Pinned Loading

1. mit-han-lab/nunchaku mit-han-lab/nunchaku Public

   [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

   Cuda 1k 67

2. mit-han-lab/omniserve mit-han-lab/omniserve Public

   [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

   C++ 613 40

3. mit-han-lab/deepcompressor mit-han-lab/deepcompressor Public

   Model Compression Toolbox for Large Language Models and Diffusion Models

   Python 388 32

4. mit-han-lab/pvcnn mit-han-lab/pvcnn Public archive

   [NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning

   Python 652 130

5. deep-gradient-compression deep-gradient-compression Public

   [ICLR 2018] Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

   Python 217 45

6. nn-compression nn-compression Public

   A Pytorch implementation of Neural Network Compression (pruning, deep compression, channel pruning)

   Python 155 25