cortex
cortex copied to clipboard
cortexlabs
Production infrastructure for machine learning at scale
### Notes We currently use `gorilla/handlers` for CORS, which does not support `*` in their `handlers.AllowedHeaders()` function. Therefore, if the user sets a custom header in their request, the async-gateway...
API autoscaler cron failures are only visible to users in the logs. Detect and include autoscaler cron failures in the Cortex API status.
#### Description If configured, when a request is taken off of the queue for processing, if the time spent on the queue is greater than the configured timeout, the request...
### Implementation For example, `GET /` could respond with a list of the deployed APIs. ### Things to consider * Should there be an option to disable this feature? *...
### Description Instead of spinning up a GPU nodegroup, spin up a CPU nodegroup with Elastic Inference (GPU accelerated inference). ### Additional Context * https://aws.amazon.com/machine-learning/elastic-inference/ * [Optimizing TensorFlow model serving...
### Notes * Can this be determined from kubestate metrics? * Also consider if this makes sense for the Async API dashboard
### Description Changing images cluster configuration requires restarting the cluster. It would be helpful if images can be changed without requiring cluster restart to save time.
Metadata
Owner
Metadata
Production infrastructure for machine learning at scale