---
_id: '63060'
author:
- first_name: Jing
  full_name: Wu, Jing
  last_name: Wu
- first_name: Lin
  full_name: Wang, Lin
  id: '102868'
  last_name: Wang
  orcid: 0000-0001-7181-6128
- first_name: Qirui
  full_name: Jin, Qirui
  last_name: Jin
- first_name: Fangming
  full_name: Liu, Fangming
  last_name: Liu
citation:
  ama: 'Wu J, Wang L, Jin Q, Liu F. Graft: Efficient Inference Serving for Hybrid
    Deep Learning With SLO Guarantees via DNN Re-Alignment. <i>IEEE Transactions on
    Parallel and Distributed Systems</i>. 2023;35(2):280-296. doi:<a href="https://doi.org/10.1109/tpds.2023.3340518">10.1109/tpds.2023.3340518</a>'
  apa: 'Wu, J., Wang, L., Jin, Q., &#38; Liu, F. (2023). Graft: Efficient Inference
    Serving for Hybrid Deep Learning With SLO Guarantees via DNN Re-Alignment. <i>IEEE
    Transactions on Parallel and Distributed Systems</i>, <i>35</i>(2), 280–296. <a
    href="https://doi.org/10.1109/tpds.2023.3340518">https://doi.org/10.1109/tpds.2023.3340518</a>'
  bibtex: '@article{Wu_Wang_Jin_Liu_2023, title={Graft: Efficient Inference Serving
    for Hybrid Deep Learning With SLO Guarantees via DNN Re-Alignment}, volume={35},
    DOI={<a href="https://doi.org/10.1109/tpds.2023.3340518">10.1109/tpds.2023.3340518</a>},
    number={2}, journal={IEEE Transactions on Parallel and Distributed Systems}, publisher={Institute
    of Electrical and Electronics Engineers (IEEE)}, author={Wu, Jing and Wang, Lin
    and Jin, Qirui and Liu, Fangming}, year={2023}, pages={280–296} }'
  chicago: 'Wu, Jing, Lin Wang, Qirui Jin, and Fangming Liu. “Graft: Efficient Inference
    Serving for Hybrid Deep Learning With SLO Guarantees via DNN Re-Alignment.” <i>IEEE
    Transactions on Parallel and Distributed Systems</i> 35, no. 2 (2023): 280–96.
    <a href="https://doi.org/10.1109/tpds.2023.3340518">https://doi.org/10.1109/tpds.2023.3340518</a>.'
  ieee: 'J. Wu, L. Wang, Q. Jin, and F. Liu, “Graft: Efficient Inference Serving for
    Hybrid Deep Learning With SLO Guarantees via DNN Re-Alignment,” <i>IEEE Transactions
    on Parallel and Distributed Systems</i>, vol. 35, no. 2, pp. 280–296, 2023, doi:
    <a href="https://doi.org/10.1109/tpds.2023.3340518">10.1109/tpds.2023.3340518</a>.'
  mla: 'Wu, Jing, et al. “Graft: Efficient Inference Serving for Hybrid Deep Learning
    With SLO Guarantees via DNN Re-Alignment.” <i>IEEE Transactions on Parallel and
    Distributed Systems</i>, vol. 35, no. 2, Institute of Electrical and Electronics
    Engineers (IEEE), 2023, pp. 280–96, doi:<a href="https://doi.org/10.1109/tpds.2023.3340518">10.1109/tpds.2023.3340518</a>.'
  short: J. Wu, L. Wang, Q. Jin, F. Liu, IEEE Transactions on Parallel and Distributed
    Systems 35 (2023) 280–296.
date_created: 2025-12-12T08:17:09Z
date_updated: 2025-12-12T08:17:56Z
department:
- _id: '34'
- _id: '7'
- _id: '75'
doi: 10.1109/tpds.2023.3340518
intvolume: '        35'
issue: '2'
language:
- iso: eng
page: 280-296
publication: IEEE Transactions on Parallel and Distributed Systems
publication_identifier:
  issn:
  - 1045-9219
  - 1558-2183
  - 2161-9883
publication_status: published
publisher: Institute of Electrical and Electronics Engineers (IEEE)
status: public
title: 'Graft: Efficient Inference Serving for Hybrid Deep Learning With SLO Guarantees
  via DNN Re-Alignment'
type: journal_article
user_id: '102868'
volume: 35
year: '2023'
...