notesum.ai

Published at November 22

XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models

cs.CL
cs.AI
cs.PL

Released Date: November 22, 2024

Authors: Yixin Dong1, Charlie F. Ruan1, Yaxing Cai2, Ruihang Lai1, Ziyi Xu3, Yilong Zhao4, Tianqi Chen5

Aff.: 1Carnegie Mellon University; 2NVIDIA; 3Shanghai Jiao Tong University; 4University of California, Berkeley; 5Carnegie Mellon University, NVIDIA

Arxiv: http://arxiv.org/abs/2411.15100v1