github SeldonIO/seldon-core v1.12.0

latest releases: v1.18.2, v2.8.1, v1.18.1...
2 years ago

v1.12.0

Full Changelog

Fixed bugs:

  • Ensure docker images have the source code included for MPL based licenses #3787
  • Stateful Model Feedback Metrics Server uses wrong image #3784
  • seldon-core-microservice: error: unrecognized arguments: test REST --service-type MODEL --persistence 0 #3775
  • Tensorflow protocol can't support /v1/models/${MODEL_NAME}[/versions/${VERSION}|/labels/${LABEL}] when using istioingress gateway #3767
  • seldonio/mlflowserver:1.12.0-dev now unable to server models #3766
  • TEP PY SITH #3752
  • OOM when stress test the Seldon model, which may be caused by the logging of request and response payloads #3726
  • Unable to install seldon via Helm #3725
  • Conda pip install permission denied in OpenShift #3712
  • Python/Executor path mis-match #3705
  • seldon-core-operator helm chart - in single namespace mode the role seldon1-manager-role does not include poddisruptionbudgets #3692
  • Currently engine related values cannot be ommited from the values.yaml while deploying seldon #3691
  • apiversion is deprecated in notebooks/resources/ambassador-rbac.yaml #3677
  • Error to build env: Command 'conda run -n mlflow pip install -r /microservice/requirements.txt' returned non-zero exit status 1. #3670
  • Seldon Manager Config Map has an extra comma that can cause parsing error #3652
  • Validate and address recent apparent flakiness in v2 server tests #3639
  • Executor returns minimal information on http client failure #3625
  • helm chart not compatible with k8s v1.22 #3618
  • Upgrade Grafana chart in seldon-core-analytics #3558
  • Mlflow getting downgraded #3454
  • Deploying custom MLflow model - stuck at "Readiness probe failed" #3186
  • Java Engine and Go Executor Does not Terminate Graph upon Error #2480

Security fixes:

Closed issues:

  • Exposing GRPC timeouts in Python client #3779
  • remove explainer_examples notebook #3777
  • Submit cloud events uncompressed until consumers supports it #3749
  • When is seldon v1.12 going to drop? #3735
  • Add model chaining example for the V2 protocol #3732
  • Fix alibi-explain-server to use alibi load\_explainer helper function #3708
  • Batch processor enhancemenst through raw data parameter #3702
  • Allow for Annotations and Labels to be injected into helm chart templates #3699
  • Allow Controller Manager to have configurable container security context #3698
  • Batch processor cast integers to floats in payloads #3681
  • Integrated alibi-explain mlserver runtime in Core #3675
  • Add e2e example on training explainers with Poetry-locked environment #3664
  • Move adserver to use Poetry #3660
  • Update Openshift OperatorHub Releases for 1.11.1 #3563
  • Better support Istio Mesh Internal to cluster #3485
  • Enable index filed in batch_processor #3409
  • Add "names" field in batch_processor.py to align with seldon_client.py #3408
  • upgrade seldon-core-analytics helm charts #3403
  • batch processor: add raw inputs support to predict method #2657
  • Publish RedHat images via API #2085
  • Seldon deployment name in case of complex graph #1801

Merged pull requests:

Don't miss a new seldon-core release

NewReleases is sending notifications on new releases.