ML Anthology

Inference Analysis of Optical Transformers

Xianxin Guo, Chenchen Wang, Djamshid Damry
NeurIPSW 2023
/neuripsw/2023/guo2023neuripsw-inference/

Abstract

This paper explores the utilization of optical computing for accelerating inference in transformer models, which have demonstrated substantial success in various applications. Optical computing offers ultra-fast computation and ultra-high energy efficiency compared to conventional electronics. Our findings suggest that optical implementation has the potential to achieve a significant 10-100 times improvement in the inference throughput of compute-limited transformer models.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Guo et al. "Inference Analysis of Optical Transformers." NeurIPS 2023 Workshops: MLNCP, 2023.

Markdown

[Guo et al. "Inference Analysis of Optical Transformers." NeurIPS 2023 Workshops: MLNCP, 2023.](https://mlanthology.org/neuripsw/2023/guo2023neuripsw-inference/)

BibTeX

@inproceedings{guo2023neuripsw-inference,
  title     = {{Inference Analysis of Optical Transformers}},
  author    = {Guo, Xianxin and Wang, Chenchen and Damry, Djamshid},
  booktitle = {NeurIPS 2023 Workshops: MLNCP},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/guo2023neuripsw-inference/}
}