Stars
DeepSeek Harness: Everything is a Plugin.
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
Run DeepSeek-V4-Flash on SM89 (Ada / RTX 4090) with vLLM — patch over PR #41834. Validated on 4x RTX 4090.
An Agentic Framework for Reflective PowerPoint Generation
The official implementation of GTCRN, an ultra-lightweight SE model.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Flash OS images to SD cards & USB drives, safely and easily.
Find the password of protected ZIP files.
World's fastest and most advanced password recovery utility
mlpack: a fast, header-only C++ machine learning library
A toolkit for making real world machine learning and data analysis applications in C++
Robust Speech Recognition via Large-Scale Weak Supervision
Mirror of the PulseAudio sound server (for bug reports and pull requests go to the website!)
Official repository for the Microsoft C/C++ extension for VS Code.
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
A general-purpose encoder-decoder framework for Tensorflow
A family of open-sourced Mixture-of-Experts (MoE) Large Language Models
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
SGLang is a high-performance serving framework for large language models and multimodal models.
Data manipulation and transformation for audio signal processing, powered by PyTorch
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast, portable, simple, and free C/C++ IDE