{
  "autoDestroy": false,
  "bundlePath": "/home/mnm/workspaces/runpod-devenv-module/templates/llm-inference/.devenv/state/runpod/bundles/job-20260319T114904Z-ccaf43cd.tar.gz",
  "bundleUploadedAt": "2026-03-19T11:49:31.870930+00:00",
  "createdAt": "2026-03-19T11:49:05.068533+00:00",
  "diskGb": 160,
  "downloadedAt": "2026-03-19T11:53:40.817957+00:00",
  "gpuSelection": {
    "available": true,
    "communityCloud": true,
    "displayName": "RTX A5000",
    "id": "NVIDIA RTX A5000",
    "memoryInGb": 24.0,
    "onDemandPricePerHr": null,
    "secureCloud": true,
    "spotPricePerHr": null,
    "stockStatus": "High"
  },
  "gpuType": "NVIDIA RTX A5000",
  "image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
  "jobId": "job-20260319T114904Z-ccaf43cd",
  "lastRemoteStatus": {
    "message": "vLLM server is running and the probe request succeeded",
    "model": "Qwen/Qwen2.5-0.5B-Instruct",
    "port": "8000",
    "status": "completed",
    "template": "llm-inference",
    "updatedAt": "2026-03-19T11:53:12Z"
  },
  "launchMode": "workspace",
  "launchedAt": "2026-03-19T11:49:33.398881+00:00",
  "localOutputDir": "/home/mnm/workspaces/runpod-devenv-module/templates/llm-inference/.devenv/state/runpod/outputs/runpod-20260319T114904Z-bfd218fc",
  "podCreateResponse": {
    "containerDiskInGb": 160,
    "costPerHr": 0.27,
    "desiredStatus": "RUNNING",
    "env": [
      "MODEL_NAME=Qwen/Qwen2.5-0.5B-Instruct",
      "PROBE_PROMPT=Reply with a single short greeting from RunPod.",
      "VLLM_GPU_MEMORY_UTILIZATION=0.85",
      "VLLM_HOST=0.0.0.0",
      "VLLM_INSTALL_COMMAND=pip install --upgrade pip && pip install vllm --extra-index-url https://download.pytorch.org/whl/cu128",
      "VLLM_PORT=8000",
      "PYTHONUNBUFFERED=1",
      "SERVE_COMMAND=vllm serve \"$MODEL_NAME\" --host \"$VLLM_HOST\" --port \"$VLLM_PORT\" --gpu-memory-utilization \"$VLLM_GPU_MEMORY_UTILIZATION\" --max-model-len \"$VLLM_MAX_MODEL_LEN\"",
      "SIMULATE_ONLY=0",
      "VLLM_MAX_MODEL_LEN=4096",
      "VLLM_READINESS_TIMEOUT_SECONDS=900",
      "VLLM_VENV_DIR=.venv",
      "PUBLIC_KEY=ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIP8Sz0duXbGb7qNKmePuFC/CyP+1S1IJVtDn6UDbohy0\nssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIPIMlUNghkurym2x9wmtp7Hai3mjc4AGKJLCXQ2Duunl mnm@devenv-586391a4.cultscale.net"
    ],
    "gpuCount": 1,
    "id": "swa1jyq47jq9t8",
    "imageName": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
    "lastStatusChange": "Rented by User: Thu Mar 19 2026 11:49:04 GMT+0000 (Coordinated Universal Time)",
    "machine": {
      "gpuDisplayName": "RTX A5000",
      "location": "CA"
    },
    "memoryInGb": 50,
    "name": "runpod-runner-job-20260319T114904Z-ccaf43cd",
    "ports": "22/tcp,8000/http",
    "vcpuCount": 9,
    "volumeInGb": 0,
    "volumeMountPath": "/workspace"
  },
  "podId": "swa1jyq47jq9t8",
  "podType": "RESERVED",
  "ports": "22/tcp,8000/http",
  "profilePath": "/nix/store/3q22z1q25hybxmmhkgv342mfc5irsl3y-runpod-profile-serve.json",
  "remoteBundlePath": "/workspace/job-20260319T114904Z-ccaf43cd.tar.gz",
  "remoteEntrypoint": "./serve.sh",
  "remoteEnvKeys": [
    "MODEL_NAME",
    "PROBE_PROMPT",
    "PYTHONUNBUFFERED",
    "SERVE_COMMAND",
    "SIMULATE_ONLY",
    "VLLM_GPU_MEMORY_UTILIZATION",
    "VLLM_HOST",
    "VLLM_INSTALL_COMMAND",
    "VLLM_MAX_MODEL_LEN",
    "VLLM_PORT",
    "VLLM_READINESS_TIMEOUT_SECONDS",
    "VLLM_VENV_DIR"
  ],
  "remoteWorkspaceRoot": "/workspace/job-20260319T114904Z-ccaf43cd",
  "runId": "runpod-20260319T114904Z-bfd218fc",
  "sshHost": "69.30.85.192",
  "sshPort": 22168,
  "sshReadyAt": "2026-03-19T11:49:28.103367+00:00",
  "sshUser": "root",
  "timeoutMinutes": 60,
  "workspaceDir": "/home/mnm/workspaces/runpod-devenv-module/templates/llm-inference/workspace"
}