Stars
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
Retrieval and Retrieval-augmented LLMs
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"
A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
A list of open-source, affordable, less-known, or visionary robotics projects.
Implementation of kuwahara filter in Python (numpy + OpenCV)
Integrate the DeepSeek API into popular softwares
DeepEP: an efficient expert-parallel communication library
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Wan: Open and Advanced Large-Scale Video Generative Models
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
OpenCV JavaScript version for node.js or browser
A client-side JavaScript implementation of Canny Edge Detection
Example of Canny edge detection algorithm in javascript
Friendly machine learning for the web! 🤖
Optimizes mesh and polygon colliders in Unity
An Open-Source Framework for Prompt-Learning.
SGLang is a fast serving framework for large language models and vision language models.
A high-throughput and memory-efficient inference and serving engine for LLMs
User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)
Fully open reproduction of DeepSeek-R1