MIT HAN Lab

bevfusion

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

efficientvit

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

llm-awq

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

once-for-all

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

proxylessnas

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

smoothquant

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

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

temporal-shift-module

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

torchquantum

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.

torchsparse

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

mit-han-lab/llm-awq

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

mit-han-lab/efficientvit

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

mit-han-lab/bevfusion

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

mit-han-lab/temporal-shift-module

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

mit-han-lab/torchquantum

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/smoothquant

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

mit-han-lab/proxylessnas

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

mit-han-lab/torchsparse

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

mit-han-lab/data-efficient-gans

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

mit-han-lab/nunchaku

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

mit-han-lab/tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

mit-han-lab/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

mit-han-lab/distrifuser

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

mit-han-lab/fastcomposer

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

mit-han-lab/hart

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

mit-han-lab/spvnas

[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

mit-han-lab/lite-transformer

[ICLR 2020] Lite Transformer with Long-Short Range Attention

mit-han-lab/duo-attention

[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

mit-han-lab/ComfyUI-nunchaku

mit-han-lab/deepcompressor

Model Compression Toolbox for Large Language Models and Diffusion Models

mit-han-lab/hardware-aware-transformers

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

mit-han-lab/Block-Sparse-Attention

A sparse attention kernel supporting mix sparse patterns

mit-han-lab/vila-u

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

mit-han-lab/Quest

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

mit-han-lab/x-attention

XAttention: Block Sparse Attention with Antidiagonal Scoring

mit-han-lab/spatten

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

mit-han-lab/patch_conv

Patch convolution to avoid large GPU memory usage of Conv2D

mit-han-lab/tinychat-tutorial

mit-han-lab/VisCompare

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

mit-han-lab/sparserefine

[ECCV 2024] SparseRefine: Sparse Refinement for Efficient High-Resolution Semantic Segmentation