chore: import upstream snapshot with attribution

doc/source/serve/examples.yml

@@ -0,0 +1,185 @@
+# This file is used to auto-generate the Examples Gallery page.
+# Do not edit the generated examples.rst page directly.
+# To request formatting changes to the generated page, file an issue with the Ray docs team.
+# To reference the generated page, use examples.html.
+# When adding a new example, include the skill level and framework, if applicable.
+
+text: Below are tutorials for exploring Ray Serve capabilities and learning how to integrate different modeling frameworks.
+groupby: related_technology
+examples:
+  - title: Serve ML Models
+    skill_level: beginner
+    frameworks:
+      - pytorch
+    use_cases:
+      - computer vision
+    link: tutorials/serve-ml-models
+    related_technology: ml applications
+  - title: Serve a Stable Diffusion Model
+    skill_level: beginner
+    use_cases:
+      - computer vision
+      - generative ai
+    link: tutorials/stable-diffusion
+    related_technology: ml applications
+  - title: Serve a Text Classification Model
+    skill_level: beginner
+    use_cases:
+      - natural language processing
+    link: tutorials/text-classification
+    related_technology: ml applications
+  - title: Serve an Object Detection Model
+    skill_level: beginner
+    use_cases:
+      - computer vision
+    link: tutorials/object-detection
+    related_technology: ml applications
+  - title: Serve an Inference Model on AWS NeuronCores Using FastAPI
+    skill_level: intermediate
+    use_cases:
+      - natural language processing
+    link: tutorials/aws-neuron-core-inference
+    related_technology: ai accelerators
+  - title: Serve an Inference with Stable Diffusion Model on AWS NeuronCores Using FastAPI
+    skill_level: intermediate
+    use_cases:
+      - computer vision
+      - generative ai
+    link: tutorials/aws-neuron-core-inference-stable-diffusion
+    related_technology: ai accelerators
+  - title: Serve a model on Intel Gaudi Accelerator
+    skill_level: intermediate
+    frameworks:
+      - pytorch
+    use_cases:
+      - generative ai
+      - large language models
+    link: tutorials/intel-gaudi-inference
+    related_technology: ai accelerators
+  - title: Scale a Gradio App with Ray Serve
+    skill_level: intermediate
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: tutorials/gradio-integration
+    related_technology: integrations
+  - title: Serve a Text Generator with Request Batching
+    skill_level: intermediate
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: tutorials/batch
+    related_technology: integrations
+  - title: Serve DeepSeek
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: tutorials/serve-deepseek
+    related_technology: llm applications
+  - title: Deploy a small-sized LLM
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: ../_collections/serve/tutorials/deployment-serve-llm/small-size-llm/README
+    related_technology: llm applications
+  - title: Deploy a medium-sized LLM
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: ../_collections/serve/tutorials/deployment-serve-llm/medium-size-llm/README
+    related_technology: llm applications
+  - title: Deploy a large-sized LLM
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: ../_collections/serve/tutorials/deployment-serve-llm/large-size-llm/README
+    related_technology: llm applications
+  - title: Deploy a vision LLM
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: ../_collections/serve/tutorials/deployment-serve-llm/vision-llm/README
+    related_technology: llm applications
+  - title: Deploy a reasoning LLM
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: ../_collections/serve/tutorials/deployment-serve-llm/reasoning-llm/README
+    related_technology: llm applications
+  - title: Deploy a hybrid reasoning LLM
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: ../_collections/serve/tutorials/deployment-serve-llm/hybrid-reasoning-llm/README
+    related_technology: llm applications
+  - title: Deploy gpt-oss
+    skill_level: beginner
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: ../_collections/serve/tutorials/deployment-serve-llm/gpt-oss/README
+    related_technology: llm applications
+  - title: Serve a Chatbot with Request and Response Streaming
+    skill_level: intermediate
+    use_cases:
+      - generative ai
+      - large language models
+      - natural language processing
+    link: tutorials/streaming
+    related_technology: ml applications
+  - title: Serving models with Triton Server in Ray Serve
+    skill_level: intermediate
+    use_cases:
+      - computer vision
+      - generative ai
+    link: tutorials/triton-server-integration
+    related_technology: integrations
+  - title: Serve a Java App
+    skill_level: advanced
+    link: tutorials/java
+    related_technology: integrations
+  - title: Model Multiplexing with Forecasting Models
+    skill_level: intermediate
+    use_cases:
+      - time series forecasting
+    link: ../_collections/serve/tutorials/model_multiplexing_forecast/README
+    related_technology: deployment patterns
+  - title: Model Composition for Recommendation Systems
+    skill_level: intermediate
+    use_cases:
+      - recommendation systems
+    link: ../_collections/serve/tutorials/model-composition-recsys/README
+    related_technology: deployment patterns
+  - title: Asynchronous Inference using Ray Serve
+    skill_level: advanced
+    use_cases:
+      - generative ai
+    link: ../_collections/serve/tutorials/asynchronous-inference/asynchronous-inference
+    related_technology: integrations
+  - title: Video Analysis Inference Pipeline
+    skill_level: advanced
+    use_cases:
+      - computer vision
+    link: tutorials/video-analysis/README
+    related_technology: ml applications
+  - title: Integrate with MLflow Model Registry
+    skill_level: intermediate
+    link: model-registries
+    related_technology: integrations