🧑🔬 Zhekai Zhang — papers of 2020 — 1 paper, the most cited first1 paper · all years of Zhekai ZhangSpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head PruningProceedings - International Symposium on High-Performance Computer Architecture/ProceedingsHanrui Wang, Zhekai Zhang, Song Han2020 · 534 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/zhekai-zhang/year/2020/