Pinned Loading

1. OpenGVLab/OmniQuant OpenGVLab/OmniQuant Public

   [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

   Python 743 56

2. OpenGVLab/EfficientQAT OpenGVLab/EfficientQAT Public

   EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

   Python 234 18

3. PrefixQuant PrefixQuant Public

   An algorithm for static activation quantization of LLMs

   Python 100 4

4. CF-ViT CF-ViT Public

   (AAAI 2023 Oral) Pytorch implementation of "CF-ViT: A General Coarse-to-Fine Method for Vision Transformer"

   Python 102 7

5. OpenGVLab/DiffRate OpenGVLab/DiffRate Public

   [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.

   Jupyter Notebook 90 8

6. SMMix SMMix Public

   [ICCV 23]This is a Pytorch implementation of our paper "SMMix: Self-Motivated Image Mixing for Vision Transformers"

   Python 16 1