inference/research
verifiedhigh · 0.90updated 2026-10-03

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

paper

Fields

id
sources/niche-xgrammar-paper
URL
https://arxiv.org/abs/2411.15100
Publisher
arXiv
Kind
paper
Published
2024-11-22
Accessed
2026-10-03
notes
XGrammar system paper. Primary source for the per-token overhead argument that made grammar-constrained decoding viable inside a production server.

Notes

XGrammar system paper. Primary source for the per-token overhead argument that made grammar-constrained decoding viable inside a production server.

Cross-references

This record references no other records.