model-quantization-paper

reading list for quantization

CV

PTQ(post training quantization for transformer)

• (NeurIPS2021) Post-Training Quantization for Vision Transformer
• (IJCAI2022) FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
• (ECCV2022) PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization
• (ACM MM2022) Towards Accurate Post-Training Quantization for Vision Transformer
• (ICASSAP2023) TSPTQ-ViT: TWO-SCALED POST-TRAINING QUANTIZATION FOR VISION TRANSFORMER

PTQ for CNN

• (ICML2020) Up or Down? Adaptive Rounding for Post-Training Quantization
• (ICLR 2021) BRECQ: PUSHING THE LIMIT OF POST-TRAINING QUANTIZATION BY BLOCK RECONSTRUCTION

QAT

• (NeurIPS2022) Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer
• Q-ViT: Fully Differentiable Quantization for Vision Transformer
• (TPAMI2023) Quantformer: Learning Extremely Low-Precision Vision Transformers
• (AAAI2023) Quantized Feature Distillation for Network Quantization
• (ICCV2023) I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference

Data free quantization

• (ECCV2022) Patch Similarity Aware Data-Free Quantization for Vision Transformers
• (IEEE Transactions on Neural Networks and Learning Systems) PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers

LLM