Publications

Ziming Liu, Boyu Tian, Guoteng Wang, Zhen Jiang, Peng Sun, Zhenhua Han, Tian Tang, Xiaohe Hu, Yanmin Jia, Yan Zhang, He Liu, Mingjun Zhang, Yiqi Zhang, Qiaoling Chen, Shenggan Cheng, Mingyu Gao, Yang You, Siyuan Feng (2025). Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving. Arxiv Preprint.

Ziming Liu, Yifan Yang, Chengruidong Zhang, Yiqi Zhang, Lili Qiu, Yang You, Yuqing Yang (2025). Region-Adaptive Sampling for Diffusion Transformers. Arxiv Preprint.

Junfeng Lin*, Ziming Liu*, Yang You, Jun Wang, Weihao Zhang, Rong Zhao (2024). WeiPipe: Weight Pipeline Parallelism for Communication-Effective Long-Context Large Model Training. PPoPP 2025. *:Equal Contribution.

Shenggan Cheng, Shengjie Lin, Lansong Diao, Hao Wu, Siyu Wang, Chang Si, Ziming Liu, Xuanlei Zhao, Jiangsu Du, Wei Lin, Yang You (2024). Concerto: Automatic Communication Optimization and Scheduling for Large-Scale Deep Learning. To appear on ASPLOS 2025.

Ziming Liu, Shaoyu Wang, Shenggan Cheng, Zhongkai Zhao, Kai Wang, Xuanlei Zhao, James Demmel, Yang You (2024). StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training. NeurIPS 2025.

Xuanlei Zhao, Bin Jia, Haotian Zhou, Ziming Liu, Shenggan Cheng, Yang You (2024). HeteGen: Efficient Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices. In MLSys 2024, Proceedings of Machine Learning and Systems.

Xuanlei Zhao, Shenggan Cheng, Guangyang Lu, Jiarui Fang, Haotian Zhou, Bin Jia, Ziming Liu, Yang You (2024). AutoChunk: Automated Activation Chunk for Memory-Efficient Long Sequence Inference. In ICLR 2024, International Conference on Learning Representations.

Xuanlei Zhao, Shenggan Cheng, Zangwei Zheng, Zheming Yang, Ziming Liu, Yang You (2024). DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers. Arxiv Preprint.

Ziming Liu*, Shenggan Cheng*, Haotian Zhou, Yang You (2023). Hanayo: Harnessing Wave-like Pipeline Parallelism for Enhanced Large Model Training Efficiency. In SC ‘23, Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. *:Equal Contribution.

Shenggan Cheng, Ziming Liu, Jiangsu Du, Yang You (2023). ATP: Adaptive Tensor Parallelism for Foundation Models. Arxiv Preprint.