Fast Video Generation with Sliding Tile AttentionFebruary 18, 2025Peiyuan Zhang, Yongqi Chen*, Runlong Su*, Hangliang Ding, Ion Stoica, Zhengzhong Liu, Hao Zhang
Dynasor: More Efficient Chain-of-Thought Through Certainty ProbingFebruary 16, 2025Yichao Fu, Junda Chen, Yonghao Zhuang, Zheyu Fu, Ion Stoica, Hao Zhang
Efficient LLM Scheduling by Learning to RankJanuary 13, 2025Yichao Fu, Siqi Zhu, Runlong Su, Aurick Qiao, Ion Stoica, Hao Zhang
MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM ServingMay 20, 2024Jiangfei Duan, Runyu Lu, Haojie Duanmu, Xiuhong Li, Xingcheng Zhang, Dahua Lin, Ion Stoica, Hao Zhang
Consistency Large Language Models: A Family of Efficient Parallel DecodersMay 6, 2024Siqi Kou*, Lanxiang Hu*, Zhezhi He, Zhijie Deng, Hao Zhang
Throughput is Not All You Need: Maximizing Goodput in LLM Serving using Prefill-Decode DisaggregationMarch 17, 2024Yinmin Zhong, Junda Chen, Shengyu Liu, Yibo Zhu, Xin Jin, Hao Zhang
