@inproceedings{tu-etal-2018-pay,
title = "Pay-Per-Request Deployment of Neural Network Models Using Serverless Architectures",
author = "Tu, Zhucheng and
Li, Mengping and
Lin, Jimmy",
editor = "Liu, Yang and
Paek, Tim and
Patwardhan, Manasi",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Demonstrations",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-5002",
doi = "10.18653/v1/N18-5002",
pages = "6--10",
abstract = "We demonstrate the serverless deployment of neural networks for model inferencing in NLP applications using Amazon{'}s Lambda service for feedforward evaluation and DynamoDB for storing word embeddings. Our architecture realizes a pay-per-request pricing model, requiring zero ongoing costs for maintaining server instances. All virtual machine management is handled behind the scenes by the cloud provider without any direct developer intervention. We describe a number of techniques that allow efficient use of serverless resources, and evaluations confirm that our design is both scalable and inexpensive.",
}
Markdown (Informal)
[Pay-Per-Request Deployment of Neural Network Models Using Serverless Architectures](https://aclanthology.org/N18-5002) (Tu et al., NAACL 2018)
ACL