BibTeX record journals/corr/abs-2401-14112

• > Home > journals/corr/abs-2401-14112

@article{DBLP:journals/corr/abs-2401-14112,
  author       = {Haojun Xia and
                  Zhen Zheng and
                  Xiaoxia Wu and
                  Shiyang Chen and
                  Zhewei Yao and
                  Stephen Youn and
                  Arash Bakhtiari and
                  Michael Wyatt and
                  Donglin Zhuang and
                  Zhongzhu Zhou and
                  Olatunji Ruwase and
                  Yuxiong He and
                  Shuaiwen Leon Song},
  title        = {{FP6-LLM:} Efficiently Serving Large Language Models Through FP6-Centric
                  Algorithm-System Co-Design},
  journal      = {CoRR},
  volume       = {abs/2401.14112},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2401.14112},
  doi          = {10.48550/ARXIV.2401.14112},
  eprinttype    = {arXiv},
  eprint       = {2401.14112},
  timestamp    = {Tue, 06 Feb 2024 14:15:49 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2401-14112.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}