黃仁勳GB10(ACER)+VLLM 當機 詢AI解決方案 (GB10+VLLM crash Inquire about AI solutions)

資料來源:https://copilot.microsoft.com/shares/eCBp96Ba9eaMKQe7QMwzN

https://copilot.microsoft.com/shares/eCBp96Ba9eaMKQe7QMwzN
https://www.meta.ai/share/c/xU3dqnensu
https://grok.com/share/bGVnYWN5LWNvcHk_5559001d-970e-4617-964a-ecffa8e0a13e
https://share.gemini.google/h5X4PtETav3N
https://chatgpt.com/share/6aa236fb-d464-83ee-956c-23b558c0662d

GITHUB: https://github.com/jash-git/GB10-VLLM-crash-Inquire-about-AI-solutions

問題:

我在GB10硬體 配置檔如下 從2026/08/18 ~ 2026/09/09 VLLM服務都正常
但今早 服務停止 連線過去看 發現主記憶體吃到99% 置換記憶體也吃了17G(100%)

配置檔:

services:
  # ----------------------------------------------------------------
  # 1. Redis 服務：用於高速分散式流控 (Rate Limiting) 與快取
  # ----------------------------------------------------------------
  redis:
    image: redis:7-alpine
    container_name: litellm-redis
    restart: unless-stopped
    ports:
      - "6379:6379"
    volumes:
      - ./redis_data:/data

  # ----------------------------------------------------------------
  # 2. PostgreSQL 資料庫：儲存 LiteLLM 的金鑰、額度、用戶與消費日誌
  # ----------------------------------------------------------------
  db:
    image: postgres:16-alpine
    container_name: litellm-db
    restart: unless-stopped
    environment:
      POSTGRES_USER: litellm_user
      POSTGRES_PASSWORD: SecurePassword123! # 💡 生產環境建議修改此密碼
      POSTGRES_DB: litellm_db
    volumes:
      - ./postgres_data:/var/lib/postgresql/data
    ports:
      - "5432:5432"

  # ----------------------------------------------------------------
  # 3. vLLM 服務（已修正位置參數與 Tool Call Parser）
  # ----------------------------------------------------------------
  vllm-qwen:
    image: vllm/vllm-openai:latest-aarch64
    container_name: vllm-qwen
    restart: unless-stopped
    ipc: host
    ports:
      - "8000:8000"
    volumes:
      - /data/models/Qwen/Qwen3.6-35B-A3B-NVFP4:/model
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    environment:
      - FORCE_CUDA=1
      - PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
      - VLLM_TORCH_COMPILE_LEVEL=0
    # 🎯 修正處：直接把 /model 當作位置參數置於最前，並改用 qwen3_xml 解析器
    command: >
      /model
      --served-model-name Qwen3.6-35B-FP4
      --api-key "MySecretKey_123456"
      --gpu-memory-utilization 0.75
      --max-model-len 163840
      --quantization modelopt
      --kv-cache-dtype fp8
      --max-num-seqs 64
      --max-num-batched-tokens 8192
      --enable-auto-tool-choice
      --tool-call-parser qwen3_xml
      --reasoning-parser deepseek_r1
      --trust-remote-code
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 10s
      timeout: 5s
      retries: 60
      start_period: 90s

  # ----------------------------------------------------------------
  # 4. LiteLLM Proxy 閘道：嚴格等待 vLLM 載入完畢後才對外服務
  # ----------------------------------------------------------------
  litellm-proxy:
    image: ghcr.io/berriai/litellm:main-v1.60.0
    container_name: litellm-proxy
    restart: unless-stopped
    ports:
      - "4000:4000"
    volumes:
      - ./litellm-config.yaml:/app/config.yaml
    depends_on:
      db:
        condition: service_started
      redis:
        condition: service_started
      vllm-qwen:
        condition: service_healthy
    environment:
      - DATABASE_URL=postgresql://litellm_user:SecurePassword123!@db:5432/litellm_db
      - REDIS_URL=redis://litellm-redis:6379
      - LITELLM_MASTER_KEY=sk-master-key-1234567890
    command: [ "--config", "/app/config.yaml" ]
    
  # ----------------------------------------------------------------
  # 5. Open WebUI (已啟用帳號密碼登入與註冊)
  # ----------------------------------------------------------------
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    restart: unless-stopped
    ports:
      - "3000:8080"
    volumes:
      - ./webui_data:/app/backend/data
    depends_on:
      litellm-proxy:
        condition: service_started
      searxng:                 # 讓 WebUI 等待搜尋引擎啟動
        condition: service_started
    environment:
      - OPENAI_API_BASE_URL=http://litellm-proxy:4000/v1
      - OPENAI_API_KEY=sk-master-key-1234567890
      - ENABLE_OLLAMA_API=False
      
      # 🎯 【修改處：啟用登入驗證與註冊功能】
      - WEBUI_AUTH=True              # 開啟登入驗證
      - ENABLE_SIGNUP=True           # 開啟註冊功能（第一個註冊的帳號會自動變成管理員）
      
      - WEBUI_NAME=Local AI Workspace
      - ENABLE_RAG_WEB_SEARCH=True
      - RAG_WEB_SEARCH_ENGINE=searxng
      - RAG_WEB_SEARCH_RESULT_COUNT=3
      - SEARXNG_QUERY_URL=http://searxng:8080/search?q=<query>

  # ----------------------------------------------------------------
  # 6. SearXNG：在地端運作的隱私搜尋引擎
  # ----------------------------------------------------------------
  searxng:
    image: searxng/searxng:latest
    container_name: searxng
    restart: unless-stopped
    # 🎯 新增 volumes 掛載本地設定檔
    volumes:
      - ./searxng:/etc/searxng    
    environment:
      - SEARXNG_SETTINGS_URL=/etc/searxng/settings.yml