@inproceedings{el-kurdi-etal-2022-zero,
title = "Zero-Shot Dynamic Quantization for Transformer Inference",
author = "El-kurdi, Yousef and
Quinn, Jerry and
Sil, Avi",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.45",
doi = "10.18653/v1/2022.emnlp-industry.45",
pages = "451--457",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-kurdi-etal-2022-zero">
<titleInfo>
<title>Zero-Shot Dynamic Quantization for Transformer Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yousef</namePart>
<namePart type="family">El-kurdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jerry</namePart>
<namePart type="family">Quinn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">el-kurdi-etal-2022-zero</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.45</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.45</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>451</start>
<end>457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-Shot Dynamic Quantization for Transformer Inference
%A El-kurdi, Yousef
%A Quinn, Jerry
%A Sil, Avi
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F el-kurdi-etal-2022-zero
%X 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.
%R 10.18653/v1/2022.emnlp-industry.45
%U https://aclanthology.org/2022.emnlp-industry.45
%U https://doi.org/10.18653/v1/2022.emnlp-industry.45
%P 451-457
Markdown (Informal)
[Zero-Shot Dynamic Quantization for Transformer Inference](https://aclanthology.org/2022.emnlp-industry.45) (El-kurdi et al., EMNLP 2022)
ACL
- Yousef El-kurdi, Jerry Quinn, and Avi Sil. 2022. Zero-Shot Dynamic Quantization for Transformer Inference. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 451–457, Abu Dhabi, UAE. Association for Computational Linguistics.