mgonzs13/llama_ros

llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2

52
/ 100
Established

Supports speculative decoding for accelerated inference, real-time LoRA adapter switching, and GBNF grammar constraints for structured output generation. Provides ROS 2 service/action interfaces wrapping llama.cpp's C++ bindings, enabling both text and vision capabilities across ROS 2 distros (Humble through Rolling) with optional CUDA acceleration. Integrates with LangChain for RAG pipelines and offers CLI tools and launch files for straightforward deployment in robotics workflows.

245 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 20 / 25

How are scores calculated?

Stars

245

Forks

43

Language

C++

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mgonzs13/llama_ros"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.