🧑🔬 Sehoon Kim — papers of 2024 — 1 paper, the most cited first1 paper · all years of Sehoon KimKVQuant: Towards 10 Million Context Length LLM Inference with KV Cache QuantizationConference on Neural Information Processing Systems (NeurIPS)Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, et al.2024 · 294 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/sehoon-kim/year/2024/