An Efficient FPGA-Based Hardware Accelerator of Fully Quantized Mamba-2
2025 IEEE 33rd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)（2025）
Key words
Hardware Accelerators,Efficient Acceleration,FPGA-based Hardware Accelerator,Square Root,Energy Efficiency,State Space,Flow Data,Lookup Table,Design Space,Balance Performance,State-space Model,Improve Energy Efficiency,Computational Pipeline,Hardware Implementation,Hardware Resources,Hardware Architecture,Quantization Scheme,Segmentation Strategy,Selective Layer,Inverse Square Root,Hidden State,Linear Layer,Linear Operator,Digital Signal Processing,Nonlinear Function,Einstein Summation,Bit-width,Convolutional Layers,Perplexity,Computational Resources
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined