succinct-trie

Tag

Cards List
#succinct-trie

FlashTrie: A GPU-Accelerated Constrained Beam Search for Generative Retrieval

arXiv cs.LG · 2026-07-14 Cached

FlashTrie presents a GPU-accelerated constrained beam search for generative retrieval, using a succinct trie layout and cooperative CUDA kernels to reduce decoding latency and enable real-time serving at scale, achieving up to 24× speedup and a 0.71% revenue lift in a commercial search engine.

0 favorites 0 likes
← Back to home

Submit Feedback