Litcius/Paper detail

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Amir Gholami, Coleman Hooper, Kurt Keutzer, Sehoon Kim, Michael W. Mahoney, Hiva Mohammadzadeh, Yakun Sophia Shao

202415 citationsDOI

Topics & Concepts

Computer scienceCacheContext (archaeology)AlgorithmInferenceQuantization (signal processing)Artificial intelligenceTheoretical computer scienceVector quantizationData miningCaching and Content DeliveryAdvanced Data Storage TechnologiesNetwork Packet Processing and Optimization
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization | Litcius