🧑🔬 Yucheng Li — papers of 2024 — 2 papers, the most cited first2 papers · all years of Yucheng LiMInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse AttentionConference on Neural Information Processing Systems (NeurIPS)Huiqiang Jiang, Yucheng Li, Chengruidong Zhang, et al.2024 · 202 citationsPyramidKV: Dynamic KV Cache Compression based on Pyramidal Information FunnelingarXiv:2406.02069Zefan Cai, Yichi Zhang, Bofei Gao, et al.2024 · 155 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/yucheng-li/year/2024/