mkdocs.yml

nav:
    - Home: index.md
    - Getting started:
          - KServe Quickstart: get_started/README.md
          - First InferenceService: get_started/first_isvc.md
          - Interact with InferenceService Swagger UI: get_started/swagger_ui.md
    - Administration Guide:
          - Install KServe:
                - Predictive Inference:
                  - Serverless installation: admin/serverless/serverless.md
                  - Kubernetes deployment installation: admin/kubernetes_deployment.md
                  - ModelMesh installation: admin/modelmesh.md
                  - Kourier Networking Layer: admin/serverless/kourier_networking/README.md
                - Generative Inference:
                  - Kubernetes deployment installation: admin/kubernetes_deployment.md
                  - AI Gateway Integration: admin/ai-gateway_integration.md
                - Istio Service Mesh: admin/serverless/servicemesh/README.md
                - Gateway API migration: admin/gatewayapi_migration.md
    - User Guide:
          - Concepts:
                - Control Plane:
                  - Model Serving Control Plane: modelserving/control_plane.md
                - Data Plane:
                  - Model Serving Data Plane: modelserving/data_plane/data_plane.md
                  - V1 Inference Protocol: modelserving/data_plane/v1_protocol.md
                  - Open Inference Protocol (V2 Inference Protocol): modelserving/data_plane/v2_protocol.md
                  - Open Inference Protocol Extensions:
                    - Binary Tensor Data Extension: modelserving/data_plane/binary_tensor_data_extension.md
                - Serving Runtimes: modelserving/servingruntimes.md
          - Generative Inference:
              - Serving Runtime:
                  - Overview: modelserving/v1beta1/llm/huggingface/README.md
                  - Text Generation: modelserving/v1beta1/llm/huggingface/text_generation/README.md
                  - Text2Text Generation: modelserving/v1beta1/llm/huggingface/text2text_generation/README.md
                  - OpenAI SDK Integration: modelserving/v1beta1/llm/huggingface/sdk_integration/README.md
              - Multi Node Inference: modelserving/v1beta1/llm/huggingface/multi-node/README.md
              - Model Cache: modelserving/storage/modelcache/localmodel.md
              - LLM Autoscaler: modelserving/autoscaling/keda/autoscaling_llm.md
              - KV Cache Offloading: modelserving/v1beta1/llm/huggingface/kv_cache_offloading/README.md
              - AI Gateway Integration: admin/ai-gateway_integration.md
          - Predictive Inference:
              - Model Serving Runtimes:
                  - Supported Model Frameworks/Formats:
                      - Overview: modelserving/v1beta1/serving_runtime.md
                      - Tensorflow: modelserving/v1beta1/tensorflow/README.md
                      - PyTorch: modelserving/v1beta1/torchserve/README.md
                      - Scikit-learn: modelserving/v1beta1/sklearn/v2/README.md
                      - XGBoost: modelserving/v1beta1/xgboost/README.md
                      - PMML: modelserving/v1beta1/pmml/README.md
                      - Spark MLlib: modelserving/v1beta1/spark/README.md
                      - LightGBM: modelserving/v1beta1/lightgbm/README.md
                      - Paddle: modelserving/v1beta1/paddle/README.md
                      - MLFlow: modelserving/v1beta1/mlflow/v2/README.md
                      - ONNX: modelserving/v1beta1/onnx/README.md
                      - Hugging Face:
                         - Overview: modelserving/v1beta1/huggingface/README.md
                         - Token Classification: modelserving/v1beta1/huggingface/token_classification/README.md
                         - Text Classification: modelserving/v1beta1/huggingface/text_classification/README.md
                         - Fill Mask: modelserving/v1beta1/huggingface/fill_mask/README.md
                  - Multi-Framework Serving Runtimes:
                      - Nvidia Triton:
                        - TorchScript: modelserving/v1beta1/triton/torchscript/README.md
                        - Tensorflow: modelserving/v1beta1/triton/bert/README.md
                        - Hugging Face: modelserving/v1beta1/triton/huggingface/README.md
                      - AMD: modelserving/v1beta1/amd/README.md
                  - How to write a custom predictor: modelserving/v1beta1/custom/custom_model/README.md
              - Multi Model Serving:
                - Overview:
                  - The Scalability Problem: modelserving/mms/multi-model-serving.md
                  - ModelMesh Overview: modelserving/mms/modelmesh/overview.md
              - Transformers(pre/post processing):
                - How to write a custom transformer: modelserving/v1beta1/transformer/torchserve_image_transformer/README.md
                - Collocate transformer and predictor: modelserving/v1beta1/transformer/collocation/README.md
                - Feast: modelserving/v1beta1/transformer/feast/README.md
              - Rollout Strategies:
                  - Canary: modelserving/v1beta1/rollout/canary.md
                  - Canary Example: modelserving/v1beta1/rollout/canary-example.md
              - Autoscaling:
                  - Knative Autoscaler(KPA): modelserving/autoscaling/autoscaling.md
                  - Kubernetes Autoscaler(HPA): modelserving/autoscaling/raw_deployment_autoscaling.md
                  - KEDA Autoscaler: modelserving/autoscaling/keda/autoscaling_keda.md
              - Request Batching:
                  - Inference Batcher: modelserving/batcher/batcher.md
              - Payload Logging:
                  - Inference Logger: modelserving/logger/logger.md
              - Kafka:
                  - Inference with Kafka Event Source: modelserving/kafka/kafka.md
              - Inference Observability:
                 - Prometheus Metrics:  modelserving/observability/prometheus_metrics.md
                 - Grafana Dashboards:  modelserving/observability/grafana_dashboards.md
              - Model Explainability:
                  - Concept: modelserving/explainer/explainer.md
                  - TrustyAI Explainer: modelserving/explainer/trustyai/README.md
                  - Alibi Explainer:
                      - Image Explainer: modelserving/explainer/alibi/cifar10/README.md
                      - Income Explainer: modelserving/explainer/alibi/income/README.md
                      - Text Explainer: modelserving/explainer/alibi/moviesentiment/README.md
                  - AIX Explainer: modelserving/explainer/aix/mnist/aix.md
              - Model Monitoring:
                  - Alibi Detector: modelserving/detect/alibi_detect/alibi_detect.md
                  - AIF Bias Detector: modelserving/detect/aif/germancredit/README.md
                  - ART Adversarial Detector: modelserving/detect/art/mnist/README.md
          - Inference Graph:
                - Concept: modelserving/inference_graph/README.md
                - Overview: modelserving/inference_graph/overview.md
                - Image classification inference graph: modelserving/inference_graph/image_pipeline/README.md
          - Model Storage:
                - Storage Containers: modelserving/storage/storagecontainers.md
                - Configure CA Certificate: modelserving/certificate/kserve.md
                - Azure: modelserving/storage/azure/azure.md
                - PVC: modelserving/storage/pvc/pvc.md
                - S3: modelserving/storage/s3/s3.md
                - OCI: modelserving/storage/oci.md
                - URI: modelserving/storage/uri/uri.md
                - GCS: modelserving/storage/gcs/gcs.md
                - Hugging Face: modelserving/storage/huggingface/hf.md
          - Node Scheduling:
                - Overview: modelserving/nodescheduling/overview.md
                - InferenceService Node Scheduling: modelserving/nodescheduling/inferenceservicenodescheduling.md
    - API Reference:
          - Control Plane API: reference/api.md
          - Open Inference Protocol API Spec: reference/swagger-ui.md
          - Python Client SDK: sdk_docs/sdk_doc.md
          - Python Runtime Server SDK: python_runtime_api/docs/index.md
          - Inference Python Client: inference_client/doc.md
    - Developer Guide:
          - How to contribute: developer/developer.md
          - Debugging guide: developer/debug.md
    - Blog:
          - Releases:
            - KServe 0.15 Release: blog/articles/2025-05-27-KServe-0.15-release.md
            - KServe 0.14 Release: blog/articles/2024-12-13-KServe-0.14-release.md
            - KServe 0.13 Release: blog/articles/2024-05-15-KServe-0.13-release.md
            - KServe 0.11 Release: blog/articles/2023-10-08-KServe-0.11-release.md
            - KServe 0.10 Release: blog/articles/2023-02-05-KServe-0.10-release.md
            - KServe 0.9 Release: blog/articles/2022-07-21-KServe-0.9-release.md
            - KServe 0.8 Release: blog/articles/2022-02-18-KServe-0.8-release.md
            - KServe 0.7 Release: blog/articles/2021-10-11-KServe-0.7-release.md
    - Community:
        - How to Get Involved: community/get_involved.md
        - Adopters: community/adopters.md
        - Demos and Presentations: community/presentations.md

site_name: KServe Documentation Website
site_url: https://kserve.io/website
site_description: KServe Documentation
extra_css:
  - stylesheets/extra.css

repo_url: https://github.com/kserve/kserve
edit_uri: https://github.com/kserve/website/edit/main/docs

theme:
  name: material
  logo: images/logo/kserve.png
  favicon: images/favicon/favicon-32x32.png
  custom_dir: overrides
  features:
    - navigation.tabs
    - navigation.tracking
    - navigation.tabs.sticky
    - navigation.top

markdown_extensions:
  - markdown_include.include:
      base_path: docs
  # - mdx_include:
  #     base_path: docs
  - pymdownx.emoji:
      emoji_index: !!python/name:pymdownx.emoji.twemoji
      emoji_generator: !!python/name:pymdownx.emoji.to_svg
  - attr_list
  - meta
  - pymdownx.superfences
  - pymdownx.tabbed:
      alternate_style: true
  - pymdownx.details
  - pymdownx.snippets:
      base_path: docs/snippets
  - pymdownx.keys
  - pymdownx.caret
  - pymdownx.mark
  - pymdownx.tilde
  - pymdownx.escapeall
  - pymdownx.tasklist:
      custom_checkbox: true
  - admonition
  - toc:
      permalink: true
  - def_list

copyright: "Copyright © 2021 The KServe Authors"

plugins:
  - search
  - macros:
      on_undefined: keep
  - mkdocstrings:
      default_handler: python
      handlers:
        python:
          load_external_modules: true
  - mike:
     version_selector: true
     css_dir: css
     javascript_dir: js
  - swagger-ui-tag:
        background: White
        docExpansion: none
        filter: ""
        syntaxHighlightTheme: monokai
        tryItOutEnabled: true
       

extra:
  kserve_release_version: 0.15.0
  social:
    - icon: fontawesome/brands/github
      link: https://github.com/kserve
      name: KServe Community on Github
    - icon: fontawesome/brands/slack
      link: https://github.com/kserve/community/blob/main/README.md#questions-and-issues
      name: Join Slack
  version_warning: !ENV VERSION_WARNING
  kserve_version: !ENV KSERVE_VERSION
  branch: !ENV ["SAMPLES_BRANCH", "mkdocs"]
  version:
    provider: mike