SpeedLimit: Neural Architecture Search for Quantized Transformer Models
Yuji Chai, Luke Bailey, Yunho Jin, Matthew Karle, Glenn G. Ko, Brooks, David, Wei, Gu-Yeon, Kung, H. T. · arXiv (Cornell University) · 2022
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.