如何确定Deep Java Library (DJL)中的可用GPU内存？

import ai.djl.Device;
import ai.djl.Model;
import ai.djl.ModelException;
import ai.djl.inference.Predictor;
import ai.djl.inference.PredictionException;
import ai.djl.inference.PredictorBuilder;
import ai.djl.modality.Classifications;
import ai.djl.modality.cv.Image;
import ai.djl.modality.cv.ImageFactory;
import ai.djl.modality.cv.ImageTransform;
import ai.djl.modality.cv.ImageVisualization;
import ai.djl.modality.cv.transform.Resize;
import ai.djl.modality.cv.transform.ToTensor;
import ai.djl.translate.TranslateException;
import ai.djl.translate.TranslateMethod;
import ai.djl.translate.TranslatePipeline;
import ai.djl.translate.Translator;
import ai.djl.util.Utils;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.List;

public class GpuMemoryExample {

    public static void main(String[] args) throws IOException, ModelException, TranslateException, PredictionException {
        // 初始化DJL
        Device device = Device.gpu(); // 使用GPU设备
        Model model = Model.newInstance("path_to_your_model", device); // 加载模型
        ImageFactory imageFactory = ImageFactory.getInstance(); // 获取图像工厂

        // 创建一个GPU管理器
        GpuMemoryManager gpuMemoryManager = GpuMemoryManager.getInstance();
        gpuMemoryManager.setDevice(device);

        // 获取可用的GPU内存
        long availableGpuMemory = gpuMemoryManager.getAvailableMemory();

        System.out.println("可用的GPU内存：" + availableGpuMemory + " bytes");

        // 其他DJL操作...
    }
}