Product Overview
Qwak Serving allows deployment of scalable models to production with one click, which reduces the friction between data science and engineers.
Qwak Serving enables teams to deliver prediction services in a fast, repeatable, and scalable way—including advanced metrics, logging, and alerting capabilities.
Qwak Serving enables teams to deliver prediction services in a fast, repeatable, and scalable way—including advanced metrics, logging, and alerting capabilities.
The Main Pillars
One click deployment
Easily deploy models using UI, CLI, or Qwak SDK
Auto scaling
Automatically scales deployed models based on predefined metrics.
Observability
Track your models’ metrics, logs, and performance in one place
Getting Started
Deploy a Qwak build using any of the mentioned modes using Qwak CLI, management application, or Python SDK.
Get started
Qwak Serving Use Cases
Batch inference
Deploy your models as batch inference jobs if you need to take advantage of scalable compute resources to generate many predictions at once.
Realtime inference
Deploy your models as real-time endpoints to generate predictions on a single observation at run time.
Streaming inference
Deploy your model as a streaming application if you need to trigger your models in an asynchronous way or on an existing stream of data.
