.png){kind=icon}
返回
Autonomous Model Quantization Framework for Hybrid Vision Transformers Based on Reinforcement Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/tcad.2025.3641538.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing quantization approaches often suffer from significant accuracy degradation when compressing hybrid convolution and transformer models with low bit-width. This article presents RL-PTQv2, an extension of our previous RL-PTQ framework, which introduces a new reinforcement learning (RL)-based posttraining quantization (PTQ) method. RL-PTQv2 introduces two key advances: 1) hardware (HW)-aware PTQ (optional), where RL is guided by real latency and energy feedback from an in-loop PIM simulator, enabling deployable designs that jointly optimize accuracy, latency, and energy and 2) improved quantization techniques, supporting symmetric/asymmetric quantization and mixed adaptive rounding to better balance precision and efficiency. Across various hybrid vision transformer families, including MobileViTv1 and v2, EfficientFormerv1 and v2, and MobileFormer, RL-PTQv2 achieves state-of-the-art quantized accuracy compared to previous PTQ methods. Furthermore, our quantized model showed an improvement in energy efficiency of $10.1\times $ on TransPIM and $22.6\times $ on the Titan RTX GPU compared to the baseline model, specifically when deployed on HViT-PIM, a dedicated processing framework for efficiently executing MobileViT models. HViT-PIM was developed primarily to explore the potential of HW-aware PTQ. However, the RL-PTQv2 is not limited to processing-in-memory (PIM). It can also be seamlessly integrated with a variety of bit-serial accelerators, enabling automatic quantization tailored to the underlying HW.
Keyword:
Transformer accelerator
transformer optimization
vision transformer
期刊
I
IF:
2.9
论文数:
671
被引数:
9.6K
机构
引用论文
.png){kind=icon}
ADRL: An attention-based deep reinforcement learning framework for knowledge graph reasoningADRL: 一种基于注意力的深度强化学习知识图推理框架
PREAI
分享收藏分享收藏Mobile Transformer Accelerator Exploiting Various Line Sparsity and Tile-Based Dynamic Quantization
PREAI
分享收藏Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference用于有效的仅整数算术推理的神经网络的量化和训练
OAAI
OAAI分享收藏
查看更多内容