Note, however, that I have much more experience with Cortex.
Common
- both deploy and serve models via API
- both support major ML frameworks (TensorFlow, Pytorch)
- both have good documentation
Comparison
| Feature | BentoML.org | Cortex.dev |
|---|---|---|
| Language | Python - easier to modify, integrate? | Go |
| Deployment | Delegated to other tools: Docker, Kubernetes, AWS Lambda, SageMaker, GCP, Azule ML and more. | Works currently only with local Docker and AWS EKS (GCP is planned) |
| Service configuration | via decorators directly in Python code | via YAML files, or Cortex Serving Client for Python |
| Service packaging and distribution | Can be packaged, saved via Python command to management repository with a web dashboard or PyPI | Packaging only via Docker images without explicit support |
| Horizontal scaling | Configured separately in other clustering tools. Working on an opinionated Kubernetes deployment. | Is part of Cortex configs. But is thus less flexible (private cloud, HTTPS deploy requires custom scripts) |
| User interface | CLI, Web UI | CLI |
| Metrics | Prometheus metrics | AWS EKS metrics |
| API Auto-Docs | Swagger/OpenAPI | N/A |
| User support | Responsive unpaid Slack Channel, but Slack is not the best tool for support | Very responsive Gitter |
| Suggest anything else? |
My Experience with Cortex
Here is a blog post on Cortex use at GLAMI. Consider using this Cortex client for Python, which is a Python wrapper around Cortex CLI that we use at GLAMI for MLOps.