Stars
SGLang is a fast serving framework for large language models and vision language models.
Super-fast/easy runtime validators and serializers via transformation
DSPy: The framework for programming—not prompting—language models
An extremely fast Python type checker and language server, written in Rust.
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
An open protocol enabling communication and interoperability between opaque agentic applications.
🔎 Open source distributed and RESTful search engine.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A Datacenter Scale Distributed Inference Serving Framework
A framework for few-shot evaluation of language models.
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
Python toolkit for building graph-enhanced GenAI applications
📚 Parameterize, execute, and analyze notebooks
PostgreSQL database anonymization and synthetic data generation tool
High accuracy RAG for answering questions from scientific documents with citations
data load tool (dlt) is an open source Python library that makes data loading easy 🛠️
A high-throughput and memory-efficient inference and serving engine for LLMs
Cloud replacement for vacuum robots enabling local-only operation
Composable building blocks to build Llama Apps
High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.
A modular graph-based Retrieval-Augmented Generation (RAG) system
DuckDB-powered Postgres for high performance apps & analytics.