TurboTransformers: an efficient GPU serving system for transformer models
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
The transformer is the most critical algorithm innovation of the Nature Language Processing (NLP) field in recent years. Unlike the Recurrent Neural Network (RNN) models, transformers are able to process on dimensions of sequence lengths in parallel, therefore leads to better accuracy on long sequences. However, efficient deployments of them for online services in data centers equipped with GPUs are not easy. First, more computation introduced by transformer structures makes it more challenging to meet the latency and throughput constraints of serving. Second, NLP tasks take in sentences of variable length. The variability of input dimensions brings a severe problem to efficient memory management and serving optimization.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) · arXiv · doi:10.48550/arxiv.1909.11942 · Cited by 4,308 · cited 2×
“The runtime is evaluated on three transformer networks, including Bert [7], Albert [14] and a Seq2Seq Decoder [28], the parameters of which are shown in Table 3.”
MethodTVM: an automated end-to-end optimizing compiler for deep learning
(2018) · arXiv (Cornell University) · doi:10.5555/3291168.3291211 · Cited by 1,170
(2018) · doi:10.1109/ipdpsw.2018.00091 · Cited by 399
Low latency RNN inference with cellular batching
Gao, P., Yu, L., Wu, Y., & Li, J. (2018) · Proceedings of the Thirteenth EuroSys Conference · doi:10.1145/3190508.3190541 · Cited by 66
Cited by
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J. E., Zhang, H., & Stoica, I. (2023) · arXiv · doi:10.48550/arxiv.2309.06180 · Cited by 1,802
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J., Zhang, H., & Stoica, I. (2023) · Proceedings of the 29th Symposium on Operating Systems Principles · doi:10.1145/3600006.3613165 · Cited by 1,817
“These systems utilize GPU kernel optimizations [1, 29, 31, 56], advanced batching mechanisms [14, 60], model parallelism [1, 41, 60], and parameter sharing [64] for efficient serving.”
MethodDeepSpeed- Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale
Aminabadi, R. Y., Rajbhandari, S., Awan, A. A., Li, C., Li, D., Zheng, E., Ruwase, O., Smith, S., Zhang, M., Rasley, J., et al. (2022) · SC22: International Conference for High Performance Computing, Networking, Storage and Analysis · doi:10.1109/sc41404.2022.00051 · Cited by 297
“TurboTransformers [26] similarly fuses elementwise and reduction operators for transformer inference.”
BackgroundMethodLightSeq: A High Performance Inference Library for Transformers
Wang, X., Xiong, Y., Wei, Y., Wang, M., & Li, L. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers · doi:10.18653/v1/2021.naacl-industry.15 · Cited by 36
SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models
Chen, F., Li, P., Luan, T. H., Su, Z., & Deng, J. (2025) · IEEE INFOCOM 2025 - IEEE Conference on Computer Communications · doi:10.1109/infocom55648.2025.11044522 · Cited by 11
Metadata
- Authors
- Fang, J., Yu, Y., Zhao, C., & Zhou, J.
- Venue
- Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
- Publisher
- ACM
- Published
- 2021-02-17
- Pages
- 389-402
- OpenAlex
- W3130716829
- Cited by
- 116
- References
- 10
- FWCI
- 14.19
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: TurboTransformers: an efficient GPU serving system for transformer models. https://app.cochat.ai/papers/10.1145/3437801.3441578
- The paper
- Fang, J., Yu, Y., Zhao, C., & Zhou, J. (2021). TurboTransformers: an efficient GPU serving system for transformer models. Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. https://doi.org/10.1145/3437801.3441578
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.