‪Shengyu Liu‬ - ‪„Google“ mokslinčius‬

Gauti savo profilį

Cituota

	Visi	Nuo 2020
Šaltiniai	241	241
h-rodyklė	4	4
i10-rodyklė	3	3

0

180

90

45

135

20232024202510 169 58

Bendraautoriai

Xin JinPeking UniversityPatvirtintas el. paštas pku.edu.cn
Yinmin ZhongPeking UniversityPatvirtintas el. paštas pku.edu.cn
Bingyang WuPeking UniversityPatvirtintas el. paštas pku.edu.cn
Hao ZhangUC San DiegoPatvirtintas el. paštas ucsd.edu

Shengyu Liu

Shengyu Liu

Peking University

Patvirtintas el. paštas stu.pku.edu.cn - Pagrindinis puslapis

Computer System Machine Learning System


Pavadinimas Rūšiuoti pagal šaltinius Rūšiuoti pagal metus Rūšiuoti pagal pavadinimą	Cituota Cituota	Metai
{DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving Y Zhong, S Liu, J Chen, J Hu, Y Zhu, X Liu, X Jin, H Zhang 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI …, 2024	123	2024
Fast distributed inference serving for large language models B Wu, Y Zhong, Z Zhang, S Liu, F Liu, Y Sun, G Huang, X Liu, X Jin arXiv preprint arXiv:2305.05920, 2023	88	2023
Loongserve: Efficiently serving long-context large language models with elastic sequence parallelism B Wu, S Liu, Y Zhong, P Sun, X Liu, X Jin Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles …, 2024	26	2024
RLHFuse: Efficient RLHF Training for Large Language Models with Inter-and Intra-Stage Fusion Y Zhong, Z Zhang, B Wu, S Liu, Y Chen, C Wan, H Hu, L Xia, R Ming, ... arXiv preprint arXiv:2409.13221, 2024	4	2024
SwiftLLM: A tiny yet powerful LLM inference system tailored for researching purpose S Liu https://github.com/interestingLSY/swiftLLM, 2024		2024
{DistServe}: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Y Zhong, S Liu, J Chen, J Hu, Y Zhu, X Liu, X Jin, H Zhang 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI …, 2024		2024

Sistema negali atlikti operacijos. Bandykite vėliau dar kartą.

Straipsniai 1–6