cnfatal

Inject storage initializer on not prepacked server

5

```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...

support use model-initializer with "no-engine" when modelUri set

1

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...

enpoint config `endpoint.httpPort` in graph does'n take effect.

1

## Describe the bug Configuration `httpPort` and `grpcPort` in `.spec.predictors[].graph.endpoint` do not take effect. ## To reproduce ```yaml apiVersion: machinelearning.seldon.io/v1 kind: SeldonDeployment metadata: name: sklearn-iris spec: predictors: - name: default...

See: https://github.com/ppwwyyxx/wechat-dump/issues/70

[优化] nettop 可以输出csv格式,更好解析

1

环境： ```sh % sw_vers ProductName: macOS ProductVersion: 12.0.1 BuildVersion: 21A559 ``` 示例： ```sh % nettop -L 1 -P -J bytes_in,bytes_out ,bytes_in,bytes_out, systemstats.503,0,0, configd.504,0,0, apsd.533,11417,23504, locationd.541,0,0, bluetoothd.555,0,0, ```

Fixed the push with update-dependencies error: ```bash $ helm cm-push -d -f my-chart Getting updates for unmanaged Helm repositories... ...Successfully got an update from the "https://charts.bitnami.com/bitnami" chart repository Error: no...

## Description _Describe the big picture of your changes here to communicate to the maintainers why we should accept this pull request. If it fixes a bug or resolves a...

Add support for pass devices via `volume-mounts`. https://github.com/NVIDIA/k8s-device-plugin#configuration-option-details > The DEVICE_LIST_STRATEGY flag allows one to choose which strategy the plugin will use to advertise the list of GPUs allocated to...

Feature: Allow save multi-arch images on `sealos build`

1

### What is the problem this feature will solve? The [build-multi-arch-image](https://sealos.run/docs/k8s/operations/build-image/build-multi-arch-image) is designed to build images targeting multi-architecture clusters. However, the images currently loaded into the cluster are single-architecture only....