Следене
Dacheng Li
Dacheng Li
Потвърден имейл адрес: berkeley.edu - Начална страница
Заглавие
Позовавания
Позовавания
Година
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, 2024
957*2024
Dual contradistinctive generative autoencoder
G Parmar, D Li, K Lee, Z Tu
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021
812021
How Long Can Context Length of Open-Source LLMs truly Promise?
D Li, R Shao, A Xie, Y Sheng, L Zheng, J Gonzalez, I Stoica, X Ma, ...
NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following, 2023
52*2023
MPCFormer: fast, performant and private Transformer inference with MPC
D Li, R Shao, H Wang, H Guo, EP Xing, H Zhang
2023 International Conference on Learning Representations, 2022
312022
S-lora: Serving thousands of concurrent lora adapters
Y Sheng, S Cao, D Li, C Hooper, N Lee, S Yang, C Chou, B Zhu, L Zheng, ...
MLSys 2024, The Seventh Annual Conference on Machine Learning and Systems, 2023
182023
Chatbot arena: An open platform for evaluating llms by human preference
WL Chiang, L Zheng, Y Sheng, AN Angelopoulos, T Li, D Li, H Zhang, ...
arXiv preprint arXiv:2403.04132, 2024
52024
Fairness in serving large language models
Y Sheng, S Cao, D Li, B Zhu, Z Li, D Zhuo, JE Gonzalez, I Stoica
18th USENIX Symposium on Operating Systems Design and Implementation (OSDI’24), 2023
52023
Lightseq: Sequence level parallelism for distributed training of long context transformers
D Li, R Shao, A Xie, EP Xing, JE Gonzalez, I Stoica, X Ma, H Zhang
NeurIPS 2023 Workshop on Advancing Neural Network Training (WANT), 2023
52023
Amp: Automatically finding model parallel strategies with heterogeneity awareness
D Li, H Wang, E Xing, H Zhang
Advances in Neural Information Processing Systems 35, 6630-6639, 2022
52022
Does compressing activations help model parallel training?
S Bian, D Li, H Wang, EP Xing, S Venkataraman
MLSys 2024, The Seventh Annual Conference on Machine Learning and Systems, 2023
12023
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–10