Episode
REFRAG with Xiaoqiang Lin - Weaviate Podcast #130!
- Podcast
- Weaviate Podcast
- Published
- Nov 3, 2025
- Duration seconds
- 3600
- Processing state
not_requested- Canonical source
- https://podcasters.spotify.com/pod/show/weaviate/episodes/REFRAG-with-Xiaoqiang-Lin---Weaviate-Podcast-130-e3aed71
Actions
POST https://stenobird.com/v1/public/podcasts/weaviate-podcast-6288219/episodes/refrag-with-xiaoqiang-lin-weaviate-podcast-130/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/weaviate-podcast-6288219/refrag-with-xiaoqiang-lin-weaviate-podcast-130.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
Xiaoqiang Lin is a Ph.D. student at the National University of Singapore. During his time at Meta, Xiaoqiang lead the research behind REFRAG: Rethinking RAG-based Decoding. Traditional RAG systems use vectors to retrieve relevant context with semantic search, but then throw away the vectors when passing the context to the LLM. REFRAG instead feeds the LLM these pre-compute vectors, achieving massive gains in long context processing and LLM inference speed! REFRAG makes Time-To-First-Token (TTFT) 31x faster and Time-To-Iterative-Token (TTIT) 3x faster, boosting overall LLM throughput by 7x while also being able to handle much longer contexts! There are so many interesting aspects to this and I really loved diving into the details with Xiaoqiang! I hope you enjoy the podcast!