Ningren Han

YouTube

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Distributed Systems & Hardware (1)Inference & Quantization (1)Recommendation & Information Retrieval (1)

Frequent co-authors

Zhengyang Su (1)Isay Katsman (1)Isay Katsman (1)Yueqi Wang (1)

Papers (1)

Feb 26, 2026

YouTube2w ago·also DeepMind, Yale

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Forget slow prefix trees: STATIC unlocks massive speedups (up to 1033x) for constrained LLM decoding on GPUs/TPUs by vectorizing trie traversals into sparse matrix operations.

Zhengyang Su, Isay Katsman, Isay Katsman +22

Distributed Systems & Hardware Inference & Quantization Recommendation & Information Retrieval

Search

Ningren Han

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)