Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs Permalink
Yixuan Mei and Zikun Li and Zixuan Chen and Shiqi Pan and Mengdi Wu and Xupeng Miao and Zhihao Jia and K. V. Rashmi
Yixuan Mei and Zikun Li and Zixuan Chen and Shiqi Pan and Mengdi Wu and Xupeng Miao and Zhihao Jia and K. V. Rashmi
Chen, Zixuan and Fan, Lei and Liu, Shengyun and Vukolić, Marko and Wang, Xiangzhe and Zhang, Jingjing
Conference proceedings talk at Testing Institute of America 2014 Annual Conference, Los Angeles, CA, USA
Talk at London School of Testing, London, UK
Tutorial at UC-Berkeley Institute for Testing Science, Berkeley, CA, USA
Talk at UC San Francisco, Department of Testing, San Francisco, CA, USA