Discover mit-han-lab/sparsevit Open Source project

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

6,530

bevfusion

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

2,286

temporal-shift-module

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

2,060

once-for-all

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

1,866

llm-awq

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

1,687

proxylessnas

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.

1,420

torchquantum

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

1,304

data-efficient-gans

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

1,277

efficientvit

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

1,218

torchsparse

Cuda

1,181

smoothquant

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

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

1,175

gan-compression

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

1,104

anycost-gan

tinyml

TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library

[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

730

tinyengine

717

fastcomposer

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

[NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning

644

pvcnn

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

639

lite-transformer

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

589

spvnas

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

577

distrifuser

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

538

mcunet

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

460

tiny-training

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

432

amc

[NeurIPS 2019] Deep Leakage From Gradients

428

dlg

[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision

400

haq

Offsite-Tuning: Transfer Learning without Full Model

368

offsite-tuning

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

365

hardware-aware-transformers

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

321

litepose

[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration

304

inter-operator-scheduler

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

191

amc-models

[CVPR 2020] APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

166

apq

156

parallel-computing-tutorial

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

134

flatformer

Patch convolution to avoid large GPU memory usage of Conv2D

119

patch_conv

6s965-fall2022

Binary Neural Network on IceStick FPGA.

bnn-icestick

Efficient 3D Deep Learning

e3d

neurips-micronet

[JMLR'20] NeurIPS 2019 MicroNet Challenge Efficient Language Modeling, Champion

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

spatten-llm

Scala

tinychat-tutorial

[ICCAD'22 TinyML Contest] Efficient Heart Stroke Detection on Low-cost Microcontrollers

pruning-sparsity-publications

iccad-tinyml-open

calo-cluster

ml-blood-pressure

gan-compression-dynamic

data-efficient-gans-dynamic