arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.09541cs.LGcs.PF
收藏

将TensorFlow扩展到每秒3亿次预测

Scaling TensorFlow to 300 million predictions per second

Zemanta, an Outbrain company(Zemanta,一家Outbrain公司)

Jan Hartman, Davorin Kopič

摘要:

我们介绍了在在线广告生态系统中将机器学习模型大规模过渡到TensorFlow框架的过程。在这次演讲中,我们将讨论我们面临的关键挑战,并描述我们如何成功地解决这些挑战;特别是,在TF中实现模型,并使用各种优化技术以低延迟有效地为它们提供服务。

英文摘要:

We present the process of transitioning machine learning models to the TensorFlow framework at a large scale in an online advertising ecosystem. In this talk we address the key challenges we faced and describe how we successfully tackled them; notably, implementing the models in TF and serving them efficiently with low latency using various optimization techniques.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑