使用教程

{
    "region": "us-east-2",              # 一个有效的 AWS 区域名称
    "high_availability": {              # 高可用性。您可以将其指定为 'false' 以关闭 HA
        "nat_count": 3,                 # NAT 实例的数量
        "jumpserver_instance_type": {   # jumpserver 配置。您也可以指定实例类型名称
            "cpu_arch": "x86_64",       # jumpserver 搜索项 - CPU 架构
            "cpu_providers": ["amd"],   # jumpserver 搜索项 - CPU 提供商
            "vcpu_count": 2,            # jumpserver 搜索项 - vCPU 数量
            "memory_gb": 4              # jumpserver 搜索项 - RAM（GiB）
        }
    },
    "cni_name": "calico",               # 集群网络插件，仅支持 flannel 和 calico
    "management_nodes": {               # 管理节点配置
        "nat_instance_type": {          # NAT 配置。您也可以指定实例类型名称
            "cpu_arch": "x86_64",
            "cpu_providers": ["amd"],
            "vcpu_count": 2,
            "memory_gb": 4
        },
        "master_instance_type": "c7a.xlarge"  # master 配置。您也可以指定搜索项
    },
    "worker_groups": [                        # 工作节点组，它是一个列表[字典]
        {
            "group_name": "a10_group",        # 组的唯一名称
            "kata_enabled": false,            # 是否安装 Kata 安全容器（需要嵌套虚拟化支持）
            "instance_type": {                # 工作节点配置。您也可以指定实例类型名称
                "cpu_arch": "x86_64",
                "cpu_providers": [],
                "vcpu_count": {
                    "start": 1,
                    "end": 16
                },
                "memory_gb": {
                    "start": 32,
                    "end": 10000
                },
                "mem_per_cpu_gb": {
                    "start": 0,
                    "end": 1000000
                },
                "acc_names": ["a10g"],      # 加速器（GPU）名称
                "acc_count": {              # 每个节点的加速器（GPU）数量
                    "start": 1,
                    "end": 1
                }
            },
            "init_workers": {
                "total_workers": 1,         # 初始总工作节点数
                "od_workers": 1,            # 初始按需工作节点数
                "fixed_workers": 0,         # 固定按需工作节点数
            }
            "schedule_priority": "",        # 可用区优先或区域优先（默认）
            "os_disk_gb": 10,               # OS 卷/磁盘大小
            "container_disk_ini_gb": 20,    # 容器初始卷/磁盘大小
            "container_disk_max_gb": 300,   # 容器最大卷/磁盘大小
            "autoscaling": "full",          # 自动扩展策略
            "od_to_spot": {                 # 按需实例到竞价实例的切换计划
                                            # 您可以指定一个空字典以禁用 od_to_spot
                                            # 或者，您可以指定一个 'copy_from' 从另一个
                                            # 工作节点组复制
                "rate_in_minutes": 15,
                "delay_in_minutes": 15
            }
        },
        {
            "group_name": "cpu_group",
            "instance_type": "c7a.xlarge",
            "init_workers": {
                "total_workers": 1,
                "od_workers": 1,
                "fixed_workers": 0
            }
            "schedule_priority": "",
            "os_disk_gb": 10,
            "container_disk_ini_gb": 20,
            "container_disk_max_gb": 300,
            "autoscaling": "off",
            "od_to_spot": {
                "copy_from": "a10_group"    # 您可以指定一个空字典以禁用 od_to_spot
            }
        }
    ]
}

Checking the ingested request attributes ...
The format of configs is checked and good to go.
Checking the contents of the configs.
Worker group: a10_group will use instance type: g5.xlarge.
Worker group: cpu_group will use instance type: c5a.xlarge.
[*] scalex (scale-x) kubernetes stack started creating ...
Stack id: k8s-lml6uq7wbk5e
...
...
...
Worker group: cpu_group provision summary: spot: 1 | od: 1 | total: 2
Worker group: cpu_group: All planned 2 node(s) provisioned.

Scalex k8s stack summary:
...

Please connect to the cluster: ssh ubuntu@XXX.XXX.XXX.XXX -i /your/private/key
[*] The IP address above is *elastic* and will keep unchanged during the lifecycle of this cluster.

apiVersion: apps/v1  
kind: Deployment  
metadata:  
  name: deepseek-deployment  
  namespace: deepseek  
  labels:  
    app: deepseek  
spec:  
  replicas: 3
  selector:  
    matchLabels:  
      app: deepseek  
  template:  
    metadata:  
      labels:  
        app: deepseek  
    spec:  
      tolerations:  
        - key: "nvidia.com/gpu"  
          operator: "Exists"  
          effect: "NoSchedule"  
      volumes:  
      - name: cache-volume  
        hostPath:  
          path: /tmp/deepseek  
          type: DirectoryOrCreate  
      - name: shm  
        emptyDir:  
          medium: Memory  
          sizeLimit: "2Gi"  
      containers:  
      - name: deepseek  
        image: vllm/vllm-openai:latest  
        command: ["/bin/sh", "-c"]  
        args: [  
          "vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-7B  --trust-remote-code --max_model_len 2048"  
        ]  
        env:
        - name: HUGGING_FACE_HUB_TOKEN
          valueFrom:
            secretKeyRef:
              name: huggingface-token
              key: HF_TOKEN
        ports:  
        - containerPort: 8000  
        resources:  
          requests:  
            nvidia.com/gpu: "1"  
          limits:  
            nvidia.com/gpu: "1"  
        volumeMounts:  
        - mountPath: /root/.cache/huggingface  
          name: cache-volume  
        - name: shm  
          mountPath: /dev/shm  
---  
apiVersion: v1  
kind: Service  
metadata:  
  name: deepseek-svc  
  namespace: deepseek  
spec:  
  ports:  
  - name: http  
    port: 80  
    protocol: TCP  
    targetPort: 8000
  selector:  
    app: deepseek  
  type: ClusterIP