Publications

Ziji Shi, Chaoyi Ruan, Penghui Qi, Guangxing Huang, Xinyi Wan, Min Lin, Jialin Li (2025). Tetris: Efficient and Predictive KV Cache Offloading for Agentic and Reasoning Workloads. In SOSP'25 SAA Workshop.

Ziji Shi, Le Jiang, Ang Wang, Jie Zhang, Chencan Wu, Yong Li, Xiaokui Xiao, Wei Lin, Jialin Li (2025). TAPAS: Fast and Automatic Derivation of Tensor Parallel Strategies for Large Neural Networks. In 54th International Conference on Parallel Processing (ICPP 2025).

PDF Cite Poster

Ziji Shi, Jialin Li, Yang You (2024). ParaGAN: A Scalable Distributed Training Framework for Generative Adversarial Networks. In Proceedings of the 2024 ACM Symposium on Cloud Computing.

PDF Cite Poster

Ziji Shi, Le Jiang, Jie Zhang, Xianyan Jia, Yong Li, Chencan Wu, Jialin Li, Wei Lin (2023). TAP: Efficient Derivation of Tensor Parallel Plans for Large Neural Networks. In ISCA'23 ASSYST Workshop.

PDF Cite Poster

Xianyan Jia, Le Jiang, Ang Wang, Wencong Xiao, Ziji Shi, Jie Zhang, Xinyuan Li, Langshi Chen, Yong Li, Zhen Zheng, Xiaoyong Liu, Wei Lin (2022). Whale: Efficient Giant Model Training over Heterogeneous GPUs. In USENIX ATC'22.

PDF Cite Code Slides

Fuzhao Xue, Ziji Shi, Futao Wei, Yuxuan Lou, Yong Liu, Yang You (2021). Going Wider Instead of Deeper. In AAAI'22.