Get Started
Research questionHow can grounded RAG reuse prefix caches when overlapping evidence is ordered differently?Grounded RAG requests may retrieve overlapping evidence, yet different evidence orders produce different token prefixes. This prevents prefix caching from reducing the cost of processing otherwise reusable prompt content.
Inference Optimization
Information Retrieval
Retrieval-Augmented Generation
Latest papersRecent research connected to this question, newest first.CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG InferenceThe source addresses prompt-layer evidence ordering for grounded RAG served with vLLM, while keeping the serving engine and retrieved evidence set unchanged. Evidence comes from three vLLM configurations and QA tests, reporting median time-to-first-token reductions of roughly 20–33% without a measured answer-quality loss.research paper · Sep 4, 2026
Related questions
How can structured RAG synthesize evidence scattered across many documents while limiting answer-generation cost?How can long-form RAG answer multi-hop questions across changing temporal, spatial, and relational contexts?How can long-context RAG preserve global document structure during retrieval?How can production RAG teams maintain reliable comparisons as new retrieval candidates arrive without rejudging overlapping documents?
Home
Topics
Search
Library