CLI11 is a command line parser for C++11 and beyond that provides a rich feature set with a simple and intuitive interface.

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

The gflags package contains a C++ library that implements commandline flags processing. It includes built-in support for standard types such as string and the ability to define flags in the source …

llm-export can export llm model to onnx.

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

Ongoing research training transformer models at scale

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)

Resources for Multiple Object Tracking (MOT)

FastTracker: Real-Time and Accurate Visual Tracking

VisioFirm: Cross-Platform AI-assisted Annotation Tool for Computer Vision

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…

We write your reusable computer vision tools. 💜

《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

Reference PyTorch implementation and models for DINOv3

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Wan: Open and Advanced Large-Scale Video Generative Models

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOv5, YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv8. MNN, NCNN, TNN, ONNXRuntime.

Accessible large language models via k-bit quantization for PyTorch.

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

《动手学大模型Dive into LLMs》系列编程实践教程

A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment…