English

Efficient Large Language Models with Zero-Shot Adjustable Acceleration

Computation and Language 2025-09-09 v2

Abstract

Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and during inference is critical for building efficient architectures. This paper introduces Zero-Shot Adjustable Acceleration, a novel training and inference method that dynamically adjusts hardware utilization during inference without requiring additional fine-tuning. The proposed approach is applied to recent LLMs and evaluated across multiple classification and text generation tasks. Experimental results demonstrate that the method supports a wide range of zero-shot acceleration and achieves up to 11x speedup compared to the baseline.

Keywords

Cite

@article{arxiv.2509.01190,
  title  = {Efficient Large Language Models with Zero-Shot Adjustable Acceleration},
  author = {Sajjad Kachuee and Mohammad Sharifkhani},
  journal= {arXiv preprint arXiv:2509.01190},
  year   = {2025}
}
R2 v1 2026-07-01T05:14:47.295Z