Preprint · 2020 · Open access

MNN: A Universal and Efficient Inference Engine

Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Zou, Bin, Yafeng Yang, Zongyang Cui, Cai, Yu, Tianhang Yu, Chengfei Lv, Zhihua Wu

arXiv (Cornell University) · Published 27 February 2020 · DOI 10.48550/arxiv.2002.12418

Open PDFView at the publisherCite this paper

In brief

“MNN: A Universal and Efficient Inference Engine” is a 2020 preprint by Xiaotang Jiang and 11 co-authors, published in arXiv (Cornell University). OpenAlex counts 194 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
194
Most cited in
2022 (36)
References
24
Authors
12

Abstract

Deploying deep learning models on mobile devices draws more and more attention recently. However, designing an efficient inference engine on devices is under the great challenges of model compatibility, device diversity, and resource limitation. To deal with these challenges, we propose Mobile Neural Network (MNN), a universal and efficient inference engine tailored to mobile applications. In this paper, the contributions of MNN include: (1) presenting a mechanism called pre-inference that manages to conduct runtime optimization; (2)deliveringthorough kernel optimization on operators to achieve optimal computation performance; (3) introducing backend abstraction module which enables hybrid scheduling and keeps the engine lightweight. Extensive benchmark experiments demonstrate that MNN performs favorably against other popular lightweight deep learning frameworks. MNN is available to public at: https://github.com/alibaba/MNN.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Jiang, X., Wang, H., Chen, Y., Wu, Z., Wang, L., Bin, Z., Yang, Y., Cui, Z., Yu, C., Yu, T., Lv, C., & Wu, Z. (2020). MNN: A Universal and Efficient Inference Engine. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2002.12418

MLA 9

Jiang, Xiaotang, et al. “MNN: A Universal and Efficient Inference Engine.” arXiv (Cornell University), 2020. https://doi.org/10.48550/arxiv.2002.12418.

Chicago

Jiang, Xiaotang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Zou, Bin, Yafeng Yang, et al. 2020. “MNN: A Universal and Efficient Inference Engine.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2002.12418.

Harvard

Jiang, X. et al. (2020) ‘MNN: A Universal and Efficient Inference Engine’, arXiv (Cornell University). doi:10.48550/arxiv.2002.12418.

IEEE

X. Jiang et al., “MNN: A Universal and Efficient Inference Engine,” arXiv (Cornell University), 2020, doi: 10.48550/arxiv.2002.12418.

BibTeX

@misc{jiang2020universal,
  title     = {{MNN: A Universal and Efficient Inference Engine}},
  author    = {Jiang, Xiaotang and Wang, Huan and Chen, Yiliu and Wu, Ziqi and Wang, Lichuan and Bin, Zou, and Yang, Yafeng and Cui, Zongyang and Yu, Cai, and Yu, Tianhang and Lv, Chengfei and Wu, Zhihua},
  howpublished = {arXiv (Cornell University)},
  year      = {2020},
  doi       = {10.48550/arxiv.2002.12418},
  url       = {https://doi.org/10.48550/arxiv.2002.12418}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202066
20212727
20223636
20233636
20243434
20253232
20262323

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • inference engine
  • mobile deep learning
  • runtime optimization
  • hybrid scheduling
  • model compatibility
  • device diversity

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Jiang, X., Wang, H., Chen, Y., Wu, Z., Wang, L., Bin, Z., Yang, Y., Cui, Z., Yu, C., Yu, T., Lv, C., & Wu, Z. (2020). MNN: A Universal and Efficient Inference Engine. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2002.12418

How many times has this paper been cited?

194 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Zou, Bin, Yafeng Yang, Zongyang Cui, Cai, Yu, Tianhang Yu, Chengfei Lv, Zhihua Wu.

What is the DOI of this paper?

10.48550/arxiv.2002.12418, permanently at https://doi.org/10.48550/arxiv.2002.12418. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.