feat: 重构vLLM守护进程脚本，增强模型注册和服务管理功能，添加状态检查和配置命令

zhch/vllm_daemon.sh

@@ -1,76 +1,323 @@
 #!/bin/bash
+# filepath: /home/ubuntu/zhch/dots.ocr/zhch/vllm_daemon.sh
+
+# DotsOCR vLLM 服务守护进程脚本
 
 LOGDIR="/home/ubuntu/zhch/logs"
 mkdir -p $LOGDIR
 PIDFILE="$LOGDIR/vllm.pid"
 LOGFILE="$LOGDIR/vllm.log"
 
-conda activate dots.ocr
-hf_model_path="/home/ubuntu/zhch/dots.ocr/weights/DotsOCR"  # Path to your downloaded model weights
-export PYTHONPATH=$(dirname "$hf_model_path"):$PYTHONPATH
+# 配置参数
+CONDA_ENV="dots.ocr"
+PORT="8101"
+HOST="0.0.0.0"
+HF_MODEL_PATH="/home/ubuntu/zhch/dots.ocr/weights/DotsOCR"
+MODEL_NAME="DotsOCR"
+
+# GPU 配置
+GPU_MEMORY_UTILIZATION="0.70"
+DATA_PARALLEL_SIZE="1"  # 从3改为1，避免内存不足
+MAX_MODEL_LEN="32768"
+MAX_NUM_BATCHED_TOKENS="32768"
+MAX_NUM_SEQS="16"
+
+# 正确初始化和激活conda环境
+if [ -f "/home/ubuntu/anaconda3/etc/profile.d/conda.sh" ]; then
+    source /home/ubuntu/anaconda3/etc/profile.d/conda.sh
+    conda activate $CONDA_ENV
+elif [ -f "/opt/conda/etc/profile.d/conda.sh" ]; then
+    source /opt/conda/etc/profile.d/conda.sh
+    conda activate $CONDA_ENV
+else
+    # 方法2：直接使用conda可执行文件路径
+    echo "Warning: Using direct conda path activation"
+    export PATH="/home/ubuntu/anaconda3/envs/$CONDA_ENV/bin:$PATH"
+fi
 
-# launch vllm server
-model_name="DotsOCR"
+# 设置环境变量
+export PYTHONPATH=$(dirname "$HF_MODEL_PATH"):$PYTHONPATH
+export LD_LIBRARY_PATH="/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
+export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
+
+# 注册 DotsOCR 模型到 vLLM
+register_model() {
+    echo "🔧 注册 DotsOCR 模型到 vLLM..."
+    vllm_path=$(which vllm)
+    if [ -z "$vllm_path" ]; then
+        echo "❌ vLLM 未找到，请检查安装和环境激活"
+        return 1
+    fi
+    
+    if ! grep -q "from DotsOCR import modeling_dots_ocr_vllm" "$vllm_path"; then
+        sed -i '/^from vllm\.entrypoints\.cli\.main import main$/a\
+from DotsOCR import modeling_dots_ocr_vllm' "$vllm_path"
+        echo "✅ DotsOCR 模型已注册到 vLLM"
+    else
+        echo "✅ DotsOCR 模型已经注册过了"
+    fi
+}
 
 start() {
     if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
-        echo "vLLM is already running"
+        echo "vLLM DotsOCR is already running"
         return 1
     fi
     
-    echo "Starting vLLM daemon..."
-    nohup vllm serve $hf_model_path \
-		--host 0.0.0.0 \
-		--port 8101 \
-		--gpu-memory-utilization 0.70 \
-		--max-log-len 1000 \
-		--trust-remote-code \
-		--max-model-len 32768 \
-		--max-num-batched-tokens 32768 \
-		--uvicorn-log-level info \
-		--limit-mm-per-prompt '{"image": 1}' \
-		--chat-template-content-format string \
-		--data-parallel-size 3 \
-		--max-num-seqs 16 \
-		--enable-prefix-caching \
-		--served-model-name ${model_name} \
-		> $LOGFILE 2>&1 &
+    echo "Starting vLLM DotsOCR daemon..."
+    echo "Host: $HOST, Port: $PORT"
+    echo "Model path: $HF_MODEL_PATH"
+    echo "GPU memory utilization: $GPU_MEMORY_UTILIZATION"
+    echo "Data parallel size: $DATA_PARALLEL_SIZE"
+    
+    # 检查模型文件是否存在
+    if [ ! -d "$HF_MODEL_PATH" ]; then
+        echo "❌ Model path not found: $HF_MODEL_PATH"
+        return 1
+    fi
+    
+    # 检查conda环境
+    if ! command -v python >/dev/null 2>&1; then
+        echo "❌ Python not found. Check conda environment activation."
+        return 1
+    fi
+    
+    # 检查vllm命令
+    if ! command -v vllm >/dev/null 2>&1; then
+        echo "❌ vLLM not found. Check installation and environment."
+        return 1
+    fi
+    
+    echo "🔧 Using Python: $(which python)"
+    echo "🔧 Using vLLM: $(which vllm)"
+    
+    # 注册模型
+    register_model
+    if [ $? -ne 0 ]; then
+        echo "❌ Model registration failed"
+        return 1
+    fi
+    
+    # 显示GPU状态
+    echo "📊 GPU 状态检查:"
+    if command -v nvidia-smi >/dev/null 2>&1; then
+        nvidia-smi --query-gpu=index,name,memory.used,memory.total --format=csv,noheader,nounits | \
+        awk -F',' '{printf "  GPU %s: %s - 内存: %sMB/%sMB\n", $1, $2, $3, $4}'
+    else
+        echo "⚠️  nvidia-smi not available"
+    fi
+    
+    # 启动vLLM服务
+    nohup vllm serve $HF_MODEL_PATH \
+        --host $HOST \
+        --port $PORT \
+        --gpu-memory-utilization $GPU_MEMORY_UTILIZATION \
+        --max-log-len 1000 \
+        --trust-remote-code \
+        --max-model-len $MAX_MODEL_LEN \
+        --max-num-batched-tokens $MAX_NUM_BATCHED_TOKENS \
+        --uvicorn-log-level info \
+        --limit-mm-per-prompt '{"image": 1}' \
+        --chat-template-content-format string \
+        --data-parallel-size $DATA_PARALLEL_SIZE \
+        --max-num-seqs $MAX_NUM_SEQS \
+        --enable-prefix-caching \
+        --served-model-name $MODEL_NAME \
+        > $LOGFILE 2>&1 &
     
     echo $! > $PIDFILE
-    echo "vLLM started with PID: $(cat $PIDFILE)"
+    echo "✅ vLLM DotsOCR started with PID: $(cat $PIDFILE)"
+    echo "📋 Log file: $LOGFILE"
+    echo "🌐 Service URL: http://$HOST:$PORT"
+    echo "📖 API Documentation: http://localhost:$PORT/docs"
 }
 
 stop() {
     if [ ! -f $PIDFILE ]; then
-        echo "vLLM is not running"
+        echo "vLLM DotsOCR is not running"
         return 1
     fi
     
     PID=$(cat $PIDFILE)
-    echo "Stopping vLLM (PID: $PID)..."
+    echo "Stopping vLLM DotsOCR (PID: $PID)..."
+    
+    # 优雅停止
     kill $PID
+    
+    # 等待进程结束
+    for i in {1..10}; do
+        if ! kill -0 $PID 2>/dev/null; then
+            break
+        fi
+        echo "Waiting for process to stop... ($i/10)"
+        sleep 1
+    done
+    
+    # 如果进程仍在运行，强制结束
+    if kill -0 $PID 2>/dev/null; then
+        echo "Force killing process..."
+        kill -9 $PID
+    fi
+    
     rm -f $PIDFILE
-    echo "vLLM stopped"
+    echo "✅ vLLM DotsOCR stopped"
 }
 
 status() {
     if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
-        echo "vLLM is running (PID: $(cat $PIDFILE))"
+        PID=$(cat $PIDFILE)
+        echo "✅ vLLM DotsOCR is running (PID: $PID)"
+        echo "🌐 Service URL: http://$HOST:$PORT"
+        echo "📋 Log file: $LOGFILE"
+        
+        # 检查端口是否被监听
+        if command -v ss >/dev/null 2>&1; then
+            if ss -tuln | grep -q ":$PORT "; then
+                echo "🔗 Port $PORT is being listened"
+            else
+                echo "⚠️  Port $PORT is not being listened (service may be starting up)"
+            fi
+        elif command -v netstat >/dev/null 2>&1; then
+            if netstat -tuln | grep -q ":$PORT "; then
+                echo "🔗 Port $PORT is being listened"
+            else
+                echo "⚠️  Port $PORT is not being listened (service may be starting up)"
+            fi
+        fi
+        
+        # 检查API响应
+        if command -v curl >/dev/null 2>&1; then
+            if curl -s --connect-timeout 2 http://127.0.0.1:$PORT/v1/models > /dev/null 2>&1; then
+                echo "🎯 API 响应正常"
+            else
+                echo "⚠️  API 无响应 (service may be starting up)"
+            fi
+        fi
+        
+        # 显示GPU使用情况
+        if command -v nvidia-smi >/dev/null 2>&1; then
+            echo "📊 GPU 使用情况:"
+            nvidia-smi --query-gpu=index,utilization.gpu,utilization.memory,memory.used,memory.total --format=csv,noheader,nounits | \
+            awk -F',' '{printf "  GPU %s: GPU利用率 %s%%, 内存利用率 %s%%, 显存 %sMB/%sMB\n", $1, $2, $3, $4, $5}'
+        fi
+        
+        # 显示最新日志
+        if [ -f $LOGFILE ]; then
+            echo "📄 Latest logs (last 3 lines):"
+            tail -3 $LOGFILE | sed 's/^/  /'
+        fi
     else
-        echo "vLLM is not running"
+        echo "❌ vLLM DotsOCR is not running"
+        if [ -f $PIDFILE ]; then
+            echo "Removing stale PID file..."
+            rm -f $PIDFILE
+        fi
     fi
 }
 
-# 修复后的 launch_model_vllm.sh
-echo "🔧 注册 DotsOCR 模型到 vLLM..."
-vllm_path=$(which vllm)
-if ! grep -q "from DotsOCR import modeling_dots_ocr_vllm" "$vllm_path"; then
-    sed -i '/^from vllm\.entrypoints\.cli\.main import main$/a\
-from DotsOCR import modeling_dots_ocr_vllm' "$vllm_path"
-    echo "✅ DotsOCR 模型已注册到 vLLM"
-else
-    echo "✅ DotsOCR 模型已经注册过了"
-fi
+logs() {
+    if [ -f $LOGFILE ]; then
+        echo "📄 vLLM DotsOCR logs:"
+        echo "=================="
+        tail -f $LOGFILE
+    else
+        echo "❌ Log file not found: $LOGFILE"
+    fi
+}
+
+config() {
+    echo "📋 Current configuration:"
+    echo "  Conda Environment: $CONDA_ENV"
+    echo "  Host: $HOST"
+    echo "  Port: $PORT"
+    echo "  Model Path: $HF_MODEL_PATH"
+    echo "  Model Name: $MODEL_NAME"
+    echo "  GPU Memory Utilization: $GPU_MEMORY_UTILIZATION"
+    echo "  Data Parallel Size: $DATA_PARALLEL_SIZE"
+    echo "  Max Model Length: $MAX_MODEL_LEN"
+    echo "  Max Num Seqs: $MAX_NUM_SEQS"
+    echo "  PID File: $PIDFILE"
+    echo "  Log File: $LOGFILE"
+    
+    if [ -d "$HF_MODEL_PATH" ]; then
+        echo "✅ Model path exists"
+        echo "  Model files:"
+        ls -la "$HF_MODEL_PATH" | head -10 | sed 's/^/    /'
+        if [ $(ls -1 "$HF_MODEL_PATH" | wc -l) -gt 10 ]; then
+            echo "    ... and more files"
+        fi
+    else
+        echo "❌ Model path not found"
+    fi
+    
+    # 显示环境信息
+    echo ""
+    echo "🔧 Environment:"
+    echo "  Python: $(which python 2>/dev/null || echo 'Not found')"
+    echo "  vLLM: $(which vllm 2>/dev/null || echo 'Not found')"
+    echo "  Conda: $(which conda 2>/dev/null || echo 'Not found')"
+    echo "  CUDA: $(which nvcc 2>/dev/null || echo 'Not found')"
+    
+    # 显示GPU信息
+    if command -v nvidia-smi >/dev/null 2>&1; then
+        echo ""
+        echo "🔥 GPU Information:"
+        nvidia-smi --query-gpu=index,name,driver_version,memory.total --format=csv,noheader,nounits | \
+        awk -F',' '{printf "  GPU %s: %s (Driver: %s, Memory: %sMB)\n", $1, $2, $3, $4}'
+    fi
+}
+
+test_api() {
+    echo "🧪 Testing vLLM DotsOCR API..."
+    
+    if [ ! -f $PIDFILE ] || ! kill -0 $(cat $PIDFILE) 2>/dev/null; then
+        echo "❌ vLLM service is not running"
+        return 1
+    fi
+    
+    if ! command -v curl >/dev/null 2>&1; then
+        echo "❌ curl command not found"
+        return 1
+    fi
+    
+    echo "📡 Testing /v1/models endpoint..."
+    response=$(curl -s --connect-timeout 5 http://127.0.0.1:$PORT/v1/models)
+    if [ $? -eq 0 ]; then
+        echo "✅ Models endpoint accessible"
+        echo "$response" | python -m json.tool 2>/dev/null || echo "$response"
+    else
+        echo "❌ Models endpoint not accessible"
+    fi
+}
+
+# 显示使用帮助
+usage() {
+    echo "vLLM DotsOCR Service Daemon"
+    echo "============================"
+    echo "Usage: $0 {start|stop|restart|status|logs|config|test}"
+    echo ""
+    echo "Commands:"
+    echo "  start   - Start the vLLM DotsOCR service"
+    echo "  stop    - Stop the vLLM DotsOCR service"
+    echo "  restart - Restart the vLLM DotsOCR service"
+    echo "  status  - Show service status and resource usage"
+    echo "  logs    - Show service logs (follow mode)"
+    echo "  config  - Show current configuration"
+    echo "  test    - Test API endpoints"
+    echo ""
+    echo "Configuration (edit script to modify):"
+    echo "  Host: $HOST"
+    echo "  Port: $PORT"
+    echo "  Model: $HF_MODEL_PATH"
+    echo "  GPU Memory: $GPU_MEMORY_UTILIZATION"
+    echo "  Parallel Size: $DATA_PARALLEL_SIZE"
+    echo ""
+    echo "Examples:"
+    echo "  ./vllm_daemon.sh start"
+    echo "  ./vllm_daemon.sh status"
+    echo "  ./vllm_daemon.sh logs"
+    echo "  ./vllm_daemon.sh test"
+}
 
 case "$1" in
     start)
@@ -81,14 +328,23 @@ case "$1" in
         ;;
     restart)
         stop
-        sleep 2
+        sleep 3
         start
         ;;
     status)
         status
         ;;
+    logs)
+        logs
+        ;;
+    config)
+        config
+        ;;
+    test)
+        test_api
+        ;;
     *)
-        echo "Usage: $0 {start|stop|restart|status}"
+        usage
         exit 1
         ;;
 esac