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 7k 387

  2. llm-awq Public

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

    Python 3.2k 269

  3. efficientvit Public

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

    Python 3k 230

  4. bevfusion Public archive

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

    Python 2.7k 492

  5. temporal-shift-module Public

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

    Python 2.1k 421

  6. once-for-all Public

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

    Python 1.9k 344

Repositories

Showing 10 of 59 repositories
  • radial-attention Public

    Radial Attention Official Implementation

    Python 479 Apache-2.0 23 12 0 Updated Aug 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.

    Jupyter Notebook 1,523 MIT 228 61 (4 issues need help) 9 Updated Aug 4, 2025
  • llm-awq Public

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

    Python 3,203 MIT 269 162 10 Updated Jul 17, 2025
  • lpd Public

    Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation

    Python 66 MIT 5 1 0 Updated Jul 14, 2025
  • Quest Public

    [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

    Cuda 321 MIT 35 3 0 Updated Jul 10, 2025
  • x-attention Public

    [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring

    Python 217 11 4 0 Updated Jul 7, 2025
  • vila-u Public

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

    Python 378 MIT 12 19 0 Updated Apr 26, 2025
  • efficientvit Public

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

    Python 3,039 Apache-2.0 230 107 0 Updated Apr 24, 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++ 733 Apache-2.0 50 41 4 Updated Mar 6, 2025
  • torchsparse Public

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

    Cuda 1,386 MIT 173 44 3 Updated Feb 24, 2025