Local and distributed model serving
How to use
Xinference.
Running and managing multiple open or custom model types behind local or cluster APIs with model lifecycle, resource, authentication, permission, audit, and monitoring controls.
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 covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to Xinference
Get into the official Xinference experience with the right account and a setup you understand.
- 01
Start at https://inference.readthedocs.io/ and confirm the domain before entering account or payment information.
- 02
Availability: Xinference runs as local or distributed Python and container services with a built-in web UI, command line, REST API, Python client, and OpenAI-compatible access.
- 03
A supported Python or container environment, compatible CPU or accelerator hardware, licensed models, sufficient storage and memory, protected networking, initialized authentication, persistent auth secrets and database, backups, monitoring, and update ownership.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful Xinference session
Learn the interaction loop using a small task with a clear outcome.
- 01
Define the users, model and license, modality, hardware, engine, context, quality, safety, throughput, network, storage, authentication, permissions, audit, availability, and cost requirements.
- 02
Install a pinned Xinference version, keep authentication enabled, initialize the first administrator before network exposure, persist and back up auth secrets and database, and create a read-only inference user or key.
- 03
Launch a pinned model revision with bounded resources and private access, then run representative evals and load tests across the native and intended compatible clients.
- 04
Review output quality, permissions, logs, failures, actor recovery, resource use, latency, and cost, then canary the model and runtime with tested rollback, key rotation, and restore procedures.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of Xinference output
Turn a promising generation into an asset you can legally and safely ship.
- 01
Restate the brief, the deliverable format, and where the asset will appear before judging any output.
- 02
Inspect at full resolution: generated media hides its errors at thumbnail size.
- 03
Check the details these systems reliably get wrong — hands, text, logos, reflections, symmetry, and edge artefacts.
- 04
Confirm the licence and commercial-use terms for your plan, and check the output does not reproduce a recognisable style, mark, or likeness you have no right to use.
- 05
Review for accessibility and delivery: alt text, contrast, colour profile, file size, and the exact export format.
- Inspect at full resolution before approving anything.
- Confirm commercial-use rights before an asset reaches a client.
- Keep the prompt and settings with the asset so it can be reproduced.
Privacy & permissions
Use Xinference safely
Use the platform without surrendering rights, likenesses, or client material you do not control.
- 01
Confirm you hold the rights to every reference image, voice, or clip before uploading it.
- 02
Check whether your plan trains on submitted content, and opt out before uploading client work.
- 03
Never upload a real person's likeness or voice without their explicit, documented consent.
- 04
Review the output for marks, styles, or likenesses you have no licence to reproduce.
- 05
Label synthetic media where your client, platform, or jurisdiction requires disclosure.
- 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.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use Xinference for the work it does best.
Each workflow is a separate guide with its own steps and review checkpoints.
Select and expose an exact model through a scoped identity, bounded resources, validated clients, and reproducible lifecycle controls.
↗ 02 WorkflowOperate a secure distributed Xinference clusterCoordinate supervisor, workers, authentication, OIDC, secrets, audit logs, model caches, monitoring, recovery, and upgrades as one controlled system.
↗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 guide.
- Xinference documentation ↗
- Xinference authentication ↗
- Xinference 3.0 migration ↗
- Xinference custom models ↗