| Orca: A Distributed Serving System for Transformer-Based Generative Models GI Yu, JS Jeong, GW Kim, S Kim, BG Chun 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI …, 2022 | 121 | 2022 |
| Parallax: Sparsity-aware Data Parallel Training of Deep Neural Networks S Kim, GI Yu, H Park, S Cho, E Jeong, H Ha, S Lee, JS Jeong, BG Chun Proceedings of the Fourteenth EuroSys Conference 2019, 1-15, 2019 | 97 | 2019 |
| Nimble: Lightweight and Parallel GPU Task Scheduling for Deep Learning W Kwon, GI Yu, E Jeong, BG Chun Advances in Neural Information Processing Systems 33, 2020 | 58 | 2020 |
| A Tensor Compiler for Unified Machine Learning Prediction Serving S Nakandala, K Saur, GI Yu, K Karanasos, C Curino, M Weimer, ... 14th {USENIX} Symposium on Operating Systems Design and Implementation …, 2020 | 51 | 2020 |
| JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs E Jeong, S Cho, GI Yu, JS Jeong, DJ Shin, BG Chun 16th {USENIX} Symposium on Networked Systems Design and Implementation …, 2019 | 27 | 2019 |
| Dolphin: Runtime Optimization for Distributed Machine Learning BG Chun, B Cho, B Jeon, JS Jeong, G Kim, JY Kim, WY Lee, YS Lee, ... ML Systems Workshop at ICML, 2016 | 20* | 2016 |
| Automating System Configuration of Distributed Machine Learning WY Lee, Y Lee, JS Jeong, GI Yu, JY Kim, HJ Park, B Jeon, W Song, G Kim, ... 2019 IEEE 39th International Conference on Distributed Computing Systems …, 2019 | 16 | 2019 |
| Improving the expressiveness of deep learning frameworks with recursion E Jeong, JS Jeong, S Kim, GI Yu, BG Chun Proceedings of the Thirteenth EuroSys Conference, 1-13, 2018 | 16 | 2018 |
| Speculative Symbolic Graph Execution of Imperative Deep Learning Programs E Jeong, S Cho, GI Yu, JS Jeong, DJ Shin, T Kim, BG Chun ACM SIGOPS Operating Systems Review 53 (1), 26-33, 2019 | 13 | 2019 |
| BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models T Kim, H Kim, GI Yu, BG Chun | 12 | 2023 |
| WindTunnel: towards differentiable ML pipelines beyond a single model GI Yu, S Amizadeh, S Kim, A Pagnoni, C Zhang, BG Chun, M Weimer, ... Proceedings of the VLDB Endowment 15 (1), 11-20, 2021 | 8 | 2021 |
| Accelerating Multi-Model Inference by Merging DNNs of Different Weights JS Jeong, S Kim, GI Yu, Y Lee, BG Chun arXiv preprint arXiv:2009.13062, 2020 | 7 | 2020 |
| Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach GI Yu, S Amizadeh, BG Chun, M Weimer, M Interlandi Workshop on Systems for ML and Open Source Software at NeurIPS 2018, 2018 | 6 | 2018 |
| Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs T Kim, E Jeong, GW Kim, Y Koo, S Kim, GI Yu, BG Chun Advances in Neural Information Processing Systems 34, 2021 | 5 | 2021 |
| Compiling Classical ML Pipelines into Tensor Computations for One-size-fits-all Prediction Serving S Nakandala, GI Yu, M Weimer, M Interlandi Systems for ML workshop at NeurIPS, 2019 | 5 | 2019 |
| Stage-based Hyper-parameter Optimization for Deep Learning A Shin, DJ Shin, S Cho, DY Kim, E Jeong, GI Yu, BG Chun arXiv preprint arXiv:1911.10504, 2019 | 4 | 2019 |
| Dynamic batching for inference system for transformer-based generation tasks G Yu, G Kim, JS Jeong, S Kim, B Chun US Patent 11,442,775, 2022 | 3 | 2022 |
| Auto-Parallelizing Deep Learning for Multi-machine, Multi-GPU Environments S Kim, E Jeong, JS Jeong, H Park, GI Yu, BG Chun Workshop on AI Systems at Symposium on Operating Systems Principles (SOSP), 2017 | 2 | 2017 |
| Taming Model Serving Complexity, Performance and Cost: A Compilation to Tensor Computations Approach S Nakandala, K Saur, GI Yu, K Karanasos, C Curino, M Weimer, ... | 2 | |
| Demonstration of JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs E Jeong, S Cho, GI Yu, JS Jeong, DJ Shin, BG Chun SysML Conference, Stanford, CA, USA, Mar, 0 | 1 | |
Byung-Gon ChunSeoul National UniversityVerified email at snu.ac.kr
