AMPS-Inf: Automatic Model Partitioning for Serverless Inference with Cost Efficiency-Reference-Cited by-同舟云学术

AMPS-Inf: Automatic Model Partitioning for Serverless Inference with Cost Efficiency

Published:2021-08-09 Issue: Volume: Page:
ISSN:
Container-title:50th International Conference on Parallel Processing
language:
Short-container-title:

Author:

Jarachanthan Jananie¹,Chen Li¹,Xu Fei²,Li Bo³

Affiliation:

1. University of Louisiana at Lafayette, United States of America

2. East China Normal University, China

3. Hong Kong University of Science and Technology, Hong Kong

Funder

Louisiana Board of Regents

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3472456.3472501

Reference52 articles.

1. [ 2 ] Keras. Retrieved January 5 2021 from https://keras.io/ [2] Keras. Retrieved January 5 2021 from https://keras.io/

2. [ 3 ] Pillow. Retrieved January 5 2021 from https://pillow.readthedocs.io/en/stable/ [3] Pillow. Retrieved January 5 2021 from https://pillow.readthedocs.io/en/stable/

3. [ 4 ] TensorFlow. Retrieved January 5 2021 from https://www.tensorflow.org/ [4] TensorFlow. Retrieved January 5 2021 from https://www.tensorflow.org/

4. [ 5 ] VGG16 Function. https://keras.io/api/applications/vgg/#vgg16-function [5] VGG16 Function. https://keras.io/api/applications/vgg/#vgg16-function

Cited by 22 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. On Efficient Zygote Container Planning and Task Scheduling for Edge Native Application Acceleration;IEEE INFOCOM 2024 - IEEE Conference on Computer Communications;2024-05-20

2. FSD-Inference: Fully Serverless Distributed Inference with Scalable Cloud Communication;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13

3. Serverless application composition leveraging function fusion: Theory and algorithms;Future Generation Computer Systems;2024-04

4. A survey on the scheduling mechanisms in serverless computing: a taxonomy, challenges, and trends;Cluster Computing;2024-02-18

5. StarShip: Mitigating I/O Bottlenecks in Serverless Computing for Scientific Workflows;Proceedings of the ACM on Measurement and Analysis of Computing Systems;2024-02-16