https://podcasts.apple.com/nz/podcast/arxiv-preprint-kvquant-towards-10-million-context-length/id1686718892?i=1000644372033
arxiv preprint - KVQuant: Towa... - AI Breakdown - Apple Podcasts
In this episode, we discuss KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization by Coleman Hooper, Sehoon Kim, Hiva Mohammadzade
arxiv preprinttowaaibreakdownapple