Skip to content
UMKIMDocs
Search limited to 0.1.0. Switch to the latest version for up-to-date results.

fleet-llm

This content is for 0.1.0. Switch to the latest version for up-to-date documentation.

FleetLLM can enable an optional LiteLLM proxy on the hub. It is disabled unless configured and is experimental in v0.1.0.

The feature combines a FleetLLM resource, console-auth proxying, and operator-configured inference backends. GPU workload preparation and backend availability are separate concerns.

Do not expose the proxy without an independent authentication and network review. v0.1.0 does not provide a supported inference service, token-metering guarantee, availability commitment, or production security claim.