arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1906.00532cs.LG
收藏

Transformer神经机器语言翻译模型的高效8位Quantization

Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model

Intel Corporation(英特尔公司)

Aishwarya Bhandare, Vamsi Sripathi, Deepthi Karkada, Vivek Menon, Sun Choi, Kushal Datta, Vikram Saletore

摘要:

在这项工作中,我们在最新的英特尔$^\circledR$ Xeon $^\circledR$ Cascade Lake处理器中利用INT 8/VNNI指令构建了一个经过训练的Transformer机器语言翻译模型,以提高推理性能,同时保持准确性下降小于0.5 $\%$。据我们所知,这是业界首次尝试对Transformer模型进行加密。这具有很高的影响力,因为它清楚地表明了量化语言翻译模型的各种复杂性。我们直接在TensorFlow中提出了新的量化技术,以利用8位整数(INT 8)取代32位浮点(FP 32)计算,并转换FP 32计算图。我们还提出了一个装箱并行处理技术,以最大限度地提高CPU利用率。总体而言,我们对INT 8/VNNI的优化比最佳FP 32性能提高了1.5倍。此外,它还揭示了提升量化深度学习推理性能的机遇和挑战,并建立了在英特尔CPU上高效运行推理的最佳实践。

英文摘要:

In this work, we quantize a trained Transformer machine language translation model leveraging INT8/VNNI instructions in the latest Intel$^\circledR$ Xeon$^\circledR$ Cascade Lake processors to improve inference performance while maintaining less than 0.5$\%$ drop in accuracy. To the best of our knowledge, this is the first attempt in the industry to quantize the Transformer model. This has high impact as it clearly demonstrates the various complexities of quantizing the language translation model. We present novel quantization techniques directly in TensorFlow to opportunistically replace 32-bit floating point (FP32) computations with 8-bit integers (INT8) and transform the FP32 computational graph. We also present a bin-packing parallel batching technique to maximize CPU utilization. Overall, our optimizations with INT8/VNNI deliver 1.5X improvement over the best FP32 performance. Furthermore, it reveals the opportunities and challenges to boost performance of quantized deep learning inference and establishes best practices to run inference with high efficiency on Intel CPUs.

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。

↑