activity
20232026
most citedEdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models

2 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing 2024Show all

2 papers · 1 filter

cs.AR2024★ 2 cited

EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models

Mingqiang Huang, Ao Shen, Kai Li +4

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it…

cs.CV2024

Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks

Muqun Niu, Yuan Ren, Boyu Li +1

Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separat…