A latent text-to-image diffusion model

Making large AI models cheaper, faster and more accessible

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

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

An Open Source Machine Learning Framework for Everyone

CUDA 算子手撕与面试指南

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…

Open Source Application for Advanced LLM + Diffusion Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

Merlin Models is a collection of deep learning recommender system model reference implementations

🤗 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.

A course on aligning smol models.

Train transformer language models with reinforcement learning.

Large Reasoning Models

Fully open reproduction of DeepSeek-R1

Code and documentation to train Stanford's Alpaca models, and generate the data.

Powerful AI Client

s1: Simple test-time scaling

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

Playwright MCP server

A collection of MCP servers.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

verl: Volcano Engine Reinforcement Learning for LLMs