pavansreddy/llmserver
A bash script that runs local LLMs on Linux with llama.cpp, vLLM or Ollama. It plans GPU memory, checks models for security, benchmarks, runs engines in a sandbox, and adds a gateway and an Open WebUI chat with hybrid RAG and private SearXNG web search. No Docker, no sudo.
GitHub repository with 18 stars and 1 forks.
Language: Shell