Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism.
Zizhao Mo, Jianxiong Liao, Huanle Xu, Zhi Zhou, Chengzhong Xu
Browse the full SC paper archive.
Zizhao Mo, Jianxiong Liao, Huanle Xu, Zhi Zhou, Chengzhong Xu
Browse the full SC paper archive.