🧑🔬 William Brandon — papers of 2024 — Elamur Research1 paper · all years of William BrandonReducing Transformer Key-Value Cache Size with Cross-Layer AttentionConference on Neural Information Processing Systems (NeurIPS)William Brandon, Mayank Mishra, Aniruddha Nrusimha, et al.2024 · 57 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/william-brandon/year/2024/