Skip to content
@mit-han-lab

MIT HAN Lab

Efficient AI Computing. PI: Song Han

Pinned Loading

  1. streaming-llm streaming-llm Public

    [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

    Python 6.9k 385

  2. llm-awq llm-awq Public

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

    Python 3.1k 254

  3. efficientvit efficientvit Public

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

    Python 2.9k 226

  4. bevfusion bevfusion Public archive

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

    Python 2.6k 476

  5. temporal-shift-module temporal-shift-module Public

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

    Python 2.1k 420

  6. once-for-all 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

    mit-han-lab/nunchaku’s past year of commit activity
    Python 1,996 Apache-2.0 103 46 6 Updated Jun 10, 2025
  • ComfyUI-nunchaku Public

    ComfyUI plugin of Nunchaku

    mit-han-lab/ComfyUI-nunchaku’s past year of commit activity
    Python 1,222 Apache-2.0 35 38 1 Updated Jun 8, 2025
  • x-attention Public

    XAttention: Block Sparse Attention with Antidiagonal Scoring

    mit-han-lab/x-attention’s past year of commit activity
    Python 163 8 2 0 Updated Jun 6, 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.

    mit-han-lab/torchquantum’s past year of commit activity
    Jupyter Notebook 1,484 MIT 222 61 (4 issues need help) 9 Updated May 28, 2025
  • llm-awq Public

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

    mit-han-lab/llm-awq’s past year of commit activity
    Python 3,066 MIT 254 156 12 Updated May 9, 2025
  • vila-u Public

    [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

    mit-han-lab/vila-u’s past year of commit activity
    Python 341 MIT 11 17 0 Updated Apr 25, 2025
  • efficientvit Public

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

    mit-han-lab/efficientvit’s past year of commit activity
    Python 2,907 Apache-2.0 226 105 0 Updated Apr 24, 2025
  • deepcompressor Public

    Model Compression Toolbox for Large Language Models and Diffusion Models

    mit-han-lab/deepcompressor’s past year of commit activity
    Python 493 Apache-2.0 37 52 2 Updated Mar 27, 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

    mit-han-lab/omniserve’s past year of commit activity
    C++ 694 Apache-2.0 44 41 4 Updated Mar 6, 2025
  • torchsparse Public

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

    mit-han-lab/torchsparse’s past year of commit activity
    Cuda 1,356 MIT 169 40 3 Updated Feb 24, 2025