2 papers
cs.CV2024
ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
Yanfeng Jiang, Ning Sun, Xueshuo Xie +2
Vision Transformers (ViTs) have exhibited exceptional performance across diverse computer vision tasks, while their substantial parameter size incurs significantly increased memory…
cs.LG2024
DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization
Yanfeng Jiang, Zelan Yang, Bohua Chen +3
Large language models achieve exceptional performance on various downstream tasks through supervised fine-tuning. However, the diversity of downstream tasks and practical requireme…