11 citations · 11 across the 1 of their papers we have counts for
7 papers
A 28nm 0.22μJ/token memory-compute-intensity-aware CNN-Transformer accelerator with hybrid-attention-based layer-fusion and cascaded pruning for semantic-segmentation
Pingcheng Dong, Yonghao Tan, Xuejiao Liu +14
This work presents a 28nm 13.93mm2 CNN-Transformer accelerator for semantic segmentation, achieving 3.86-to-10.91x energy reduction over previous designs. It features a hybrid atte…
APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design
Yonghao Tan, Pingcheng Dong, Yongkun Wu +8
DNN accelerators, significantly advanced by model compression and specialized dataflow techniques, have marked considerable progress. However, the frequent access of high-precision…
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Dongting Hu, Jierun Chen, Xijie Huang +16
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…
Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
Xijie Huang, Zhiqiang Shen, Pingcheng Dong +1
Despite the outstanding performance of transformers in both language and vision tasks, the expanding computation and model size have increased the demand for efficient deployment.…
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
Xijie Huang, Zechun Liu, Shih-Yang Liu +1
Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the…
Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection
Xijie Huang, Zechun Liu, Shih-Yang Liu +1
Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-en…