BoostAgent Skill
Submit projectSubmit

Xinference

xorbitsai / inference

An open-source model-serving platform for running language, embedding, speech and multimodal models through APIs on local or distributed machines.

View on GitHub

Save privately. Follow for reviewed updates in your SOTA inbox. Neither changes the ranking.

Your workspace

About Xinference

Applications need a common serving interface for several model types and inference engines.

Who it’s for

  • Teams self-hosting open models
  • Developers integrating speech, embeddings and multimodal inference

When to consider it

Consider Xinference when you want to launch and manage different model types behind a shared API while choosing your inference backend.

Tradeoffs & limitations

  • The community code is Apache-2.0 licensed. Engine platform restrictions still apply: vLLM is Linux-only and MLX requires Apple Silicon; Enterprise and hosted Model API offerings are separate.

SOTA overview · Documentation-based assessment · Sources & review method

Updates

No updates shared yet.

Discussion

Newest first

Ask a question or share how you use Xinference.

Keep it helpful. Community rules

Loading discussion…

Sources & review method

Documentation-based assessment · Oct 30, 2026 · Prepared with AI assistance; not a hands-on benchmark.

Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.

Editorial policy · Suggest a correction

Import history & original evidence

Xinference official repository

Scope: Product overview · Imported Oct 30, 2026 · Apache-2.0

An open-source model-serving platform for running language, embedding, speech and multimodal models through APIs on local or distributed machines.

Based on official pages and announcements checked on 2026-10-30. No hands-on test, performance benchmark or popularity ranking is claimed.