Implementation of "Overcoming catastrophic forgetting in neural networks" in Tensorflow

OpenCV wrapper for .NET

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

A unified framework for privacy-preserving data analysis and machine learning

SmolDocling OCR App built using SmolDocling 256M Model and Streamlit.

SGLang is a fast serving framework for large language models and vision language models.

Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown

An rv32i inspired ISA, SIMT GPU implementation in system-verilog.

OpenOCR: A general OCR system with accuracy and efficiency. Supporting 24 Scene Text Recognition methods trained from scratch on large-scale real datasets, and will continue to add the latest methods.

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

SoTA LLM for converting natural language questions to SQL queries

A text extraction library supporting PDFs, images, office documents and more

Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition

Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Declarative ThreeJS using Vue Components

SamWaf开源轻量级网站防火墙，完全私有化部署 SamWaf is a lightweight, open-source web application firewall for small companies, studios, and personal websites. It supports fully private deployment, encrypts data store…

wxPython's Project Phoenix. A new implementation of wxPython, better, stronger, faster than he was before.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Best Practices on Recommendation Systems

Privacy-Preserving Computing Platform 由密码学专家团队打造的开源隐私计算平台，支持多方安全计算、联邦学习、隐私求交、匿踪查询等。

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A minimal GPU design in Verilog to learn how GPUs work from the ground up

PyTorch video decoding