Let customers deploy their models
Customers choose a supported model and deploy it on your infrastructure, with configuration managed through Aventail™ Control.
Get your customers up and running.
An inference engine and orchestrator in one, built for data centres and compute providers. Let customers deploy supported models, connect applications and route requests to your capacity, without assembling a serving stack.
Model serving and orchestration. One system.
Aventail™ Link Server runs inference on your compute. Model serving, deployment, endpoints, routing and central management work together, so your team can operate the service from one system.
CustomerApplication or Aventail™ Link-equipped device
Aventail™ Control · configuration and management
Your inference serviceAventail™ Link Server runtimeSupported model · inference endpoint
Install the Aventail™ Link Server runtime.
Run Aventail™ Link Server on supported provider infrastructure, then enrol it in Aventail™ Control for model deployment and configuration.
From model choice to first request.
Give customers a clear path to deploy a model, connect an application and start sending requests. They don’t need to be MLOps specialists to get started.
Connect the applications they use
Customers can call the model endpoint directly or route requests from other machines running Aventail™ Link.
See how your service is being used
Review machines, models and routing events in Aventail™ Control, with Aventail™ support for deployment and operation.
Central management. Direct inference.
Aventail™ Control distributes models, policies and configuration to Aventail™ Link Server, then receives device and routing events. Inference requests reach the runtime directly. Providers continue to operate their infrastructure, with Aventail™ support agreed for the deployment.
Give customers more ways to use your capacity.
Accept requests directly from applications or from other machines running Aventail™ Link. Your inference endpoints can become approved destinations alongside a customer’s own devices, servers, private cloud and frontier APIs, under their routing policies.
Customer deviceAVENTAIL™ LINK RUNTIME
On-premises machineAVENTAIL™ LINK RUNTIME
Private-cloud machineAVENTAIL™ LINK RUNTIME
Your inference endpointAVENTAIL™ LINK SERVER
Frontier APICUSTOMER’S PROVIDER ACCOUNT
Practical provider questions.
What does Aventail™ Server provide?
Aventail™ Server combines an inference engine and orchestrator in one: the Aventail™ Link Server runtime, model deployment, endpoints, policy routing and central management, supported by the Aventail™ team. Aventail™ Link Server executes models; Aventail™ Control manages configuration and activity outside the inference request path.
Do customers need deep MLOps expertise?
The experience is designed to help customers deploy, configure and route supported models without being MLOps specialists. Providers still operate their infrastructure, with Aventail™ support agreed for the deployment.
How does it fit our current serving setup?
We’ll review your current serving setup, supported models and customer workflows, then map how Aventail™ Link Server, deployment, endpoints and routing fit the service you want to offer.
Which hardware and models are supported?
Hardware and model scope is discussed with the Aventail™ team for the provider’s infrastructure and intended customer workflows.
How does a pilot begin?
Start by reviewing provider hardware, a representative model and the customer experience required from deployment through routing and support.
Build your inference service on Aventail™.
Bring your serving setup, model requirements and a customer workload. We’ll map deployment, endpoints, routing and operational support.
Choose a time with our team.