Publication
EMNLP 2022
Short paper

Zero-Shot Dynamic Quantization for Transformer Inference

Abstract

We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers. Existing methods for quantizing models either modify the training procedure, or they require an additional calibration step to adjust parameters that also requires a selected held-out dataset. Our method permits taking advantage of quantization without the need for these adjustments. We present results on several NLP tasks demonstrating the usefulness of this technique.

Date

Publication

EMNLP 2022