All Tools
L
LLMFreeOpen Source
LLAMA-CPP-PYTHON
Python bindings and OpenAI-style API for llama.cpp
MIT
ABOUT
llama.cpp is a C++ runtime, so Python apps must shell out or rewrite bindings. llama-cpp-python exposes the C API plus chat completions, embeddings, and an OpenAI-compatible server so local GGUF models drop into existing Python LLM code.
INSTALL
pip install llama-cpp-pythonINTEGRATION GUIDE
1. Load a GGUF model in Python and run chat completions locally
2. Serve llama.cpp behind an OpenAI-compatible HTTP API
3. Call tools and JSON-mode completions from Python agents
4. Run multimodal GGUF models with image-aware chat handlers
TAGS
pythonllmllama-cppgguflocal-llmopenai-compatibleinference