DUCKQUANT / THE QUANT & AI DIRECTORY
4,091 resources, ranked by in-directory PageRank
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
[ICML'21 Oral] I-BERT: Integer-only BERT Quantization
[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
[ECCV 2022] Patch Similarity Aware Data-Free Quantization for Vision Transformers
The official implementation of the NeurIPS 2022 paper Q-ViT.
The official implementation of the ICML 2023 paper OFQ-ViT
[ICCV 2023] RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
[ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.
Public repository by LiuXiaoxuanPKU. Primary language: Python.
[ICML 2022 Spotlight] Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
Public repository by SamsungLabs. Primary language: Python.
Public repository by bytedance. Primary language: Python.
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
How Do Adam and Training Strategies Help BNNs Optimization? In ICML 2021.
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
The official PyTorch implementation of the ICLR2022 paper, QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization
Information Bottleneck in Neural Networks
Pytorch implementation of RAPQ, IJCAI 2022
Official implementation for ECCV 2022 paper LIMPQ - "Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance"
BASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks, ECCV 2022
Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".
Pytorch implementation of our paper accepted by CVPR 2022 -- IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization (ICLR 2021)
Pytorch implementation of BRECQ, ICLR 2021
Identify a binary weight or binary weight and activation subnetwork within a randomly initialized network by only pruning and binarizing the network.
Code for High-Capacity Expert Binary Networks (ICLR 2021).
An official implementation of "Network Quantization with Element-wise Gradient Scaling" (CVPR 2021) in PyTorch.
Using ideas from product quantization for state-of-the-art neural network compression.
Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples [NeurIPS 2021]
