Zhuang Intelligent Processing Lab

EcoFormer

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "EcoFormer: Energy-Saving Attention with Linear Complexity"

LIT

[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"

LITv2

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"

LongVLM

Mesa

This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

PTQD

The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models

QTool

Collections of model quantization algorithms. Any issues, please contact Peng Chen (blueardour@gmail.com)

SN-Net

[CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".

SPT

[ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.

SPViT

[TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

ziplab/LITv2

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"

ziplab/SN-Net

[CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".

ziplab/Mesa

This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

ziplab/SPViT

[TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.

ziplab/PTQD

The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models

ziplab/LIT

[AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"

ziplab/LongVLM

ziplab/EcoFormer

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "EcoFormer: Energy-Saving Attention with Linear Complexity"

ziplab/QTool

Collections of model quantization algorithms. Any issues, please contact Peng Chen (blueardour@gmail.com)

ziplab/SPT

[ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.

ziplab/FASeg

[CVPR 2023] This is the official PyTorch implementation for "Dynamic Focus-aware Positional Queries for Semantic Segmentation".

ziplab/SAQ

This is the official PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

ziplab/HVT

[ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"

ziplab/SN-Netv2

[ECCV 2024] This is the official implementation of "Stitched ViTs are Flexible Vision Backbones".

ziplab/MPVSS

ziplab/QLLM

[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"

ziplab/efficient-stable-diffusion

ziplab/Stitched_LLaMA

[CVPR 2024] A framework to fine-tune LLaMAs on instruction-following task and get many Stitched LLaMAs with customized number of parameters, e.g., Stitched LLaMA 8B, 9B, and 10B...

ziplab/STPT

ziplab/ZipAR

This is the official PyTorch implementation of "ZipAR: Accelerating Autoregressive Image Generation through Spatial Locality"

ziplab/mvsplat

🌊[arXiv'24] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

ziplab/One-shot-Human-Parsing

(AAAI 2021) Progressive One-shot Human Parsing