Low-precision quantization is recognized for its efficacy in neural network optimization. Our
analysis reveals that non-quantized elementwise operations which are prevalent in layers …

Autoregressive Large Language Models (LLMs) have achieved impressive performance in
language tasks but face two significant bottlenecks:(1) quadratic complexity in the attention …

The costly multiplications challenge the deployment of modern deep neural networks
(DNNs) on resource-constrained devices. To promote hardware efficiency, prior works have …

We present Polynomial Attention Drop-in Replacement (PADRe), a novel and unifying
framework designed to replace the conventional self-attention mechanism in transformer …

Large language models (LLMs) have shown impressive performance on language tasks but
face challenges when deployed on resource-constrained devices due to their extensive …

Existing binary Transformers are promising in edge deployment due to their compact model
size, low computational complexity, and considerable inference accuracy. However …

Artificial Intelligence (AI) for edge applications represents a paradigm shift in how data is
processed and insights are generated in computing systems. Traditionally, machine learning …

The large language models (LLMs) that everyone is using are not deployed locally. Users
need to send relatively private and important data to LLM when using it. Handing over …