English

SpeedLimit: Neural Architecture Search for Quantized Transformer Models

Machine Learning 2023-10-16 v3

Abstract

While research in the field of transformer models has primarily focused on enhancing performance metrics such as accuracy and perplexity, practical applications in industry often necessitate a rigorous consideration of inference latency constraints. Addressing this challenge, we introduce SpeedLimit, a novel Neural Architecture Search (NAS) technique that optimizes accuracy whilst adhering to an upper-bound latency constraint. Our method incorporates 8-bit integer quantization in the search process to outperform the current state-of-the-art technique. Our results underline the feasibility and efficacy of seeking an optimal balance between performance and latency, providing new avenues for deploying state-of-the-art transformer models in latency-sensitive environments.

Keywords

Cite

@article{arxiv.2209.12127,
  title  = {SpeedLimit: Neural Architecture Search for Quantized Transformer Models},
  author = {Yuji Chai and Luke Bailey and Yunho Jin and Matthew Karle and Glenn G. Ko and David Brooks and Gu-Yeon Wei and H. T. Kung},
  journal= {arXiv preprint arXiv:2209.12127},
  year   = {2023}
}
R2 v1 2026-06-28T02:02:08.837Z