Starred repositories
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
"Vibe-Trading: Your Personal Trading Agent"
The backtesting engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.
A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.
Text-audio foundation model from Boson AI
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
Python WebUI with native Mac/Windows Apps for testing, comparing, and visualizing Search APIs (Querit, You, Tavily, Exa, Baidu, Brave, Parallel etc.).
这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy…
A TUI-based utility for real-time monitoring of InfiniBand traffic and performance metrics on the local node
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
A modern replacement for Redis and Memcached
Trainable fast and memory-efficient sparse attention
A Datacenter Scale Distributed Inference Serving Framework
A tool to configure, launch and manage your machine learning experiments.
Scalable toolkit for efficient model reinforcement
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Not a neutral survey — a field manual for engineers who build, train, and ship multimodal retrieval at production scale. The C-L-I triangle (Compression · Localization · Instruction), MLLM encoders…
Delivers efficient, stable, and secure data distribution and acceleration powered by P2P technology, with an optional content‑addressable filesystem that accelerates OCI container launch.
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL