Kubernetes release optimizer built for DevOps and MLOps teams.
Iter8 experiments make it simple to collect performance and business metrics for apps and ML models, assess, compare and validate multiple app/ML model versions, safely rollout winning version, and maximize business value in each release.
Experiment charts are specialized Helm charts that contain reusable experiment templates. Iter8 combines experiment charts with user supplied values to generate runnable experiment.yaml
files.
Iter8 hub is a specific location within in the Iter8 GitHub repo that hosts several pre-packaged and reusable charts. These charts enable to you to launch powerful release optimization experiments in seconds. Their usage is described in depth in various Iter8 tutorials.
-
Load testing with SLOs
Iter8 experiments can generate requests for HTTP and gRPC services, collect built-in latency and error-related metrics, and validate SLOs.
-
A/B(/n) testing
Grow your business with every release. Iter8 experiments can compare multiple versions based on business value and promote a winner.
-
Simple to use
Get started with Iter8 in seconds using pre-packaged experiment charts. Run Iter8 experiments locally, inside Kubernetes, or inside your CI/CD/GitOps pipelines.
-
K8s app/serverless/ML frameworks
Use with any app, serverless, or ML framework. Iter8 works with Kubernetes deployments, statefulsets, Knative services, KServe/Seldon ML deployments, or custom Kubernetes resource types.
Install the latest stable release of the Iter8 CLI using brew
as follows.
brew tap iter8-tools/iter8
brew install iter8
You can also install Iter8 using:
- Load test an HTTP service and validate SLOs.
- Control the load characteristics during the HTTP load test experiment.
- Load test an HTTP POST endpoint with request payload.
- Learn more about built-in metrics and SLOs in an HTTP load test experiment.
- Load test a Knative HTTP service.
Iter8 documentation is available at https://iter8.tools.
Iter8 is primarily written in go
and builds on a few awesome open source projects including:
See here for information about ways to contribute, Iter8 community meetings, finding an issue, asking for help, pull-request lifecycle, and more.