Website

MIT HAN Lab

Efficient AI Computing. PI: Song Han

  • 17 active products

Consolidated Product Portfolio

  • Anycost GAN

    [CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

    Machine Learning Model TrainingOpen Source
  • Data Efficient Gans

    [NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

    Ai Image EditingOpen Source
  • FastComposer

    [IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

    Ai Image EditingOpen Source
  • GAN Compression

    [CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

    Compression OptimizationOpen Source
  • Hardware Aware Transformers

    [ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

    Ai TranslationOpen Source
  • LLM Awq

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

    Llm OrchestrationOpen Source
  • OmniServe

    [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

    Model DeploymentOpen Source
  • Once For All

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

    Model DeploymentOpen Source
  • ProxylessNAS

    [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

    Machine Learning Model TrainingOpen Source
  • Quest

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

    Model DeploymentOpen Source
  • Radial Attention

    [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

    Ai Video CreationOpen Source
  • SmoothQuant

    [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

    Llm OrchestrationOpen Source
  • SpAtten

    [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

    Model DeploymentOpen Source
  • Streaming LLM

    [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

    Llm OrchestrationOpen Source
  • Streaming Vlm

    StreamingVLM: Real-Time Understanding for Infinite Video Streams

    Video AnalyticsOpen Source
  • TinyChatEngine

    TinyChatEngine: On-Device LLM Inference Library

    Machine Learning Model TrainingOpen Source
  • TorchSparse

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

    Model DeploymentOpen Source

Company Profile & Strategy

Effizientes KI-Computing. PI: Song Han. Das MIT HAN Lab verwaltet 16 Open-Source-Projekte auf GitHub, darunter Streaming LLM, LLM Awq und Once For All. Primäre Sprachen: Python, Cuda, C++.

Open-Source Footprint

17 repositories25.8K stars

Save & manage the vendor's products in Productapp.

Save and manage this vendor's products in Productapp.

Start free trial