A high-throughput and memory-efficient inference and serving engine for LLMs

Renderer for the harmony response format to be used with gpt-oss

Common recipes to run vLLM

Composable building blocks to build Llama Apps

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Python library for Synthetic Data Generation

Agentic components of the Llama Stack APIs

Python SDK for Llama Stack

GitHub Organization management via Peribolos

Ops files for https//github.com/meta-llama/llama-stack

Functional tests and benchmarks for verifying Llama model providers.

Get your documents ready for gen AI

Command-line interface. Use this to chat with the model or train the model (training consumes the taxonomy data)