The outcome

Keep a multi-user cluster isolated, observable, recoverable, and resistant to first-run takeover or privilege expansion.

Xinference is a Open-source platform for launching and serving language, embedding, reranking, image, audio, video, and custom models locally or in distributed clusters. Running and managing multiple open or custom model types behind local or cluster APIs with model lifecycle, resource, authentication, permission, audit, and monitoring controls. This guide narrows that broad capability into one repeatable outcome, with checkpoints that keep the source material and your judgment in the loop.

Before you begin

Set the boundary before the tool starts.

Choose one real task, identify who will use the result, and decide what evidence or test will make the result acceptable. Gather only the source material needed for that task. If the work contains confidential, personal, regulated, or client-owned information, confirm that the platform and account are approved before sharing it.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

Step by step

A workflow you can repeat.

  1. 01

    Define cluster topology, trusted networks, user groups, OIDC or local identity, permission matrix, model sources, cache and virtual-environment policy, secrets, audit retention, SLO, and backup ownership.

  2. 02

    Initialize authentication on a private endpoint, provide every API process consistent JWT, encryption and database state, restrict supervisor and worker traffic, and separate admin, operator and consumer roles.

  3. 03

    Allowlist model sources and engines, scan custom environments, protect caches and logs, cap actor recovery, replicas and resources, and expose public inference only through authenticated TLS ingress.

  4. 04

    Test first-run race prevention, login and key expiry, privilege boundaries, OIDC failure, worker loss, actor crash loops, cache corruption, malicious model files, network partition, and restore.

  5. 05

    Canary version and auth migrations, back up and restore auth state, rotate secrets coherently, audit users and keys, remove deprecated scopes, and verify retired nodes and caches are inaccessible.

Working standard

What good use looks like.

  • Complete admin setup before exposure.
  • Share consistent auth state across API processes.
  • Cap crash recovery loops.

Xinference 3.0 replaced the legacy auth system with database-backed authentication enabled by default. The first unauthenticated setup call wins, so initialize before exposure; disabling authentication makes every endpoint public. Persist the JWT secret, API-key encryption key, and auth database consistently across API processes. Separate model-read, model-write, registration, log, cache, key, and user permissions; isolate supervisor and worker traffic, vet custom model code, protect logs and monitoring, cap actor recovery, and test migration and restore.

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this collection.