{
    "name": "vLLM Dev Container",
    "image": "vllm/vllm-openai:v0.11.0",
    "runArgs": ["--gpus", "all",
               "-p", "8000:8000",
               "-p", "8080:8080",
               "--restart=unless-stopped"],
    "mounts": [
        "source=/data/lbg/models,target=/data/lbg/models,type=bind",
        "source=/data/lbg/latex_fanyi/,target=/workspace,type=bind"
    ],
    "workspaceFolder": "/workspace",
    "postCreateCommand": "pip install --ignore-installed blinker==1.9.0 flask flask-cors requests && cd /workspace && (vllm serve /data/lbg/models/brandonbeiler_InternVL3_5-8B-FP8-Dynamic --quantization compressed-tensors --served-model-name internvl3_5-8b --trust-remote-code --max-model-len 2048 --tensor-parallel-size 1 &) && sleep 10 && python3 /workspace/server.py",
    "customizations": {
        "vscode": {
            "extensions": [
                "ms-python.python",
                "ms-python.vscode-pylance"
            ]
        }
    }
}

# 手動(dòng)停止容器，看它是否會(huì)自動(dòng)重啟
docker stop latex-ai-container
# 等待 15 秒
sleep 15
# 檢查容器是否自動(dòng)啟動(dòng)
docker ps | grep latex-ai-container
預(yù)期結(jié)果：容器應(yīng)該自動(dòng)重新啟動(dòng)（因?yàn)?unless-stopped 策略）。
3. 測(cè)試系統(tǒng)重啟（最終驗(yàn)證）
bash
# 重啟整個(gè)系統(tǒng)
sudo reboot
# 系統(tǒng)重啟后，重新登錄，執(zhí)行：
docker ps | grep latex-ai-container
curl http://localhost:8080/health