Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
This addresses the problem of memory constraints for edge device deployment of large AI models, representing a strong incremental improvement over existing pipeline mechanisms.
The paper tackles the memory challenge of deploying Transformer-based large models on edge devices by introducing Hermes, a framework that achieves up to 4.24× faster inference and 86.7% lower memory consumption for BERT/ViT models, and 2.58× faster inference with 90.3% lower memory for GPT-style models compared to state-of-the-art methods.
The application of Transformer-based large models has achieved numerous success in recent years. However, the exponential growth in the parameters of large models introduces formidable memory challenge for edge deployment. Prior works to address this challenge mainly focus on optimizing the model structure and adopting memory swapping methods. However, the former reduces the inference accuracy, and the latter raises the inference latency. This paper introduces PIPELOAD, a novel memory-efficient pipeline execution mechanism. It reduces memory usage by incorporating dynamic memory management and minimizes inference latency by employing parallel model loading. Based on PIPELOAD mechanism, we present Hermes, a framework optimized for large model inference on edge devices. We evaluate Hermes on Transformer-based models of different sizes. Our experiments illustrate that Hermes achieves up to 4.24 X increase in inference speed and 86.7% lower memory consumption than the state-of-the-art pipeline mechanism for BERT and ViT models, 2.58 X increase in inference speed and 90.3% lower memory consumption for GPT-style models.