#!/bin/bash # Start Qwen3-VL server MODEL_PATH="/Users/accusys/models/Qwen3VL-8B-Instruct-Q8_0.gguf" MMPROJ_PATH="/Users/accusys/models/mmproj-Qwen3VL-8B-Instruct-F16.gguf" LOG_FILE="/Users/accusys/momentry_core/logs/qwen3vl_8086.log" PID_FILE="/tmp/qwen3vl.pid" # Kill existing process if running if [ -f "$PID_FILE" ]; then OLD_PID=$(cat "$PID_FILE") if ps -p "$OLD_PID" > /dev/null 2>&1; then kill "$OLD_PID" sleep 2 fi rm "$PID_FILE" fi # Start server nohup /opt/homebrew/bin/llama-server \ --model "$MODEL_PATH" \ --mmproj "$MMPROJ_PATH" \ --host 127.0.0.1 \ --port 8086 \ --ctx-size 8192 \ --n-gpu-layers 99 \ --threads 8 \ --batch-size 512 \ --media-path /Users/accusys/momentry/output_dev \ > "$LOG_FILE" 2>&1 & echo $! > "$PID_FILE" echo "Qwen3-VL started with PID $(cat $PID_FILE)" echo "Log file: $LOG_FILE" echo "Health check: http://localhost:8086/health"