AUM: Unleashing the Efficiency Potential of Shared Processors with Accelerator Units for LLM Serving.
Xinkai Wang, Chao Li, Yiming Zhuansun, Jinyang Guo, Xiaofeng Hou, Jing Wang, Luping Wang, Weigao Chen, Cheng Huang, Guodong Yang, Liping Zhang, Minyi Guo
Browse the full HPCA paper archive.