Skip to content
@mit-han-lab

MIT HAN Lab

Efficient AI Computing. PI: Song Han

Pinned Loading

  1. streaming-llm Public

    [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

    Python 6.8k 378

  2. llm-awq Public

    [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

    Python 2.9k 238

  3. efficientvit Public

    Efficient vision foundation models for high-resolution generation and perception.

    Python 2.7k 216

  4. bevfusion Public archive

    [ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

    Python 2.5k 450

  5. temporal-shift-module Public

    [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

    Python 2.1k 419

  6. once-for-all Public

    [ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

    Python 1.9k 342

Repositories

Showing 10 of 60 repositories
  • nunchaku Public

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

    Cuda 1,011 Apache-2.0 67 85 (5 issues need help) 1 Updated Mar 21, 2025
  • x-attention Public

    XAttention: Block Sparse Attention with Antidiagonal Scoring

    Python 80 1 0 0 Updated Mar 21, 2025
  • Python 61 Apache-2.0 1 7 0 Updated Mar 20, 2025
  • llm-awq Public

    [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

    Python 2,866 MIT 238 152 8 Updated Mar 18, 2025
  • 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++ 612 Apache-2.0 40 37 5 Updated Mar 6, 2025
  • torchsparse Public

    [MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

    Cuda 1,287 MIT 150 33 2 Updated Feb 24, 2025
  • torchquantum Public

    A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum computers.

    Jupyter Notebook 1,425 MIT 213 61 (4 issues need help) 9 Updated Feb 21, 2025
  • VisCompare Public

    A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders

    Python 21 Apache-2.0 2 0 0 Updated Feb 21, 2025
  • deepcompressor Public

    Model Compression Toolbox for Large Language Models and Diffusion Models

    Python 388 Apache-2.0 32 40 1 Updated Feb 21, 2025
  • Block-Sparse-Attention Public

    A sparse attention kernel supporting mix sparse patterns

    C++ 165 BSD-3-Clause 5 6 0 Updated Feb 13, 2025