ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
This addresses efficiency problems for deploying LLMs in resource-limited settings, though it is incremental as it revisits an existing activation function.
The study tackles the high computational cost of deploying large language models (LLMs) on resource-constrained devices by advocating for ReLU activations, which reduce inference computation up to three times with minimal performance impact.
Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices. Despite recent trends favoring alternative activation functions such as GELU or SiLU, known for increased computation, this study strongly advocates for reinstating ReLU activation in LLMs. We demonstrate that using the ReLU activation function has a negligible impact on convergence and performance while significantly reducing computation and weight transfer. This reduction is particularly valuable during the memory-bound inference step, where efficiency is paramount. Exploring sparsity patterns in ReLU-based LLMs, we unveil the reutilization of activated neurons for generating new tokens and leveraging these insights, we propose practical strategies to substantially reduce LLM inference computation up to three times, using ReLU activations with minimal performance trade-offs.