Application
Inference & Serving
OpenLLM
1Run 2open 3LLMs 4as 5OpenAI-compatible 6APIs
the six Ws · specification
W1
Who
Maintained by BentoML.
W2
What
Runs open LLMs as OpenAI-compatible API endpoints.
W3
Where
Self-hosted on your own GPUs or cloud.
W4
When
When you want a drop-in open-model API.
W5
Why
Serve and fine-tune many models with one command.
W6
With
GPUs, model weights, and Python.
W7
Watch
Company-maintained; open-source (Apache-2.0), self-hostable. Runs on your hardware; models and traffic stay local.
alternatives