Meta Superintelligence Labs Introduces REFRAG: Scaling RAG with 16× Longer Contexts and 31× Faster Decoding - MarkTechPost

Meta Superintelligence Labs Introduces REFRAG: Scaling RAG with 16× Longer Contexts and 31× Faster Decoding By Asif Razzaq - September 7, 2025 Table of contents Why is long context such a bottleneck for LLMs. How does REFRAG compress and shorten context. How is acceleration achieved.