Poster · Atlanta

Demystifying Numerical Errors in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL

Name: Demystifying Numerical Errors in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
Start: 2026-12-11T10:00:00-05:00
End: 2026-12-11T13:00:00-05:00
Location: Hall C1, Georgia World Congress Center

When: Fri 11 Dec 2026, 10:00–13:00 EST
Where: Hall C1, Georgia World Congress Center
Session: Atlanta Poster Session 5
Authors: Zhenting Zhu, Lucas Thai, Shan Yu, Yicheng Liu, Yifan Qiao, Chenxi Wang, Harry Xu, Junyi Shu
Organisations: University of California, Los Angeles, Shanghai Jiao Tong University, University of California, Berkeley, Chinese Academy of Sciences
QRS classification: Language models, Efficient and distributed ML systems

Open in schedule Official page