seldon-core
seldon-core copied to clipboard
SeldonIO
An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
Bumps [nbconvert](https://github.com/jupyter/nbconvert) from 5.6.1 to 6.3.0. Commits cefe0bf Release 6.3.0 a534fb9 Release 6.3.0b0 87920c5 Add changelog for 6.3.0 (#1669) dd6d9c7 add slide numbering (#1654) 5d2c5e2 Update state filter (#1664) 11ea593...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Currently if a containerSpec is provided to override the service orchestrator, ie. a container with the name "seldon-container-engine", the replace happens without autmenting current values, and hence everything has to...
Currently, the update strategy for seldon deployments is `RollingUpdate` with pre-set `MaxUnavailable` and `Surge` values. This should be configurable either in the Seldon Deployment Spec, or in the controller config....
**What this PR does / why we need it**: Currently, Seldon Deployments do not support setting `progressDeadlineSeconds`, which is an optional setting used to control when a deployment is [marked...
**What this PR does / why we need it**: There is a problem with the service account name usage in templates. It's not possible to change the name from the...
1. make [components/storage-initializer](https://github.com/SeldonIO/seldon-core/tree/master/components/storage-initializer) to be just re-tagged [components/rclone-storage-initializer](https://github.com/SeldonIO/seldon-core/tree/master/components/rclone-storage-initializer) 2. change default in https://github.com/SeldonIO/seldon-core/blob/master/operator/config/manager/configmap.yaml#L95
```release-note Added Storage Initializers on not prepacked server. ``` **What this PR does / why we need it**: Enable storage initalizer inject when `modelUri` set in graph on not prepacked...
For some historical reason, I need serving some custom protocol models(image). I'm not able to [Building a new inference server](https://docs.seldon.io/projects/seldon-core/en/latest/servers/custom.html#building-a-new-inference-server) for these models, so I have to serve them directly...
## Describe the bug We use _seldon-core-microservice_ to run our own Python translation model. The return value of the _predict_ method of our customer python model class wrapper is type...
