SAS: Sparse Attention Synthesizer for Efficient Language Model Inference.
Yuan Zhou, Shaojie Xiang, Lingfan Yu, Zhenyu Song, Charith Mendis, Yida Wang
Browse the full EuroSys paper archive.
Yuan Zhou, Shaojie Xiang, Lingfan Yu, Zhenyu Song, Charith Mendis, Yida Wang
Browse the full EuroSys paper archive.