Starts an OpenAI-compatible vLLM server from that run’s export and prints its endpoint and
token. Then open the console’s Playground page and chat.
A Playground Session is for a person to try a model. For application traffic, use a
Model Deployment instead.
Start one
--gpus is the tensor-parallel size.Go to Playground, pick a model from the artifact dropdown or type a hub id, choose a GPU
count, and start. The page shows status, remaining TTL and an extend button.
Manage it
A session holds real GPUs and counts against your quota. It has an idle TTL, set by the
deployment, and stops on its own when that expires. That is the protection against starting one
and forgetting it, not a fault. Extend it if you still need it.
Compare two models side by side
The Playground sends one prompt to two services at once, which is the fastest way to see what an
alignment stage actually changed. Start two sessions — the SFT artifact and the GRPO artifact —
and pick both in the A/B selector.
Chat controls are temperature, max tokens and a system prompt. The endpoints are
OpenAI-compatible, so anything that speaks that API can use them:
Which backends can serve
Check it worked
tp serve ls shows the session with an endpoint and a TTL. If it stays pending, the weights are
still loading — a 9B model takes a minute or two on a cold cache.
The Playground is a premium feature an administrator enables per role or user. When it is not
enabled, the page explains that rather than erroring.
Next
Model deployments for application traffic ·
Model registry · The Playground page 
