start.sh

#!/bin/bash
set -e

MODEL_PATH="/home/user/app/models/bitnet-b1.58-2B-4T-gguf/ggml-model-i2_s.gguf"
SERVER_BIN="/home/user/app/bin/llama-server"

# Start llama-server in background
echo "Starting bitnet.cpp llama-server..."
$SERVER_BIN \
    -m "$MODEL_PATH" \
    --host 127.0.0.1 \
    --port 8080 \
    -t 2 \
    -c 4096 \
    --log-disable &

SERVER_PID=$!

# Wait for server to be ready
echo "Waiting for server to start..."
for i in $(seq 1 60); do
    if curl -s http://127.0.0.1:8080/health > /dev/null 2>&1; then
        echo "Server ready!"
        break
    fi
    sleep 1
done

# Start Gradio app
echo "Starting Gradio app..."
exec python app.py