FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks
Abstract
Neural networks commonly execute on hardware accelerators such as NPUs and GPUs for their size and computation overhead. These accelerators are costly and it is hard to scale their resources to handle real-time workload fluctuations.
Fields of Study & Subjects
Advanced Neural Network Applications
Adversarial Robustness in Machine Learning
Big Data and Digital Economy
Publication details
- Pages
- 1298–1313
- Publication date
- 24 April 2026
- Language
- EN