Powerful menu bar manager for macOS

[SIGIR'24] The official implementation code of MOELoRA.

This is a 3Dviewer for files like .obj .mtl

Latex code for making neural networks diagrams

PyTorch library for cost-effective, fast and easy serving of MoE models.

Code for the paper: Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions

A collection of AWESOME things about mixture-of-experts

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts

GPU operators for sparse tensor operations

Bamboo-7B Large Language Model

The official GitHub page for the survey paper "A Survey on Mixture of Experts".

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Miro[ACM MobiCom '23] Cost-effective On-device Continual Learning over Memory Hierarchy with Miro

A MoE impl for PyTorch, [ATC'23] SmartMoE

ICLR 2024 论文和开源项目合集

PyTorch implementation for HyperMixing, a linear-time token-mixing technique used in HyperMixer architecture

PyTorch reimplementation of the paper "HyperMixer: An MLP-based Green AI Alternative to Transformers" [arXiv 2022].

[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

⏰ Collaboratively track deadlines of conferences recommended by CCF (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~

A pytorch adversarial library for attack and defense methods on images and graphs

Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Mora: More like Sora for Generalist Video Generation