WebsiteSlack
Search…
0.22
Deploy machine learning models to production
Install
Tutorial
GitHub
Examples
Contact us
Deployments
Realtime API
Batch API
Advanced
Compute
Using GPUs
Using Inferentia
Python packages
System packages
Networking
Cluster management
Cluster configuration
AWS credentials
EC2 instances
Spot instances
Update
Uninstall
Miscellaneous
CLI commands
Python client
Environments
Architecture diagram
Security
Telemetry
Troubleshooting
API is stuck updating
404/503 API responses
NVIDIA runtime not found
TF session in predict()
Serving-side batching errors
Cluster down failures
Guides
Exporting models
Multi-model endpoints
View API metrics
Running in production
Low-cost clusters
Set up a custom domain
Set up VPC peering
SSH into worker instance
Single node deployment
Set up kubectl
Self-hosted Docker images
Docker Hub rate limiting
Private docker registry
Set up REST API Gateway
Install CLI on Windows
Contributing
Development
Powered By GitBook
AWS credentials
As of now, Cortex only runs locally or on AWS. We plan to support other cloud providers in the future. If you don't have an AWS account you can get started with one here.
Follow this tutorial to create an access key. Enable programmatic access for the IAM user, and attach the built-in AdministratorAccess policy to your IAM user. If you'd like to use less privileged credentials once the Cortex cluster has been created, see security.
Cluster management - Previous
Cluster configuration
Next - Cluster management
EC2 instances
Last modified 10mo ago
Copy link