-
As @sakoush pointed out, for some upstream use cases (specifically `seldon-core` and `mlserver`) it is not desirable to call the passed `predictor` with random data at `__init__` time like we do in a …
-
As far as I understand the codec-friendly way of sending image/audio files in Seldon is sending images as NumPy arrays. Following the community slack [discussion-1](https://seldondev.slack.com/archive…
-
## Describe the bug
Deploying a transformer model (huggingface) on v2 using mlflow requirement fails with the following error:
```yaml
apiVersion: mlops.seldon.io/v1alpha1
kind: Model
m…
-
is it possible to have a RESTFUL api end point that returns a list of items based on one item?
e.g GET /items/{item_id}/recommendations
thank you
-
## Describe the bug
I try to install seldon core components in a restricted environment where it is mandatory to specify ephemeral storage limit to any container that runs on it. CPU and memory…
-
### Context
The `kserve-operators` (right now just the controller) are a key part in the Charmed Kubeflow inference serving offerings. This issue serves as a tracking issue for all the improvements a…
-
Setup:
MLServer instance(s) : 2 ( 1Gi, .1 vCPU) , with serverConfig.terminationGracePeriodSeconds=1200
Envoy Server instance(s) : 1 ( 4Gi , 1 vCPU)
Scheduler Server instance(s) : 1 ( 4Gi , 1 vC…
-
Charm is using version `1.14.0` instead of `1.15` for no apparent reason. We 've probably missed this during [upgrading from 1.14 to 1.15](https://github.com/canonical/seldon-core-operator/pull/97).
-
@akdetrick Would you be able to make a new copy of this repo and host it in your private account so we can remove this repo from the Meetup org? I don't think we'll be able to properly maintain it, bu…
-
The Deployments of the core components, created via
```bash
helm install seldon-v2-runtime seldon-charts/seldon-core-v2-runtime --namespace seldon-mesh --set pipelinegateway.disable=true --set dat…