MIT HAN Lab

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

bevfusion

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

llm-awq

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

temporal-shift-module

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

once-for-all

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

efficientvit

EfficientViT is a new family of vision models for efficient high-resolution vision.

data-efficient-gans

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

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.

gan-compression

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

smoothquant

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

anycost-gan

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

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

tinyml

fastcomposer

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

TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library

distrifuser

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

mcunet

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

amc

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

tiny-training

On-Device Training Under 256KB Memory [NeurIPS'22]

offsite-tuning

Offsite-Tuning: Transfer Learning without Full Model

qserve

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

litepose

[CVPR'22] Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

flatformer

[CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

lmquant

Quest

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

patch_conv

Patch convolution to avoid large GPU memory usage of Conv2D

sparsevit

[CVPR'23] SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

spatten-llm

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

tinychat-tutorial