Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward

Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward

Arnav Chavan, Raghav Magazine, Shubham Kushwaha, Merouane Debbah, Deepak Gupta

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Survey Track. Pages 7980-7988. https://doi.org/10.24963/ijcai.2024/883

Despite the impressive performance of LLMs, their widespread adoption faces challenges due to substantial computational and memory requirements during inference. Recent advancements in model compression and system-level optimization methods aim to enhance LLM inference. This survey offers an overview of these methods, emphasizing recent developments. Through experiments on LLaMA(/2)-7B, we evaluate various compression techniques, providing practical insights for efficient LLM deployment in a unified setting. The empirical analysis on LLaMA(/2)-7B highlights the effectiveness of these methods. Drawing from survey insights, we identify current limitations and discuss potential future directions to improve LLM inference efficiency. We release the codebase to reproduce the results presented in this paper at https://github.com/nyunAI/Faster-LLM-Survey
Keywords:
Natural Language Processing: NLP: Language models
Natural Language Processing: NLP: Resources and evaluation