Deployment options¶
This page serves a guide, summarizing the pros and cons of each deployment option. With this information in mind, users can make the best decision on where to deploy their models.
Option |
✅ Pros |
❌ Cons |
|---|---|---|
Deploy as serverless (model is loaded on demand) |
|
|
Deploy persistently (model is always loaded) |
|
|
|
|
|
|
|
Given the above specifications, we recommend the following typical workflows:
Deploy as serverless if your service does not need low latency and expects to either (1) receive lots of concurrent user queries or (2) receive user queries that are spaced-out in time. This is the recommended option by default for all users.
Deploy persistently if your service needs to handle, with low latency, few concurrent user queries that are close in time.
Deploy in your own cloud resources if you do not belong to the project and have access to private cloud resources.
Deploy in the EOSC node if you are a European researcher who does not belong to the project and don’t have access to private cloud resources.
If you need to generate one-off predictions on a given dataset but not maintain a running service, you have two options:
Deploy persistently with a GPU, make your predictions and delete the deployment.
Deploy as serverless and upload your dataset files to a bucket to perform async predictions. If your dataset is really big, you can contact support to create a custom batch processing pipeline tailored to your usecase.
In addition to the above deployment options from the Dashboard, there are several additional deployment methods: