🧑🔬 Xiaodong Han — papers of 2024 — 1 paper, the most cited first1 paper · all years of Xiaodong HanPyramidInfer: Pyramid KV Cache Compression for High-throughput LLM InferenceFindings of the Association for Computational LinguisticsDongjie Yang, Xiaodong Han, Yan Gao, et al.2024 · 91 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/xiaodong-han/year/2024/