LLM Serving Pack
Add LLM serving to your Nebari cluster so your team can run large language models behind a managed API. The pack handles model downloading, serving, routing, and per-model access control, with rate limiting and token counting included so usage stays accountable.
- Status: Official (OpenTeams)
- Maintainer: nebari-dev
- Source: nebari-dev/nebari-llm-serving-pack
For install and configuration, see the upstream README.