Path Lines of Code RELEASE_NOTE.md 279 contrib/aks-engine/readme.md 53 contrib/api-stress-test/readme.md 83 contrib/autoscaler/README.md 61 contrib/debug-tools/examples/caffe2-resnet50-debug.yaml 49 contrib/ha-storage/README.md 155 contrib/kubespray/roles/docker-runtime/install/files/daemon-openpai-default-runtime.json 3 contrib/kubespray/roles/docker-runtime/install/files/daemon-openpai-nvidia-runtime.json 10 contrib/profiler/Example/Typical Example.md 117 contrib/profiler/README.md 47 contrib/remote-dev-tool/README.md 63 contrib/rocm-container-runtime/README.md 43 contrib/submit-job-v2/README.md 35 contrib/submit-job-v2/package.json 56 contrib/submit-job-v2/tsconfig.json 55 contrib/submit-job-v2/tslint.json 20 docs_zh_CN/index.md 10 docs_zh_CN/manual/cluster-admin/README.md 20 docs_zh_CN/manual/cluster-admin/basic-management-operations.md 198 docs_zh_CN/manual/cluster-admin/how-to-add-and-remove-nodes.md 62 docs_zh_CN/manual/cluster-admin/how-to-autoscale-the-cluster.md 27 docs_zh_CN/manual/cluster-admin/how-to-customize-cluster-by-plugins.md 27 docs_zh_CN/manual/cluster-admin/how-to-manage-users-and-groups.md 160 docs_zh_CN/manual/cluster-admin/how-to-renew-k8s-cert.md 98 docs_zh_CN/manual/cluster-admin/how-to-set-up-docker-image-cache.md 90 docs_zh_CN/manual/cluster-admin/how-to-set-up-storage.md 319 docs_zh_CN/manual/cluster-admin/how-to-set-up-virtual-clusters.md 386 docs_zh_CN/manual/cluster-admin/how-to-uninstall-openpai.md 67 docs_zh_CN/manual/cluster-admin/how-to-use-alert-system.md 218 docs_zh_CN/manual/cluster-admin/installation-faqs-and-troubleshooting.md 127 docs_zh_CN/manual/cluster-admin/installation-guide.md 316 docs_zh_CN/manual/cluster-admin/recommended-practice.md 33 docs_zh_CN/manual/cluster-admin/troubleshooting.md 91 docs_zh_CN/manual/cluster-admin/upgrade-guide.md 49 docs_zh_CN/manual/cluster-user/README.md 14 docs_zh_CN/manual/cluster-user/docker-images-and-job-examples.md 40 docs_zh_CN/manual/cluster-user/examples/hello-world-job.yaml 38 docs_zh_CN/manual/cluster-user/frequently-asked-questions.md 4 docs_zh_CN/manual/cluster-user/how-to-debug-jobs.md 47 docs_zh_CN/manual/cluster-user/how-to-manage-data.md 59 docs_zh_CN/manual/cluster-user/how-to-run-distributed-job.md 26 docs_zh_CN/manual/cluster-user/how-to-use-advanced-job-settings.md 220 docs_zh_CN/manual/cluster-user/quick-start.md 41 docs_zh_CN/manual/cluster-user/use-jupyter-notebook-extension.md 2 docs_zh_CN/manual/cluster-user/use-marketplace.md 13 docs_zh_CN/manual/cluster-user/use-vscode-extension.md 34 examples/Distributed-example/Lite-imagenet-single-mul-DDP-gloo.yaml 50 examples/Distributed-example/Lite-imagenet-single-mul-DDP-nccl-gloo.py 104 examples/Distributed-example/LiteApex-imagenet-single-mul-DDP-nccl-gloo.py 108 examples/Distributed-example/PytorchExample-imagenet-single-mul-DDP-nccl-gloo.py 322 examples/Distributed-example/cifar10-single-mul-DDP-gloo-Apex-mixed.yaml 46 examples/Distributed-example/cifar10-single-mul-DDP-gloo.yaml 46 examples/Distributed-example/cifar10-single-mul-DDP-nccl-Apex-mixed.yaml 45 examples/Distributed-example/cifar10-single-mul-DDP-nccl-gloo-Apex-mixed.py 119 examples/Distributed-example/cifar10-single-mul-DDP-nccl-gloo.py 104 examples/Distributed-example/cifar10-single-mul-DDP-nccl.yaml 45 examples/Distributed-example/cifar10-single-node-gpus-cpu-DP.py 130 examples/Distributed-example/cifar10-single-node-gpus-cpu-DP.yaml 31 examples/Dockerfiles/autobuild_docker/README.md 28 examples/Dockerfiles/autobuild_docker/paitest.py 1 examples/MXNet_cifar10/README.md 9 examples/MXNet_cifar10/src/train_cifar10.py 161 examples/MXNet_cifar10/yaml/cifar10_resnet20_1gpu.yaml 35 examples/cluster-configuration/k8s-role-definition.yaml 42 examples/cluster-configuration/kubernetes-configuration.yaml 13 examples/cluster-configuration/layout.yaml 75 examples/cluster-configuration/services-configuration.yaml 3 examples/cntk_mnist/README.md 7 examples/cntk_mnist/yaml/ConvNet_gpu1.yaml 36 examples/mnist_500_tasks/README.md 29 examples/mnist_500_tasks/src/get_results.py 36 examples/mnist_500_tasks/src/mnist_lr_500.py 131 examples/mnist_500_tasks/src/show_results.ipynb 37 examples/mnist_500_tasks/yaml/CPU_500Task_MNIST.yaml 67 examples/pytorch_cifar10/README.md 30 examples/pytorch_cifar10/src/cifar.py 124 examples/pytorch_cifar10/src/horovod_cifar.py 126 examples/pytorch_cifar10/src/init.sh 12 examples/pytorch_cifar10/yaml/Resnet18_12cpu.yaml 37 examples/pytorch_cifar10/yaml/Resnet18_1gpu.yaml 37 examples/pytorch_cifar10/yaml/Resnet18_4gpu.yaml 39 examples/pytorch_cifar10/yaml/Resnet18_horovod.yaml 45 examples/tensorflow_cifar10/README.md 21 examples/tensorflow_cifar10/cifar10_vgg16_tf_cpu.yaml 32 examples/tensorflow_cifar10/cifar10_vgg16_tf_gpu.yaml 32 examples/tensorflow_cifar10/cifar10_vgg16_tf_gpu_distributed.yaml 32 examples/tensorflow_cifar10/cifar10_vgg16_tf_gpu_horovod.yaml 35 examples/tensorflow_cifar10/src/cifar10_vgg16_tf.py 42 examples/tensorflow_cifar10/src/cifar10_vgg16_tf_distributed.py 45 examples/tensorflow_cifar10/src/cifar10_vgg16_tf_horovod.py 59 src/alert-manager/config/alert-manager.md 83 src/alert-manager/src/alert-handler/package.json 51 src/alert-manager/src/job-status-change-notification/package.json 49 src/cluster/config/cluster.md 143 src/database-controller/README.md 2 src/database-controller/sdk/package.json 25 src/database-controller/src/package.json 50 src/database-controller/test-case.md 75 src/device-plugin/README.md 11 src/dshuttle/config/dshuttle.md 192 src/fluentd/src/fluent-plugin-pgjson/README.md 79 src/grafana/config/grafana.md 42 src/internal-storage/README.md 64 src/job-exporter/config/job-exporter.md 59 src/job-exporter/test/data/docker_inspect_sample.json 101 src/job-exporter/test/data/nvidia_smi_out_of_order.xml 1024 src/job-exporter/test/data/nvidia_smi_outdated_gpu.xml 29 src/job-exporter/test/data/nvidia_smi_sample.xml 427 src/job-exporter/test/data/nvidia_smi_sample_ecc_unsupported.xml 368 src/job-exporter/test/data/rocm_smi.json 128 src/k8s-job-exit-spec/config/user-manual.md 16 src/log-manager/config/log-manager.md 32 src/node-exporter/config/node-exporter.md 35 src/postgresql/README.md 20 src/postgresql/src/init_table.sql 1 src/postgresql/src/once_init_table.sql 1 src/prometheus/config/prometheus.md 50 src/pylon/README.md 1 src/pylon/config/pylon.md 38 src/rest-server/README.md 1 src/rest-server/config/rest-server.md 44 src/rest-server/jsconfig.json 12 src/rest-server/package.json 92 src/storage-manager/README.md 80 src/watchdog/src/go.mod 15 src/webportal/README.md 57 src/webportal/config/webportal.md 43 src/webportal/package.json 142 src/webportal/src/assets/img/job-wizard-distributed.svg 7 src/webportal/src/assets/img/job-wizard-edit-config.svg 5 src/webportal/src/assets/img/job-wizard-single.svg 6 subprojects/frameworklauncher/README.md 29 subprojects/frameworklauncher/yarn/README.md 60 subprojects/frameworklauncher/yarn/doc/USERMANUAL.md 653 subprojects/frameworklauncher/yarn/doc/example/ExampleFramework.json 19 subprojects/frameworklauncher/yarn/pom.xml 189 subprojects/frameworklauncher/yarn/src/main/resources/log4j.properties 66 subprojects/frameworklauncher/yarn/src/test/resources/TestAntiaffinityAllocation.json 49 subprojects/frameworklauncher/yarn/src/test/resources/TestApplicationCompletionPolicy.json 53 subprojects/frameworklauncher/yarn/src/test/resources/TestGangAllocation.json 49 subprojects/frameworklauncher/yarn/src/test/resources/TestInputs/FrameworkDescriptionMini.json 19 subprojects/frameworklauncher/yarn/src/test/resources/TestInputs/WrongFrameworkDescription.json 95 subprojects/frameworklauncher/yarn/src/test/resources/log4j.properties 22