Enhancing Transformer Inference Efficiency on FPGA Through Fully Fusion and Integer-Only Quantization Techniques.
Zhenqi Li, Yuan Li, Mingche Lai, Puguang Liu, Qiang Wang, Yankang Zhao, Hanyuan Li, Xingyun Qi
Browse the full ICCD paper archive.
Zhenqi Li, Yuan Li, Mingche Lai, Puguang Liu, Qiang Wang, Yankang Zhao, Hanyuan Li, Xingyun Qi
Browse the full ICCD paper archive.