SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration

Jinming Zhuang, Zhuoping Yang, Shixin Ji, Heng Huang, Alex K. Jones, Jingtong Hu, Yiyu Shi 0001, Peipei Zhou 0001. SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration. In Zhiru Zhang, Andrew Putnam, editors, Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays, FPGA 2024, Monterey, CA, USA, March 3-5, 2024. pages 55-66, ACM, 2024. [doi]

Abstract

Abstract is missing.