Segueix
Siyuan Zhuang
Siyuan Zhuang
PhD Student, UC Berkeley
Correu electrònic verificat a berkeley.edu
Títol
Citada per
Citada per
Any
Judging llm-as-a-judge with mt-bench and chatbot arena
L Zheng, WL Chiang, Y Sheng, S Zhuang, Z Wu, Y Zhuang, Z Lin, Z Li, ...
Advances in Neural Information Processing Systems 36, 46595-46623, 2023
3049*2023
Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality
WL Chiang, Z Li, Z Lin, Y Sheng, Z Wu, H Zhang, L Zheng, S Zhuang, ...
See https://vicuna. lmsys. org (accessed 14 April 2023) 2 (3), 6, 2023
2606*2023
Efficient memory management for large language model serving with pagedattention
W Kwon, Z Li, S Zhuang, Y Sheng, L Zheng, CH Yu, J Gonzalez, H Zhang, ...
Proceedings of the 29th Symposium on Operating Systems Principles, 611-626, 2023
12712023
Lmsys-chat-1m: A large-scale real-world llm conversation dataset
L Zheng, WL Chiang, Y Sheng, T Li, S Zhuang, Z Wu, Y Zhuang, Z Li, ...
arXiv preprint arXiv:2309.11998, 2023
1182023
Terapipe: Token-level pipeline parallelism for training large-scale language models
Z Li, S Zhuang, S Guo, D Zhuo, H Zhang, D Song, I Stoica
International Conference on Machine Learning, 6543-6552, 2021
1072021
{SkyPilot}: An intercloud broker for sky computing
Z Yang, Z Wu, M Luo, WL Chiang, R Bhardwaj, W Kwon, S Zhuang, ...
20th USENIX Symposium on Networked Systems Design and Implementation (NSDI …, 2023
792023
Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arXiv 2023
L Zheng, WL Chiang, Y Sheng, S Zhuang, Z Wu, Y Zhuang, Z Lin, Z Li, ...
arXiv preprint arXiv:2306.05685, 0
51
Hoplite: efficient and fault-tolerant collective communication for task-based distributed systems
S Zhuang, Z Li, D Zhuo, S Wang, E Liang, R Nishihara, P Moritz, I Stoica
Proceedings of the 2021 ACM SIGCOMM 2021 Conference, 641-656, 2021
282021
sensai: Convnets decomposition via class parallelism for fast inference on live data
G Wang, Z Liu, B Hsieh, S Zhuang, J Gonzalez, T Darrell, I Stoica
Proceedings of Machine Learning and Systems 3, 664-679, 2021
182021
Composing MPC with LQR and Neural Network for Amortized Efficiency and Stable Control
F Wu, G Wang, S Zhuang, K Wang, A Keimer, I Stoica, A Bayen
arXiv preprint arXiv:2112.07238, 2021
92021
{ExoFlow}: A universal workflow system for {Exactly-Once}{DAGs}
S Zhuang, S Wang, E Liang, Y Cheng, I Stoica
17th USENIX Symposium on Operating Systems Design and Implementation (OSDI …, 2023
72023
Sensai: Fast convnets serving on live data via class parallelism
G Wang, Z Liu, S Zhuang, B Hsieh, J Gonzalez, I Stoica
MLOps Systems workshop in MLSys, 2020
72020
Judgebench: A benchmark for evaluating llm-based judges
S Tan, S Zhuang, K Montgomery, WY Tang, A Cuadron, C Wang, ...
arXiv preprint arXiv:2410.12784, 2024
52024
Rearchitecting in-memory object stores for low latency
D Zhuo, K Zhang, Z Li, S Zhuang, S Wang, A Chen, I Stoica
Proceedings of the VLDB Endowment, 555-568, 2021
32021
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
A Cuadron, D Li, W Ma, X Wang, Y Wang, S Zhuang, S Liu, LG Schroeder, ...
arXiv preprint arXiv:2502.08235, 2025
2025
A Statistical Framework for Ranking LLM-Based Chatbots
S Ameli, S Zhuang, I Stoica, MW Mahoney
arXiv preprint arXiv:2412.18407, 2024
2024
Starburst: a cost-aware scheduler for hybrid cloud
M Luo, S Zhuang, S Vengadesan, R Bhardwaj, J Chang, E Friedman, ...
Proceedings of the 2024 USENIX Conference on Usenix Annual Technical …, 2024
2024
Providing Efficient Fault Tolerance in Distributed Systems
S Zhuang
University of California, Berkeley, 2024
2024
Starburst: A Cost-aware Scheduler for Hybrid Cloud
M Luo, S Zhuang, S Vengadesan, R Bhardwaj, J Chang, E Friedman, ...
2024 USENIX Annual Technical Conference (USENIX ATC 24), 37-57, 2024
2024
AVOIDING GPU OOM FOR DYNAMIC COMPUTATIONAL GRAPHS TRAINING
S Zhuang
En aquests moments el sistema no pot dur a terme l'operació. Torneu-ho a provar més tard.
Articles 1–20