Xinference Entperprise
Sold by: Xinference
Xinference is a fully capable inference service platform tailored to generative AI scenarios
Overview
Xinference is a fully capable inference service platform tailored to generative AI scenarios. By providing unified heterogeneous computing power inference services, full life cycle management of models, and enterprise-level management capabilities with observable operation and maintenance, we help customers quickly build AI applications and accelerate business innovation
Highlights
- Supports multiple engines
- Supports many of the latest models
- Covers a variety of heterogeneous GPUs
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 22.04
Pricing
Xinference Entperprise
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time. Alternatively, you can pay upfront for a contract, which typically covers your anticipated usage for the contract duration. Any usage beyond contract will incur additional usage-based costs.
Additional Amazon Web Services infrastructure costs may apply. Use the Amazon Web Services Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
g4dn.xlarge Recommended | CN¥1.28 |
g5.4xlarge | CN¥1.28 |
g5.2xlarge | CN¥1.28 |
p3.16xlarge | CN¥10.24 |
g4dn.metal | CN¥10.24 |
p3.8xlarge | CN¥5.12 |
g4dn.2xlarge | CN¥1.28 |
g4dn.16xlarge | CN¥1.28 |
g4dn.12xlarge | CN¥5.12 |
g5.8xlarge | CN¥1.28 |
Vendor refund policy
Returns are currently not supported, but can be cancelled at any time; please contact lipeng@xprobe.io
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. Amazon Web Services Marketplace China does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Usage information
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Xinference v0.16.0 was released. This press conference brought both enterprise and cloud version updates.
Community edition
Update guide
pip: pip install 'xinference ==0.16.0' Docker: Just pull the latest version, or use pip directly in the image to update
Additional details
Usage instructions
Linked to the operating system via ssh, the default username is ubuntu. First, start xinference with the following command: xinference-local --log-level debug -H 0.0.0.0 This will launch the system's 9997 web port. Access the web management interface via a browser: https://PublicIP:9997，即可使用xinference . For more usage, please refer to the official documentation: https://inference.readthedocs.io/zh-cn/latest/index.html
Resources
Vendor resources
Support
Vendor support
Technical support: lipeng@xprobe.io
Amazon Web Services infrastructure support
Amazon Web Services Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Customer reviews
Ratings and reviews
0 ratings
0 reviews
No customer reviews yet
Be the first to review this product .