@article{vectorizingthetrieefficientconstrainedde, title = {Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators}, author = {Zhengyang Su and Isay Katsman and Yueqi Wang and Ruining He and Lukasz Heldt and Raghunandan Keshavan and Shao-Chuan Wang and Xinyang Yi and Mingyan Gao and Onkar Dalal and Lichan Hong and Ed Chi and Ningren Han}, year = {2026}, eprint = {2602.22647}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.22647}, }