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

> Research article (Advances in Neural Information Processing Systems 37, 2024) · cited 10× · AI/ML

**Wikidata**: [openalex:W4415799217](https://www.wikidata.org/wiki/openalex:W4415799217)  
**Source**: https://4ort.xyz/entity/kvquant-towards-10-million-context-length-llm-inference-with-kv-cache-quantization