-
Scanflow described ML workflows need to be deployed on K8s clusters. In order to improve the performance of each workflow job or service, this issue requests Scanflow could use default scheduler or en…
-
You can serve your model with MLEM with:
```bash
$ mlem serve $FRAMEWORK models/mymodel
```
`$FRAMEWORK` values we want to support:
- [x] FastAPI
- [x] RabbitMQ
- [x] Streamlit
- [ ] Kafka
- …
-
/kind feature
**Describe the solution you'd like**
### Current state
Today IG is just a router. So, deploying an IG just creates a router pod. But this causes issue if you think about IG as any I…
-
/kind bug
**What steps did you take and what happened:**
Relevant code:
```python
# fairing:include-cell
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow…
-
**Describe the feature you'd like**
Would like flowise to have better kubernetes deployment, currently its just a docker container.
Would be easier if its still a docker container **however** when d…
-
Currently setting debug=true stops ALL logging which is fine for some use cases but others may want to still see some logging (ours). The behaviour we would love to see is that we can set per endpoint…
-
Based on running the seldon operator in openshift in https://github.com/operator-framework/community-operators/pull/447, it looks like the operator should have a kubebuilder mark for permissions on se…
-
We can use this gist https://gist.github.com/chaosmail/938d7db693f72adb287b
-
## Describe the bug
I have a model that failed deployment. Kubectl delete is successful but the model is still visible under `Models` CRDs in k8s.
## To reproduce
1. Train a model and …
-
### Bug Description
The `test_prometheus_grafana_integration_istio_pilot` test case that is part of the Observability Integration tests is failing intermittently in the CI, potentially because the te…