Showing cs.ARShow all
2 papers · 1 filter
cs.AR2025
SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding
Linfeng Zhong, Songqiang Xu, Huifeng Wen +4
The growing demand for efficient long-sequence modeling on edge devices has propelled widespread adoption of State Space Models (SSMs) like Mamba, due to their superior computation…
cs.AR2024
HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline
Qingyu Guo, Jiayong Wan, Songqiang Xu +2
Vision Transformer (ViT) acceleration with field programmable gate array (FPGA) is promising but challenging. Existing FPGA-based ViT accelerators mainly rely on temporal architect…