Low latency RNN inference with cellular batching
The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
Performing inference on pre-trained neural network models must meet the requirement of low-latency, which is often at odds with achieving high throughput. Existing deep learning systems use batching to improve throughput, which do not perform well when serving Recurrent Neural Networks with dynamic dataflow graphs. We propose the technique of cellular batching, which improves both the latency and throughput of RNN inference. Unlike existing systems that batch a fixed set of dataflow graphs, cellular batching makes batching decisions at the granularity of an RNN "cell" (a subgraph with shared weights) and dynamically assembles a batched cell for execution as requests join and leave the system. We implemented our approach in a system called BatchMaker. Experiments show that BatchMaker achieves much lower latency and also higher throughput than existing systems.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Moreover, with special GPU kernels, these techniques eliminate the need to pad the inputs and outputs.”
From Efficient Memory Management for Large Language Model Serving with PagedAttention (2023) · cites this paper as [16]
In the citing paper
“By reducing the queueing delay and the inefficiencies from padding, the fine-grained batching mechanisms significantly increase the throughput of LLM serving.”
From Efficient Memory Management for Large Language Model Serving with PagedAttention (2023) · cites this paper as [16]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Thumbs up?: sentiment classification using machine learning techniques
Pang, B., Lee, L., & Vaithyanathan, S. (2002) · Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02 · doi:10.3115/1118693.1118704 · Cited by 7,024
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319
Self-citationLong-term recurrent convolutional networks for visual recognition and description
Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298878 · Cited by 5,228
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
Tai, K. S., Socher, R., & Manning, C. D. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1150 · Cited by 3,081
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Amodei, D., Anubhai, R., Battenberg, E., Case, C. T., Casper, J., Catanzaro, B., Chen, J., Chrzanowski, M., Coates, A., Diamos, G., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.02595 · Cited by 2,110
MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M., Xiao, T., Xu, B., Zhang, C., & Zhang, Z. (2015) · arXiv · doi:10.48550/arxiv.1512.01274 · Cited by 1,819
Proceedings of the 29th International Conference on Machine Learning (ICML-12)
Langford, J. C., & Pineau, J. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1207.4676 · Cited by 1,618
Torch7: A Matlab-like Environment for Machine Learning
Collobert, R., Kavukcuoglu, K., & Farabet, C. (2011) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 1,588
(2011) · Cited by 1,192
Theano: A CPU and GPU Math Compiler in Python
Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., & Bengio, Y. (2010) · Proceedings of the Python in Science Conference · doi:10.25080/majora-92bf1922-003 · Cited by 1,052
MLlib: Machine Learning in Apache Spark
Meng, X., Bradley, J. K., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., Freeman, J., Tsai, D., Amde, M., Owen, S., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.06807 · Cited by 940
SEDA: an architecture for well-conditioned, scalable internet services
Welsh, M., Culler, D., & Brewer, E. (2001) · Proceedings of the eighteenth ACM symposium on Operating systems principles · doi:10.1145/502034.502057 · Cited by 834
Clipper: A Low-Latency Online Prediction Serving System
Crankshaw, D., Wang, X., Zhou, G., Franklin, M. J., Gonzalez, J. E., & Stoica, I. (2016) · arXiv · doi:10.48550/arxiv.1612.03079 · Cited by 415
Marelli, M., Bentivogli, L., Baroni, M., Bernardi, R., Menini, S., & Zamparelli, R. (2014) · Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) · doi:10.3115/v1/s14-2001 · Cited by 378
Neural Generative Question Answering
Yin, J., Jiang, X., Lu, Z., Shang, L., Li, H., & Li, X. (2016) · Proceedings of the Workshop on Human-Computer Question Answering · doi:10.18653/v1/w16-0106 · Cited by 186
QPipe: a simultaneously pipelined relational query engine
Harizopoulos, S., Shkapenyuk, V., & Ailamaki, A. (2005) · Proceedings of the 2005 ACM SIGMOD international conference on Management of data · doi:10.1145/1066157.1066201 · Cited by 174
TensorFlow-Serving: Flexible, High-Performance ML Serving
Olston, C., Fiedel, N., Gorovoy, K., Harmsen, J., Lao, L., Li, F., Rajashekhar, V., Ramesh, S., & Soyke, J. (2017) · arXiv · doi:10.48550/arxiv.1712.06139 · Cited by 171
SEDA: an architecture for well-conditioned, scalable internet services
Welsh, M., Culler, D., & Brewer, E. (2001) · ACM SIGOPS Operating Systems Review · doi:10.1145/502059.502057 · Cited by 158
Predictable performance for unpredictable workloads
Unterbrunner, P., Giannikis, G. K., Alonso, G., Fauser, D., & Kossmann, D. (2009) · Proceedings of the VLDB Endowment · doi:10.14778/1687627.1687707 · Cited by 126
Giannikis, G., Alonso, G., & Kossmann, D. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2168651.2168654 · Cited by 119
Persistent RNNs: stashing recurrent weights on-chip
Diamos, G., Sengupta, S., Catanzaro, B., Chrzanowski, M., Coates, A., Elsen, E., Engel, J., Hannun, A., & Satheesh, S. (2016) · International Conference on Machine Learning · Cited by 100
A scalable, predictable join operator for highly concurrent data warehouses
Candea, G., Polyzotis, N., & Vingralek, R. (2009) · Proceedings of the VLDB Endowment · doi:10.14778/1687627.1687659 · Cited by 87
Main-memory scan sharing for multi-core CPUs
Qiao, L., Raman, V., Reiss, F. R., Haas, P. J., & Lohman, G. M. (2008) · Proceedings of the VLDB Endowment · doi:10.14778/1453856.1453924 · Cited by 85
Deep Learning with Dynamic Computation Graphs
Looks, M., Herreshoff, M., Hutchins, D. S., & Norvig, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.02181 · Cited by 82
Crankshaw, D., Bailis, P. D., Gonzalez, J. E., Li, H., Zhang, Z., Franklin, M. J. M., Ghodsi, A., & Jordan, M. I. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.3809 · Cited by 79
LASER: a scalable response prediction platform for online advertising
Agarwal, D., Long, B., Traupman, J., Xin, D., & Zhang, L. (2014) · Proceedings of the 7th ACM international conference on Web search and data mining · doi:10.1145/2556195.2556252 · Cited by 75
On-the-fly Operation Batching in Dynamic Computation Graphs
Neubig, G., Goldberg, Y., & Dyer, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07860 · Cited by 37
Many-query join: efficient shared execution of relational joins on modern hardware
Makreshanski, D., Giannikis, G. K., Alonso, G., & Kossmann, D. (2017) · The VLDB Journal · doi:10.1007/s00778-017-0475-4 · Cited by 15
Research works printed but not linked: 5
- Awni Hannun Carl Case Jared Casper Bryan Catanzaro Greg Diamos Erich Elsen Ryan Prenger Sanjeev Satheesh Shubho Sengupta Adam Coates etal 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014). Awni Hannun Carl Case Jared Casper Bryan Catanzaro Greg Diamos Erich Elsen Ryan Prenger Sanjeev Satheesh Shubho Sengupta Adam Coates et al. 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014). · arXiv
- 10.5555/2946645.2946679 · doi:10.5555/2946645.2946679
- Graham Neubig , Chris Dyer , Yoav Goldberg , Austin Matthews , Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, et al. 2017 . DyNet: The Dynamic Neural Network Toolkit . arXiv preprint arXiv:1701.03980 (2017). Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, et al. 2017. DyNet: The Dynamic Neural Network Toolkit. arXiv preprint arXiv:1701.03980 (2017). · arXiv
- Ming Tan , Cicero dos Santos , Bing Xiang , and Bowen Zhou . 2015. LSTM-based deep learning models for non-factoid answer selection. arXiv preprint arXiv:1511.04108 ( 2015 ). Ming Tan, Cicero dos Santos, Bing Xiang, and Bowen Zhou. 2015. LSTM-based deep learning models for non-factoid answer selection. arXiv preprint arXiv:1511.04108 (2015). · arXiv
- Seiya Tokui , Kenta Oono , Shohei Hido , and Justin Clayton . 2015 . Chainer: a next-generation open source framework for deep learning . In Proceedings of workshop on machine learning systems (LearningSys) in the twenty-ninth annual conference on neural information processing systems (NIPS) , Vol. 5 . Seiya Tokui, Kenta Oono, Shohei Hido, and Justin Clayton. 2015. Chainer: a next-generation open source framework for deep learning. In Proceedings of workshop on machine learning systems (LearningSys) in the twenty-ninth annual conference on neural information processing systems (NIPS), Vol. 5.
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
“To address this problem, fine-grained batching mechanisms, such as cellular batching [16] and iteration-level scheduling [60], have been proposed.”
Deep Learning Workload Scheduling in GPU Datacenters: A Survey
Ye, Z., Gao, W., Hu, Q., Sun, P., Wang, X., Luo, Y., Zhang, T., & Wen, Y. (2024) · ACM Computing Surveys · doi:10.1145/3638757 · Cited by 269
TurboTransformers: an efficient GPU serving system for transformer models
Fang, J., Yu, Y., Zhao, C., & Zhou, J. (2021) · Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming · doi:10.1145/3437801.3441578 · Cited by 116
Deep learning in electron microscopy
Ede, J. M. (2021) · Machine Learning Science and Technology · doi:10.1088/2632-2153/abd614 · Cited by 143
Metadata
- Authors
- Gao, P., Yu, L., Wu, Y., & Li, J.
- Affiliations
- New York University (US)
- Tsinghua University (CN)
- Venue
- Proceedings of the Thirteenth EuroSys Conference
- Publisher
- ACM
- Published
- 2018-04-23
- Pages
- 1-15
- OpenAlex
- W2798291715
- Cited by
- 66
- References
- 36
- Citations by year
- 2026: 5 · 2025: 6 · 2024: 10 · 2023: 5 · 2022: 7 · 2021: 11 · 2020: 16 · 2019: 6
- FWCI
- 7.04
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- European Conference on Computer Systems (publishedVersion)
- Funders
- Nvidia
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Information Systems › Advanced Database Systems and Queries
- Keywords
- low latency, throughput
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
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.