-

Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

git clone https://github.com/aws-samples/awsome-distributed-training/

cd awsome-distributed-training/1.architectures/5.sagemaker_hyperpods/LifecycleScripts/base-config

  1. catatan

  2. catatan

    1. Tip

      Untuk mempelajari selengkapnya, lihat .

    2. penting

      {

    "ClusterConfig": {
        "ClusterArn": "arn:aws:sagemaker:us-west-2:111122223333:cluster/abcde01234yz",
        "ClusterName": "your-hyperpod-cluster"
    },
    "InstanceGroups": [
        {
            "Name": "controller-machine",
            "InstanceType": "ml.c5.xlarge",
            "Instances": [
                {
                    "InstanceName": "controller-machine-1",
                    "AgentIpAddress": "111.222.333.444",
                    "CustomerIpAddress": "111.222.333.444",
                    "InstanceId": "i-12345abcedfg67890"
                }
            ]
        },
        {
            "Name": "login-group",
            "InstanceType": "ml.m5.xlarge",
            "Instances": [
                {
                    "InstanceName": "login-group-1",
                    "AgentIpAddress": "111.222.333.444",
                    "CustomerIpAddress": "111.222.333.444",
                    "InstanceId": "i-12345abcedfg67890"
                }
            ]
        },
        {
            "Name": "compute-nodes",
            "InstanceType": "ml.trn1.32xlarge",
            "Instances": [
                {
                    "InstanceName": "compute-nodes-1",
                    "AgentIpAddress": "111.222.333.444",
                    "CustomerIpAddress": "111.222.333.444",
                    "InstanceId": "i-12345abcedfg67890"
                },
                {
                    "InstanceName": "compute-nodes-2",
                    "AgentIpAddress": "111.222.333.444",
                    "CustomerIpAddress": "111.222.333.444",
                    "InstanceId": "i-12345abcedfg67890"
                },
                {
                    "InstanceName": "compute-nodes-3",
                    "AgentIpAddress": "111.222.333.444",
                    "CustomerIpAddress": "111.222.333.444",
                    "InstanceId": "i-12345abcedfg67890"
                },
                {
                    "InstanceName": "compute-nodes-4",
                    "AgentIpAddress": "111.222.333.444",
                    "CustomerIpAddress": "111.222.333.444",
                    "InstanceId": "i-12345abcedfg67890"
                }
            ]
        }
    ]
}

    3. catatan

      1. # Install Docker/Enroot/Pyxis
if Config.enable_docker_enroot_pyxis:
    ExecuteBashScript("./utils/install_docker.sh").run()
    ExecuteBashScript("./utils/install_enroot_pyxis.sh").run(node_type)

      2. # Install metric exporting software and Prometheus for observability

if Config.enable_observability:
    if node_type == SlurmNodeType.COMPUTE_NODE:
        ExecuteBashScript("./utils/install_docker.sh").run()
        ExecuteBashScript("./utils/install_dcgm_exporter.sh").run()
        ExecuteBashScript("./utils/install_efa_node_exporter.sh").run()

    if node_type == SlurmNodeType.HEAD_NODE:
        wait_for_scontrol()
        ExecuteBashScript("./utils/install_docker.sh").run()
        ExecuteBashScript("./utils/install_slurm_exporter.sh").run()
        ExecuteBashScript("./utils/install_prometheus.sh").run()

  3. "LifeCycleConfig": { 

    "SourceS3URI": "s3://sagemaker-hyperpod-lifecycle/src",
    "OnCreate": "on_create.sh"
}

    └── lifecycle_files // your local folder
    ├── provisioning_parameters.json
    ├── on_create.sh
    ├── lifecycle_script.py
    └── ... // more setup scrips to be fed into lifecycle_script.py

    aws s3 cp --recursive ./lifecycle_scripts s3://sagemaker-hyperpod-lifecycle/src