Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents Transformer models from being used in production. To address this gap, model compression techniques such as quantization and pruning may be used to improve inference efficiency. However, these compression techniques require specialized software to apply and deploy at scale. In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators. We demonstrate the efficiency of our pipeline by creating a Fast DistilBERT model showing minimal accuracy loss on the question-answering SQuADv1.1 benchmark, and throughput results under typical production constraints and environments. Our results outperform existing state-of-the-art Neural Magic's DeepSparse runtime performance by up to 50% and up to 4.1x performance speedup over ONNX Runtime.

本文介绍了一种新的在CPU上创建和运行快速Transformer模型的流水线，利用硬件感知剪枝、知识蒸馏和量化等模型压缩技术，通过优化稀疏和量化操作库的运行时引擎来提高推理效率，创造了一个Fast DistilBERT模型，其通过问题回答SQuADv1.1基准测试表现良好，性能比现有的Neural Magic's DeepSparse运行时性能提高了高达50%，比ONNX计算时性能提升了最多4.1倍。

CPU 上的快速 DistilBERT