Resources
Guides, benchmarks,
and the blog.
Documentation, deployment guides and the writing behind Xinference. Everything you need to move from evaluation to production.
From the blog
Notes from the team shipping it.
Engineering write-ups, product releases and hands-on lessons from the team running inference in production.
Perspectives
Control is the moat, not model performance.
The interesting question is no longer which model is best. It’s what happens when something goes wrong.
Chris Qin, Founder & CEO7 min read
Read the post 
Product
Xinference brand refresh and platform update.
Perspectives
When RAG isn’t enough: a field guide to fine-tuning.
Browse all postsNew posts and release notes land in the newsletter box below.
Resource library
Go deeper, at your own pace.
Guides, benchmarks and tutorials for every stage of evaluation and rollout.
Guides
Deployment guides for cloud, on-prem and hybrid environments. Install to first working endpoint, step by step.
Read the guides
Benchmarks & Research
Performance data and technical deep-dives on paged-KV cache, quantization and multi-engine batching.
See the numbers
Tutorials
Hands-on walkthroughs. Go from a laptop test to a running, production-grade deployment.
Start a tutorial
Docs
Architecture, API reference and the full deployment and security documentation.
Browse the docs
Events
Find us in the wild.
We show up where inference and infrastructure teams meet. Talks and briefings are posted here once they’re confirmed.
Nothing on the calendar right now.Talk to an engineer
Trust Center
Compliance & security.
What you'll need for a security review.
RBAC + audit
Role-based access control and a full audit log on every request.
Private deployment
Self-managed install on your own hardware.
Data residency
Deploy in AU or SG: your own cloud or on-prem, your choice.
Vulnerability policy
[email protected] · responsible disclosure, reviewed promptly.
Ready?
Read the docs,
then talk to an engineer.
Guides, benchmarks and hands-on support for every stage of evaluation.