A team of researchers from Meta Superintelligence Labs, National University of Singapore and Rice University has unveiled REFRAG (REpresentation For RAG), a decoding framework that rethinks retrieval-augmented generation (RAG) efficiency. REFRAG extends LLM context windows by 16× and achieves up to a 30.85× acceleration in time-to-first-token (TTFT) without compromising accuracy. Why is long context such […] The post Meta Superintelligence Labs Introduces REFRAG: Scaling RAG with 16× Longer Contexts and 31× Faster Decoding appeared first on MarkTechPost.
Meta Superintelligence Labs Introduces REFRAG: Scaling RAG with 16× Longer Contexts and 31× Faster Decoding
A team of researchers from Meta Superintelligence Labs, National University of Singapore and Rice University has unveiled REFRAG (REpresentation For RAG), a decoding framework that rethinks retrieval-augmented generation (RAG) efficiency. REFRAG extends LLM context windows by 16× and achieves up to a 30.85× acceleration in time-to-first-token (TTFT) without compromising accuracy. Why is long context such […] The post Meta Superintelligence Labs Introduces REFRAG: Scaling RAG with 16× Longer Contexts and 31× Faster Decoding appeared first on MarkTechPost.