baschno/buun-stack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: write about KServe

Browse Source
This commit is contained in:
Masaki Yatsu
2025-11-10 21:36:32 +09:00
parent 2b0687330c
commit b84a1ae77a
1 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
README.md
View File

@@ -42,6 +42,7 @@ A remotely accessible Kubernetes home lab with OIDC authentication. Build a mode
- **[JupyterHub](https://jupyter.org/hub)**: Interactive computing with collaborative notebooks - **[JupyterHub](https://jupyter.org/hub)**: Interactive computing with collaborative notebooks
- **[MLflow](https://mlflow.org/)**: Machine learning lifecycle management with experiment tracking and model registry - **[MLflow](https://mlflow.org/)**: Machine learning lifecycle management with experiment tracking and model registry
- **[KServe](https://kserve.github.io/)**: Model serving platform for deploying ML models on Kubernetes
- **[Trino](https://trino.io/)**: Distributed SQL query engine for querying multiple data sources - **[Trino](https://trino.io/)**: Distributed SQL query engine for querying multiple data sources
- **[Querybook](https://www.querybook.org/)**: Big data querying UI with notebook interface - **[Querybook](https://www.querybook.org/)**: Big data querying UI with notebook interface
- **[ClickHouse](https://clickhouse.com/)**: High-performance columnar analytics database - **[ClickHouse](https://clickhouse.com/)**: High-performance columnar analytics database
@@ -183,6 +184,17 @@ Machine learning lifecycle management platform:
[📖 See MLflow Documentation](./mlflow/README.md) [📖 See MLflow Documentation](./mlflow/README.md)
### KServe
Model serving platform for deploying ML models on Kubernetes:
- **Multi-Framework Support**: TensorFlow, PyTorch, scikit-learn, XGBoost, MLflow, and more
- **MLflow Integration**: Deploy models directly from MLflow Model Registry
- **Inference Protocols**: REST and gRPC with v2 Open Inference Protocol
- **RawDeployment Mode**: Uses native Kubernetes Deployments without Knative dependency
[📖 See KServe Documentation](./kserve/README.md)
### Apache Superset ### Apache Superset
Modern business intelligence platform: Modern business intelligence platform:
@@ -450,6 +462,18 @@ The `custom.just` file is automatically imported by the main Justfile if it exis
The following demo projects showcase end-to-end data workflows using buun-stack: The following demo projects showcase end-to-end data workflows using buun-stack:
### ML Model Serving with MLflow and KServe
[**examples/kserve-mlflow-iris**](./examples/kserve-mlflow-iris/README.md)
End-to-end machine learning workflow demonstrating JupyterHub, MLflow, and KServe integration:
- **JupyterHub** for model training and testing
- **MLflow** for experiment tracking and model registry
- **KServe** for model deployment and inference
Key technologies: MLflow, KServe, MinIO, JupyterHub
### Salesforce to Iceberg REST Catalog ### Salesforce to Iceberg REST Catalog
[**dlt-salesforce-iceberg-rest-demo**](https://github.com/buun-ch/dlt-salesforce-iceberg-rest-demo) [**dlt-salesforce-iceberg-rest-demo**](https://github.com/buun-ch/dlt-salesforce-iceberg-rest-demo)