BibTeX record conf/asplos/MiaoOZCWZWZYSSC24

• > Home > conf/asplos/MiaoOZCWZWZYSSC24

@inproceedings{DBLP:conf/asplos/MiaoOZCWZWZYSSC24,
  author       = {Xupeng Miao and
                  Gabriele Oliaro and
                  Zhihao Zhang and
                  Xinhao Cheng and
                  Zeyu Wang and
                  Zhengxin Zhang and
                  Rae Ying Yee Wong and
                  Alan Zhu and
                  Lijie Yang and
                  Xiaoxiang Shi and
                  Chunan Shi and
                  Zhuoming Chen and
                  Daiyaan Arfeen and
                  Reyna Abhyankar and
                  Zhihao Jia},
  editor       = {Rajiv Gupta and
                  Nael B. Abu{-}Ghazaleh and
                  Madan Musuvathi and
                  Dan Tsafrir},
  title        = {SpecInfer: Accelerating Large Language Model Serving with Tree-based
                  Speculative Inference and Verification},
  booktitle    = {Proceedings of the 29th {ACM} International Conference on Architectural
                  Support for Programming Languages and Operating Systems, Volume 3,
                  {ASPLOS} 2024, La Jolla, CA, USA, 27 April 2024- 1 May 2024},
  pages        = {932--949},
  publisher    = {{ACM}},
  year         = {2024},
  url          = {https://doi.org/10.1145/3620666.3651335},
  doi          = {10.1145/3620666.3651335},
  timestamp    = {Sat, 04 May 2024 10:55:05 +0200},
  biburl       = {https://dblp.org/rec/conf/asplos/MiaoOZCWZWZYSSC24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}