llama-cpp-python
Python bindings for llama.cpp with OpenAI-compatible API server.
About
llama-cpp-python provides Python bindings for Georgi Gerganov's llama.cpp inference library, making local LLM inference available from Python with a simple pip install that builds llama.cpp from source. It includes an OpenAI-compatible API server, function-calling support, and GPU acceleration options, and exposes both low-level and high-level interfaces. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- LLM Inference & Serving
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- MIT
- Added
- Apr 3, 2026
Related Tools
Port of Meta's LLaMA model in C/C++ for efficient CPU inference
High-throughput LLM serving engine with PagedAttention
Minimalist ML framework in Rust by Hugging Face for fast inference.
Optimized inference library for running quantized LLMs on consumer GPUs.
Open-source ChatGPT alternative that runs 100% offline on your computer.
Fast LLM inference on consumer GPUs using neuron-aware sparse computation.