Реклама

SALT: Salience-Aware Lexical Trie for Long-Context Compression

#SALT #Salience-Aware #Lexical #Trie #Long-Context

arXiv:2607.17486v2 Announce Type: replace-cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-level prompt compression methods address this, but rank each…