llmux

Run and manage vLLM and llama.cpp model servers from one terminal UI and CLI.

Desktopfreeglobal

llmux runs and manages both vLLM and llama.cpp model servers from one terminal UI and CLI, with shared Docker Compose profiles, live tokens-per-second stats and cross-backend port/GPU conflict checks. It's aimed at developers running both inference backends who want unified management instead of separate tooling for each.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of llmux - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim llmux to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether llmux (or something else) actually fits.

Try a problem