Ziheng works on large language model (LLM) systems at Bytedance, focusing on scaling and optimizing LLM training and inference. He was a Ph.D. student advised by Luis Ceze and Tianqi Chen in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. He received his Bachelor’s degree from Fudan University, where he was a member of Fudan NLP Lab, working with Xipeng Qiu, and Zheng Zhang.
He is/was heavily involved in projects: MegaScale, Apache TVM, Apache MXNet