UELLM: A Unified and Efficient Approach for Large Language Model Inference Serving.
Yiyuan He, Minxian Xu, Jingfeng Wu, Wanyi Zheng, Kejiang Ye, Cheng-Zhong Xu
Browse the full ICSOC paper archive.
Yiyuan He, Minxian Xu, Jingfeng Wu, Wanyi Zheng, Kejiang Ye, Cheng-Zhong Xu
Browse the full ICSOC paper archive.