seldon-core
seldon-core copied to clipboard
An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models
The proposal here is to be able to specify in the helm installation (of the operator) values a list of namespaces in which the Seldon Core operator being installed can...
my ingress is : ``` apiVersion: networking.k8s.io/v1 kind: Ingress metadata: labels: app: seldon-mesh app.kubernetes.io/name: seldon-mesh name: seldon-mesh namespace: seldon-mesh spec: defaultBackend: service: name: seldon-mesh port: number: 80 rules: - host:...
I noticed that both SeldonConfig and SeldonRuntime Custom Resources use [ v1.PodSpec](https://github.com/kubernetes/api/blob/v0.24.4/core/v1/types.go#L3050) to define podSpec for the components, and re-use the Annotations/Metadata set in the CustomResource in the Pod spec...
seldon-core supports deployment on AWS EKS. The AWS have newer ARM based EC2 instance class Name Graviton ie. a series, cheaper and faster. As of now `seldon-core don't have support...
## Describe the bug I have a simple model taking one input with datatype `"BYTES"`. I've implemented this as an `mlserver` custom runtime, deployed it and can successfully call it....
Bumps [fonttools](https://github.com/fonttools/fonttools) from 4.42.0 to 4.43.0. Release notes Sourced from fonttools's releases. 4.43.0 [subset] Set up lxml XMLParser(resolve_entities=False) when parsing OT-SVG documents to prevent XML External Entity (XXE) attacks (9f61271dc):...
Background --- Proposing that we bump the upper bound of the [prometheus_client](https://github.com/prometheus/client_python/releases?page=1) library required by the `seldon-core` python sdk to include the latest `0.19.0` Reasoning --- We have projects that...
**What this PR does / why we need it**: Due to the independent memory space between processes, loading a model in a child process will result in loading multiple times....
## Describe the bug As of Release version 2.6.0, there was a change, where the seldon-controller can be installed clusterwide. With this new feature, there now is a bug (with...
Bumps [transformers](https://github.com/huggingface/transformers) from 4.31.0 to 4.36.0. Release notes Sourced from transformers's releases. v4.36: Mixtral, Llava/BakLlava, SeamlessM4T v2, AMD ROCm, F.sdpa wide-spread support New model additions Mixtral Mixtral is the new...