#
Starred repositories
A high-throughput and memory-efficient inference and serving engine for LLMs
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
COLMAP - Structure-from-Motion and Multi-View Stereo
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
A GUI client for Windows, Linux and macOS, support Xray and sing-box and others
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
ncnn is a high-performance neural network inference framework optimized for the mobile platform
A generative world for general-purpose robotics & embodied AI learning.
🦜🔗 The platform for reliable agents.
SRS is a simple, high-efficiency, real-time media server supporting RTMP, WebRTC, HLS, HTTP-FLV, HTTP-TS, SRT, MPEG-DASH, and GB28181.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.
Supervisely SDK for Python - convenient way to automate, customize and extend Supervisely Platform for your computer vision task
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
A comprehensive and up-to-date compilation of datasets, tools, methods, review papers, and competitions for remote sensing change detection.
Simple, unified interface to multiple Generative AI providers
DC-SDK is based on the open source project Cesium for the second development of two three-dimensional WebGis application framework , the framework optimizes the use of Cesium and adds some addition…
SimpleAICV:pytorch training and testing examples.
Sample apps to demonstrate how to deploy models trained with TAO on DeepStream
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
A command line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images. 📷