AI RESEARCH
QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations
arXiv CS.LG
•
ArXi:2511.06767v2 Announce Type: replace Transformer-based models have revolutionized computer vision (CV) and natural language processing (NLP) by achieving state-of-the-art performance across a range of benchmarks. However, nonlinear operations in models significantly contribute to inference latency, presenting unique challenges for efficient hardware acceleration. To this end, we propose QUARK, a quantization-enabled FPGA acceleration framework that leverages common patterns in nonlinear operations to enable efficient circuit sharing, thereby reducing hardware resource requirements.