feat(zhch): 添加 vLLM 守护进程脚本，支持启动、停止和状态检查功能

zhch/vllm_daemon.sh

@@ -0,0 +1,82 @@
+#!/bin/bash
+
+LOGDIR="/home/ubuntu/zhch/logs"
+mkdir -p $LOGDIR
+PIDFILE="$LOGDIR/vllm.pid"
+LOGFILE="$LOGDIR/vllm.log"
+
+conda activate py312
+hf_model_path="/home/ubuntu/zhch/dots.ocr/weights/DotsOCR"  # Path to your downloaded model weights
+export PYTHONPATH=$(dirname "$hf_model_path"):$PYTHONPATH
+# launch vllm server
+model_name="DotsOCR"
+
+start() {
+    if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
+        echo "vLLM 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 0.90 \
+		--max-log-len 1000 \
+		--trust-remote-code \
+		--max-model-len 65536 \
+		--max-num-batched-tokens 65536 \
+		--uvicorn-log-level info \
+		--limit-mm-per-prompt '{"image": 5}' \
+		--chat-template-content-format string \
+		--data-parallel-size 2 \
+		--max-num-seqs 32 \
+		--enable-prefix-caching \
+		--served-model-name ${model_name} \
+		> $LOGFILE 2>&1 &
+    
+    echo $! > $PIDFILE
+    echo "vLLM started with PID: $(cat $PIDFILE)"
+}
+
+stop() {
+    if [ ! -f $PIDFILE ]; then
+        echo "vLLM is not running"
+        return 1
+    fi
+    
+    PID=$(cat $PIDFILE)
+    echo "Stopping vLLM (PID: $PID)..."
+    kill $PID
+    rm -f $PIDFILE
+    echo "vLLM stopped"
+}
+
+status() {
+    if [ -f $PIDFILE ] && kill -0 $(cat $PIDFILE) 2>/dev/null; then
+        echo "vLLM is running (PID: $(cat $PIDFILE))"
+    else
+        echo "vLLM is not running"
+    fi
+}
+
+case "$1" in
+    start)
+        start
+        ;;
+    stop)
+        stop
+        ;;
+    restart)
+        stop
+        sleep 2
+        start
+        ;;
+    status)
+        status
+        ;;
+    *)
+        echo "Usage: $0 {start|stop|restart|status}"
+        exit 1
+        ;;
+esac