andyrull / width-and-Depth-pruning-for-Vision-Transformer

Related projects: ⓘ

• VITA-Group / SViTE
  [NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang…
  ☆90Updated 9 months ago
• MingSun-Tse / Why-the-State-of-Pruning-so-Confusing
  [Preprint] Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Prunin…
  ☆40Updated last year
• hikvision-research / SAViT
  ☆9Updated 11 months ago
• VITA-Group / UVC
  [ICLR 2022] "Unified Vision Transformer Compression" by Shixing Yu*, Tianlong Chen*, Jiayi Shen, Huan Yuan, Jianchao Tan, Sen Yang, Ji Li…
  ☆45Updated 9 months ago
• PeiyanFlying / SPViT
  ☆39Updated 3 weeks ago
• megvii-research / TPS-CVPR2023
  ☆40Updated last year
• GATECH-EIC / ShiftAddViT
  [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
  ☆29Updated 9 months ago
• liuzechun / Data-Free-NAS
  Data-Free Neural Architecture Search via Recursive Label Calibration. ECCV 2022.
  ☆32Updated 2 years ago
• YanjingLi0202 / Q-ViT
  The official implementation of the NeurIPS 2022 paper Q-ViT.
  ☆77Updated last year
• MingSun-Tse / TPP
  [ICLR'23] Trainability Preserving Neural Pruning (PyTorch)
  ☆29Updated last year
• szq0214 / S2-BNN
  S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)
  ☆63Updated 3 years ago
• YifanXu74 / Evo-ViT
  Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
  ☆69Updated 2 years ago
• ModelTC / QLLM
  [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…
  ☆33Updated 6 months ago
• facebookresearch / DepthShrinker
  [ICML 2022] "DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks", by Yonggan …
  ☆69Updated 2 years ago
• Daner-Wang / VTC-LFC
  ☆23Updated last year
• bychen515 / GLiT
  ☆23Updated 2 years ago
• ziplab / QTool
  Collections of model quantization algorithms. Any issues, please contact Peng Chen (blueardour@gmail.com)
  ☆68Updated 2 years ago
• VITA-Group / M3ViT
  [NeurIPS 2022] “M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design”, Hanxue …
  ☆90Updated last year
• chenbong / PSS-Net
  ☆16Updated 2 years ago
• OSVAI / NORM
  The official project website of "NORM: Knowledge Distillation via N-to-One Representation Matching" (The paper of NORM is published in IC…
  ☆19Updated last year
• ThisisBillhe / torch_quantizer
  torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.
  ☆17Updated 5 months ago
• selkerdawy / FTWT
  Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction
  ☆9Updated 2 years ago
• orashi / NSE_NAS
  Official PyTorch implementation of "Evolving Search Space for Neural Architecture Search"
  ☆10Updated 3 years ago
• NVlabs / SMCP
  ☆20Updated last year
• lliai / EMQ-series
  [ICCV-2023] EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization
  ☆27Updated 9 months ago
• OpenGVLab / DiffRate
  [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…
  ☆85Updated last year
• Yanqi-Chen / LATS
  To appear in the 11th International Conference on Learning Representations (ICLR 2023).
  ☆16Updated last year
• ZiweiWangTHU / GMPQ
  This is the pytorch implementation for the paper: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation, which is…
  ☆24Updated 3 years ago
• lmbxmu / SuperViT
  Official Pytorch implementation of Super Vision Transformer (IJCV)
  ☆42Updated last year
• OpenGVLab / LLMPrune-BESA
  BESA is a differentiable weight pruning technique for large language models.
  ☆12Updated 6 months ago