Reaching 1B Context Length With RAG

Zyphra: https://www.zyphra.com/post/reaching-1b-context-length-with-rag

retrieval system enables LLMs to process up to 1 billion tokens efficiently on a standard CPU using a sparse graph-based approach. Outperforms RAG methods with dense embeddings or long-context transformers.

I’m impressed with the work Zyphra has been doing in the SSM space (most recently Zamba2-7B) so I’m eager to see more.

I'm not super booked up-- does this mean that somebody built a retrieval system that works fine with 1 billion tokens on normal hardware?