mgonzs13/llama_ros
llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2
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.
Stars
245
Forks
43
Language
C++
License
MIT
Category
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.
Related models
muxi-ai/onellm
Unified interface for interacting with various LLMs hundreds of models, caching, fallback...
Atome-FE/llama-node
Believe in AI democratization. llama for nodejs backed by llama-rs, llama.cpp and rwkv.cpp, work...
docusealco/rllama
Ruby FFI bindings for llama.cpp to run open-source LLMs such as GPT-OSS, Qwen 3, Gemma 3, and...
Rin313/StegLLM
离线的LLM文本隐写程序。Offline LLM text steganography program.