -0
  200. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/kueue_manager.py +0 -0
  201. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/kueue_manager_test.py +0 -0
  202. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/monitoring.py +0 -0
  203. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/mtc.py +0 -0
  204. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/nap.py +0 -0
  205. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/network.py +0 -0
  206. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/nodepool.py +0 -0
  207. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/nodepool_test.py +0 -0
  208. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/pathways.py +0 -0
  209. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/pathways_test.py +0 -0
  210. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/ray.py +0 -0
  211. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/remote_state/__init__.py +0 -0
  212. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/remote_state/fuse_remote_state.py +0 -0
  213. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/remote_state/remote_state_client.py +0 -0
  214. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/resources.py +0 -0
  215. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/scheduling.py +0 -0
  216. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/scheduling_test.py +0 -0
  217. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/storage.py +0 -0
  218. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/system_characteristics_test.py +0 -0
  219. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/telemetry.py +0 -0
  220. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/telemetry_test.py +0 -0
  221. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/testing/__init__.py +0 -0
  222. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/testing/commands_tester.py +0 -0
  223. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/testing/commands_tester_test.py +0 -0
  224. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/updates.py +0 -0
  225. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/updates_test.py +0 -0
  226. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/vertex.py +0 -0
  227. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload.py +0 -0
  228. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload_decorators/__init__.py +0 -0
  229. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload_decorators/storage_decorator.py +0 -0
  230. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/core/workload_test.py +0 -0
  231. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/main.py +0 -0
  232. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/__init__.py +0 -0
  233. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/cluster.py +0 -0
  234. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/cluster_test.py +0 -0
  235. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/common_test.py +0 -0
  236. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/config.py +0 -0
  237. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/info.py +0 -0
  238. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/inspector.py +0 -0
  239. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/kind.py +0 -0
  240. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/storage.py +0 -0
  241. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/storage_test.py +0 -0
  242. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/validators.py +0 -0
  243. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/version.py +0 -0
  244. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/workload.py +0 -0
  245. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/parser/workload_test.py +0 -0
  246. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/telemetry_uploader.py +0 -0
  247. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/__init__.py +0 -0
  248. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/arm_gpu_workload_crate.yaml.j2 +0 -0
  249. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/cluster_preheat.yaml.j2 +0 -0
  250. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/filestore-pv.yaml +0 -0
  251. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/filestore-pvc.yaml +0 -0
  252. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/filestore-sc.yaml +0 -0
  253. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/fuse-pv.yaml +0 -0
  254. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/fuse-pvc.yaml +0 -0
  255. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/kueue_config.yaml.j2 +0 -0
  256. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/kueue_gke_default_topology.yaml.j2 +0 -0
  257. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/kueue_sub_slicing_topology.yaml.j2 +0 -0
  258. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/kueue_super_slicing_topology.yaml.j2 +0 -0
  259. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/mtc-cpc.yaml +0 -0
  260. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/templates/storage.yaml +0 -0
  261. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/__init__.py +0 -0
  262. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/console.py +0 -0
  263. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/console_test.py +0 -0
  264. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/execution_context.py +0 -0
  265. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/feature_flags.py +0 -0
  266. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/file.py +0 -0
  267. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/gcs_utils.py +0 -0
  268. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/kubectl.py +0 -0
  269. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/kueue.py +0 -0
  270. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/network.py +0 -0
  271. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/objects.py +0 -0
  272. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/templates.py +0 -0
  273. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/topology.py +0 -0
  274. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/topology_test.py +0 -0
  275. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/user_agent.py +0 -0
  276. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/user_agent_test.py +0 -0
  277. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/user_input.py +0 -0
  278. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/user_input_test.py +0 -0
  279. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/validation_test.py +0 -0
  280. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/versions.py +0 -0
  281. {xpk-0.17.1 → xpk-0.17.3}/src/xpk/utils/yaml.py +0 -0
  282. {xpk-0.17.1 → xpk-0.17.3}/src/xpk.egg-info/dependency_links.txt +0 -0
  283. {xpk-0.17.1 → xpk-0.17.3}/src/xpk.egg-info/entry_points.txt +0 -0
  284. {xpk-0.17.1 → xpk-0.17.3}/src/xpk.egg-info/requires.txt +0 -0
  285. {xpk-0.17.1 → xpk-0.17.3}/src/xpk.egg-info/top_level.txt +0 -0
  286. {xpk-0.17.1 → xpk-0.17.3}/tools/Dockerfile-kjob +0 -0
  287. {xpk-0.17.1 → xpk-0.17.3}/tools/build-kjob.sh +0 -0
  288. {xpk-0.17.1 → xpk-0.17.3}/tools/install-gke-auth-plugin.sh +0 -0
  289. {xpk-0.17.1 → xpk-0.17.3}/tools/install-xpk.sh +0 -0
  290. {xpk-0.17.1 → xpk-0.17.3}/xpk-large-scale-guide.sh +0 -0
  291. {xpk-0.17.1 → xpk-0.17.3}/xpk-notebooks.md +0 -0
  292. {xpk-0.17.1 → xpk-0.17.3}/xpk-slurm-commands.md +0 -0
  293. {xpk-0.17.1 → xpk-0.17.3}/xpk.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: xpk
3
- Version: 0.17.1
3
+ Version: 0.17.3
4
4
  Summary: xpk helps Cloud developers to orchestrate training jobs on accelerators on GKE.
5
5
  Author-email: XPK team <xpk-code-reviewers@google.com>
6
6
  License: Apache-2.0
@@ -261,91 +261,6 @@ kubectl get node --no-headers | wc -l
261
261
  [XPK] Try 1: Updating Kueue Controller Manager resources
262
262
  [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run.
263
263
  kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
264
- [XPK] Verifying kjob installation
265
- [XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run.
266
- kubectl-kjob help
267
- [XPK] kjob found
268
- [XPK] Applying kjob CDRs
269
- [XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run.
270
- kubectl kjob printcrds | kubectl apply --server-side -f -
271
- [XPK] Creating kjob CRDs succeeded
272
- [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run.
273
- kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
274
- [XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content:
275
-
276
- apiVersion: kjobctl.x-k8s.io/v1alpha1
277
- kind: JobTemplate
278
- metadata:
279
- name: xpk-def-batch
280
- namespace: default
281
- template:
282
- spec:
283
- parallelism: 1
284
- completions: 1
285
- completionMode: Indexed
286
- template:
287
- spec:
288
- dnsPolicy: ClusterFirstWithHostNet
289
- tolerations:
290
- - operator: "Exists"
291
- key: nvidia.com/gpu
292
- containers:
293
- - name: xpk-batch-container
294
- image: ubuntu:22.04
295
- workingDir: /
296
-
297
-
298
- priorityClassName: medium
299
- restartPolicy: OnFailure
300
- serviceAccountName:
301
-
302
- [XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run.
303
- kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
304
- [XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content:
305
-
306
- apiVersion: v1
307
- kind: PodTemplate
308
- metadata:
309
- name: xpk-def-pod
310
- namespace: default
311
- template:
312
- spec:
313
- tolerations:
314
- - effect: NoSchedule
315
- key: components.gke.io/gke-managed-components
316
- operator: Equal
317
- value: "true"
318
- containers:
319
- - name: xpk-interactive-container
320
- image: busybox:1.28
321
- command: [/bin/sh]
322
- workingDir: /
323
- initContainers:
324
- - name: init
325
- image: busybox:1.28
326
- command: ['/bin/mkdir', '-p', '/']
327
- serviceAccountName:
328
-
329
- [XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run.
330
- kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
331
- [XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content:
332
-
333
- apiVersion: kjobctl.x-k8s.io/v1alpha1
334
- kind: ApplicationProfile
335
- metadata:
336
- name: xpk-def-app-profile
337
- namespace: default
338
- spec:
339
- supportedModes:
340
- - name: Slurm
341
- template: xpk-def-batch
342
- requiredFlags: []
343
- - name: Interactive
344
- template: xpk-def-pod
345
- volumeBundles: []
346
-
347
- [XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run.
348
- kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
349
264
  [XPK] GKE commands done! Resources are created.
350
265
  [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster/details?project=golden-project
351
266
  [XPK] Exiting XPK cleanly
@@ -263,91 +263,6 @@ kubectl get node --no-headers | wc -l
263
263
  [XPK] Try 1: Updating Kueue Controller Manager resources
264
264
  [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run.
265
265
  kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
266
- [XPK] Verifying kjob installation
267
- [XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run.
268
- kubectl-kjob help
269
- [XPK] kjob found
270
- [XPK] Applying kjob CDRs
271
- [XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run.
272
- kubectl kjob printcrds | kubectl apply --server-side -f -
273
- [XPK] Creating kjob CRDs succeeded
274
- [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run.
275
- kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
276
- [XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content:
277
-
278
- apiVersion: kjobctl.x-k8s.io/v1alpha1
279
- kind: JobTemplate
280
- metadata:
281
- name: xpk-def-batch
282
- namespace: default
283
- template:
284
- spec:
285
- parallelism: 1
286
- completions: 1
287
- completionMode: Indexed
288
- template:
289
- spec:
290
- dnsPolicy: ClusterFirstWithHostNet
291
- tolerations:
292
- - operator: "Exists"
293
- key: nvidia.com/gpu
294
- containers:
295
- - name: xpk-batch-container
296
- image: ubuntu:22.04
297
- workingDir: /
298
-
299
-
300
- priorityClassName: medium
301
- restartPolicy: OnFailure
302
- serviceAccountName:
303
-
304
- [XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run.
305
- kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
306
- [XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content:
307
-
308
- apiVersion: v1
309
- kind: PodTemplate
310
- metadata:
311
- name: xpk-def-pod
312
- namespace: default
313
- template:
314
- spec:
315
- tolerations:
316
- - effect: NoSchedule
317
- key: components.gke.io/gke-managed-components
318
- operator: Equal
319
- value: "true"
320
- containers:
321
- - name: xpk-interactive-container
322
- image: busybox:1.28
323
- command: [/bin/sh]
324
- workingDir: /
325
- initContainers:
326
- - name: init
327
- image: busybox:1.28
328
- command: ['/bin/mkdir', '-p', '/']
329
- serviceAccountName:
330
-
331
- [XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run.
332
- kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
333
- [XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content:
334
-
335
- apiVersion: kjobctl.x-k8s.io/v1alpha1
336
- kind: ApplicationProfile
337
- metadata:
338
- name: xpk-def-app-profile
339
- namespace: default
340
- spec:
341
- supportedModes:
342
- - name: Slurm
343
- template: xpk-def-batch
344
- requiredFlags: []
345
- - name: Interactive
346
- template: xpk-def-pod
347
- volumeBundles: []
348
-
349
- [XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run.
350
- kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
351
266
  [XPK] GKE commands done! Resources are created.
352
267
  [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster/details?project=golden-project
353
268
  [XPK] Exiting XPK cleanly
@@ -278,91 +278,6 @@ kubectl get node --no-headers | wc -l
278
278
  [XPK] Try 1: Updating Kueue Controller Manager resources
279
279
  [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run.
280
280
  kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
281
- [XPK] Verifying kjob installation
282
- [XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run.
283
- kubectl-kjob help
284
- [XPK] kjob found
285
- [XPK] Applying kjob CDRs
286
- [XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run.
287
- kubectl kjob printcrds | kubectl apply --server-side -f -
288
- [XPK] Creating kjob CRDs succeeded
289
- [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run.
290
- kubectl get configmap golden-cluster-private-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
291
- [XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content:
292
-
293
- apiVersion: kjobctl.x-k8s.io/v1alpha1
294
- kind: JobTemplate
295
- metadata:
296
- name: xpk-def-batch
297
- namespace: default
298
- template:
299
- spec:
300
- parallelism: 1
301
- completions: 1
302
- completionMode: Indexed
303
- template:
304
- spec:
305
- dnsPolicy: ClusterFirstWithHostNet
306
- tolerations:
307
- - operator: "Exists"
308
- key: nvidia.com/gpu
309
- containers:
310
- - name: xpk-batch-container
311
- image: ubuntu:22.04
312
- workingDir: /
313
-
314
-
315
- priorityClassName: medium
316
- restartPolicy: OnFailure
317
- serviceAccountName:
318
-
319
- [XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run.
320
- kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
321
- [XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content:
322
-
323
- apiVersion: v1
324
- kind: PodTemplate
325
- metadata:
326
- name: xpk-def-pod
327
- namespace: default
328
- template:
329
- spec:
330
- tolerations:
331
- - effect: NoSchedule
332
- key: components.gke.io/gke-managed-components
333
- operator: Equal
334
- value: "true"
335
- containers:
336
- - name: xpk-interactive-container
337
- image: busybox:1.28
338
- command: [/bin/sh]
339
- workingDir: /
340
- initContainers:
341
- - name: init
342
- image: busybox:1.28
343
- command: ['/bin/mkdir', '-p', '/']
344
- serviceAccountName:
345
-
346
- [XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run.
347
- kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
348
- [XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content:
349
-
350
- apiVersion: kjobctl.x-k8s.io/v1alpha1
351
- kind: ApplicationProfile
352
- metadata:
353
- name: xpk-def-app-profile
354
- namespace: default
355
- spec:
356
- supportedModes:
357
- - name: Slurm
358
- template: xpk-def-batch
359
- requiredFlags: []
360
- - name: Interactive
361
- template: xpk-def-pod
362
- volumeBundles: []
363
-
364
- [XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run.
365
- kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
366
281
  [XPK] GKE commands done! Resources are created.
367
282
  [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster-private/details?project=golden-project
368
283
  [XPK] Exiting XPK cleanly
@@ -283,91 +283,6 @@ kubectl get node --no-headers | wc -l
283
283
  [XPK] Try 1: Updating Kueue Controller Manager resources
284
284
  [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run.
285
285
  kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
286
- [XPK] Verifying kjob installation
287
- [XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run.
288
- kubectl-kjob help
289
- [XPK] kjob found
290
- [XPK] Applying kjob CDRs
291
- [XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run.
292
- kubectl kjob printcrds | kubectl apply --server-side -f -
293
- [XPK] Creating kjob CRDs succeeded
294
- [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run.
295
- kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
296
- [XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content:
297
-
298
- apiVersion: kjobctl.x-k8s.io/v1alpha1
299
- kind: JobTemplate
300
- metadata:
301
- name: xpk-def-batch
302
- namespace: default
303
- template:
304
- spec:
305
- parallelism: 1
306
- completions: 1
307
- completionMode: Indexed
308
- template:
309
- spec:
310
- dnsPolicy: ClusterFirstWithHostNet
311
- tolerations:
312
- - operator: "Exists"
313
- key: nvidia.com/gpu
314
- containers:
315
- - name: xpk-batch-container
316
- image: ubuntu:22.04
317
- workingDir: /
318
-
319
-
320
- priorityClassName: medium
321
- restartPolicy: OnFailure
322
- serviceAccountName:
323
-
324
- [XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run.
325
- kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
326
- [XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content:
327
-
328
- apiVersion: v1
329
- kind: PodTemplate
330
- metadata:
331
- name: xpk-def-pod
332
- namespace: default
333
- template:
334
- spec:
335
- tolerations:
336
- - effect: NoSchedule
337
- key: components.gke.io/gke-managed-components
338
- operator: Equal
339
- value: "true"
340
- containers:
341
- - name: xpk-interactive-container
342
- image: busybox:1.28
343
- command: [/bin/sh]
344
- workingDir: /
345
- initContainers:
346
- - name: init
347
- image: busybox:1.28
348
- command: ['/bin/mkdir', '-p', '/']
349
- serviceAccountName:
350
-
351
- [XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run.
352
- kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
353
- [XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content:
354
-
355
- apiVersion: kjobctl.x-k8s.io/v1alpha1
356
- kind: ApplicationProfile
357
- metadata:
358
- name: xpk-def-app-profile
359
- namespace: default
360
- spec:
361
- supportedModes:
362
- - name: Slurm
363
- template: xpk-def-batch
364
- requiredFlags: []
365
- - name: Interactive
366
- template: xpk-def-pod
367
- volumeBundles: []
368
-
369
- [XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run.
370
- kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
371
286
  [XPK] GKE commands done! Resources are created.
372
287
  [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster/details?project=golden-project
373
288
  [XPK] Exiting XPK cleanly
@@ -294,91 +294,6 @@ kubectl get node --no-headers | wc -l
294
294
  [XPK] Try 1: Updating Kueue Controller Manager resources
295
295
  [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run.
296
296
  kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
297
- [XPK] Verifying kjob installation
298
- [XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run.
299
- kubectl-kjob help
300
- [XPK] kjob found
301
- [XPK] Applying kjob CDRs
302
- [XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run.
303
- kubectl kjob printcrds | kubectl apply --server-side -f -
304
- [XPK] Creating kjob CRDs succeeded
305
- [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run.
306
- kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
307
- [XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content:
308
-
309
- apiVersion: kjobctl.x-k8s.io/v1alpha1
310
- kind: JobTemplate
311
- metadata:
312
- name: xpk-def-batch
313
- namespace: default
314
- template:
315
- spec:
316
- parallelism: 1
317
- completions: 1
318
- completionMode: Indexed
319
- template:
320
- spec:
321
- dnsPolicy: ClusterFirstWithHostNet
322
- tolerations:
323
- - operator: "Exists"
324
- key: nvidia.com/gpu
325
- containers:
326
- - name: xpk-batch-container
327
- image: ubuntu:22.04
328
- workingDir: /
329
-
330
-
331
- priorityClassName: medium
332
- restartPolicy: OnFailure
333
- serviceAccountName:
334
-
335
- [XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run.
336
- kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
337
- [XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content:
338
-
339
- apiVersion: v1
340
- kind: PodTemplate
341
- metadata:
342
- name: xpk-def-pod
343
- namespace: default
344
- template:
345
- spec:
346
- tolerations:
347
- - effect: NoSchedule
348
- key: components.gke.io/gke-managed-components
349
- operator: Equal
350
- value: "true"
351
- containers:
352
- - name: xpk-interactive-container
353
- image: busybox:1.28
354
- command: [/bin/sh]
355
- workingDir: /
356
- initContainers:
357
- - name: init
358
- image: busybox:1.28
359
- command: ['/bin/mkdir', '-p', '/']
360
- serviceAccountName:
361
-
362
- [XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run.
363
- kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
364
- [XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content:
365
-
366
- apiVersion: kjobctl.x-k8s.io/v1alpha1
367
- kind: ApplicationProfile
368
- metadata:
369
- name: xpk-def-app-profile
370
- namespace: default
371
- spec:
372
- supportedModes:
373
- - name: Slurm
374
- template: xpk-def-batch
375
- requiredFlags: []
376
- - name: Interactive
377
- template: xpk-def-pod
378
- volumeBundles: []
379
-
380
- [XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run.
381
- kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
382
297
  [XPK] GKE commands done! Resources are created.
383
298
  [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster/details?project=golden-project
384
299
  [XPK] Exiting XPK cleanly
@@ -265,91 +265,6 @@ kubectl get node --no-headers | wc -l
265
265
  [XPK] Try 1: Updating Kueue Controller Manager resources
266
266
  [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run.
267
267
  kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
268
- [XPK] Verifying kjob installation
269
- [XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run.
270
- kubectl-kjob help
271
- [XPK] kjob found
272
- [XPK] Applying kjob CDRs
273
- [XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run.
274
- kubectl kjob printcrds | kubectl apply --server-side -f -
275
- [XPK] Creating kjob CRDs succeeded
276
- [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run.
277
- kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
278
- [XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content:
279
-
280
- apiVersion: kjobctl.x-k8s.io/v1alpha1
281
- kind: JobTemplate
282
- metadata:
283
- name: xpk-def-batch
284
- namespace: default
285
- template:
286
- spec:
287
- parallelism: 1
288
- completions: 1
289
- completionMode: Indexed
290
- template:
291
- spec:
292
- dnsPolicy: ClusterFirstWithHostNet
293
- tolerations:
294
- - operator: "Exists"
295
- key: nvidia.com/gpu
296
- containers:
297
- - name: xpk-batch-container
298
- image: ubuntu:22.04
299
- workingDir: /
300
-
301
-
302
- priorityClassName: medium
303
- restartPolicy: OnFailure
304
- serviceAccountName:
305
-
306
- [XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run.
307
- kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
308
- [XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content:
309
-
310
- apiVersion: v1
311
- kind: PodTemplate
312
- metadata:
313
- name: xpk-def-pod
314
- namespace: default
315
- template:
316
- spec:
317
- tolerations:
318
- - effect: NoSchedule
319
- key: components.gke.io/gke-managed-components
320
- operator: Equal
321
- value: "true"
322
- containers:
323
- - name: xpk-interactive-container
324
- image: busybox:1.28
325
- command: [/bin/sh]
326
- workingDir: /
327
- initContainers:
328
- - name: init
329
- image: busybox:1.28
330
- command: ['/bin/mkdir', '-p', '/']
331
- serviceAccountName:
332
-
333
- [XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run.
334
- kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
335
- [XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content:
336
-
337
- apiVersion: kjobctl.x-k8s.io/v1alpha1
338
- kind: ApplicationProfile
339
- metadata:
340
- name: xpk-def-app-profile
341
- namespace: default
342
- spec:
343
- supportedModes:
344
- - name: Slurm
345
- template: xpk-def-batch
346
- requiredFlags: []
347
- - name: Interactive
348
- template: xpk-def-pod
349
- volumeBundles: []
350
-
351
- [XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run.
352
- kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
353
268
  [XPK] GKE commands done! Resources are created.
354
269
  [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster/details?project=golden-project
355
270
  [XPK] Exiting XPK cleanly
@@ -265,91 +265,6 @@ kubectl get node --no-headers | wc -l
265
265
  [XPK] Try 1: Updating Kueue Controller Manager resources
266
266
  [XPK] Task: `Updating Kueue Controller Manager resources` is implemented by the following command not running since it is a dry run.
267
267
  kubectl patch deployment kueue-controller-manager -n kueue-system --type='strategic' --patch='{"spec": {"template": {"spec": {"containers": [{"name": "manager", "resources": {"limits": {"memory": "4096Mi"}}}]}}}}'
268
- [XPK] Verifying kjob installation
269
- [XPK] Task: `Verify kjob installation ` is implemented by the following command not running since it is a dry run.
270
- kubectl-kjob help
271
- [XPK] kjob found
272
- [XPK] Applying kjob CDRs
273
- [XPK] Task: `Create kjob CRDs on cluster` is implemented by the following command not running since it is a dry run.
274
- kubectl kjob printcrds | kubectl apply --server-side -f -
275
- [XPK] Creating kjob CRDs succeeded
276
- [XPK] Task: `GKE Cluster Get ConfigMap` is implemented by the following command not running since it is a dry run.
277
- kubectl get configmap golden-cluster-resources-configmap -o=custom-columns="ConfigData:data" --no-headers=true
278
- [XPK] Temp file (4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61) content:
279
-
280
- apiVersion: kjobctl.x-k8s.io/v1alpha1
281
- kind: JobTemplate
282
- metadata:
283
- name: xpk-def-batch
284
- namespace: default
285
- template:
286
- spec:
287
- parallelism: 1
288
- completions: 1
289
- completionMode: Indexed
290
- template:
291
- spec:
292
- dnsPolicy: ClusterFirstWithHostNet
293
- tolerations:
294
- - operator: "Exists"
295
- key: nvidia.com/gpu
296
- containers:
297
- - name: xpk-batch-container
298
- image: ubuntu:22.04
299
- workingDir: /
300
-
301
-
302
- priorityClassName: medium
303
- restartPolicy: OnFailure
304
- serviceAccountName:
305
-
306
- [XPK] Task: `Creating JobTemplate` is implemented by the following command not running since it is a dry run.
307
- kubectl apply -f 4abb796ed6e7c9d7256a51f13124efd989fc12ee83839bed432fcf7d64f68e61
308
- [XPK] Temp file (a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8) content:
309
-
310
- apiVersion: v1
311
- kind: PodTemplate
312
- metadata:
313
- name: xpk-def-pod
314
- namespace: default
315
- template:
316
- spec:
317
- tolerations:
318
- - effect: NoSchedule
319
- key: components.gke.io/gke-managed-components
320
- operator: Equal
321
- value: "true"
322
- containers:
323
- - name: xpk-interactive-container
324
- image: busybox:1.28
325
- command: [/bin/sh]
326
- workingDir: /
327
- initContainers:
328
- - name: init
329
- image: busybox:1.28
330
- command: ['/bin/mkdir', '-p', '/']
331
- serviceAccountName:
332
-
333
- [XPK] Task: `Creating PodTemplate` is implemented by the following command not running since it is a dry run.
334
- kubectl apply -f a63aa3c4593c38ad90671fd8b067d1886f6313ad558379b364b51791aa50f4e8
335
- [XPK] Temp file (1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486) content:
336
-
337
- apiVersion: kjobctl.x-k8s.io/v1alpha1
338
- kind: ApplicationProfile
339
- metadata:
340
- name: xpk-def-app-profile
341
- namespace: default
342
- spec:
343
- supportedModes:
344
- - name: Slurm
345
- template: xpk-def-batch
346
- requiredFlags: []
347
- - name: Interactive
348
- template: xpk-def-pod
349
- volumeBundles: []
350
-
351
- [XPK] Task: `Creating AppProfile` is implemented by the following command not running since it is a dry run.
352
- kubectl apply -f 1d13ddebae3c90a05ba26b312df088982dd0df0edc4f4013b88384e476c20486
353
268
  [XPK] GKE commands done! Resources are created.
354
269
  [XPK] See your GKE Cluster here: https://console.cloud.google.com/kubernetes/clusters/details/us-central1/golden-cluster/details?project=golden-project
355
270
  [XPK] Exiting XPK cleanly