Towards Greener Yet Powerful Code Generation via Quantization: An Empirical Study
Abstract
ML-powered code generation aims to assist developers to write code in a more productive manner by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have pushed the boundary of code generation and achieved impressive performance. However, the huge number of model parameters poses a significant challenge to their adoption in a typical software development environment, where a developer might use a standard laptop or mid-size server to develop code. Such large models cost significant resources in terms of memory, latency, dollars, as well as carbon footprint.
BibTeX
@inproceedings{Wei-al:FSE23,
author = {Xiaokai Wei and
Sujan Kumar Gonugondla and
Shiqi Wang and
Wasi Uddin Ahmad and
Baishakhi Ray and
Haifeng Qian and
Xiaopeng Li and
Varun Kumar and
Zijian Wang and
Yuchen Tian and
Qing Sun and
Ben Athiwaratkun and
Mingyue Shang and
Murali Krishna Ramanathan and
Parminder Bhatia and
Bing Xiang},
title = {Towards Greener Yet Powerful Code Generation via Quantization: An Empirical Study},
booktitle = {{ESEC/SIGSOFT} {FSE}},
pages = {224--236},
publisher = {{ACM}},
year = {2023},
}