HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis

arXiv:2405.00738v1 Announce Type: cross
Abstract: Graphics Processing Units (GPUs) have become the leading hardware accelerator for deep learning applications and are used widely in training and inference of transformers; transformers have achieved state-of-the-art performance in many areas of machine learning and are especially used in most modern Large Language Models (LLMs). However, GPUs require large amounts of energy, which poses environmental concerns, demands high operational costs, and causes GPUs to be unsuitable for edge computing. We develop an accelerator for …

arxiv cs.ai cs.ar cs.lg energy fpgas inference llama llama 2 synthesis type via