How NVIDIA Technical Documentation prepared their website for AI search

# NVIDIA Technical Documentation

## CUDA Toolkit Documentation 12.9

- [CUDA C++ Programming Guide | NVIDIA Docs] (https://docs.nvidia.com/cuda/cuda-c-programming-guide.md): The programming guide to the CUDA model and interface.
- [CUDA Installation Guide for Linux | NVIDIA Docs] (https://docs.nvidia.com/cuda/cuda-installation-guide-linux.md):The installation instructions for the CUDA Toolkit on Linux.
- [CUDA Installation Guide for Microsoft Windows | NVIDIA Docs] (https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.md): The installation instructions for the CUDA Toolkit on Microsoft Windows systems.
- [Parallel Thread Execution ISA Version 8.8 | NVIDIA Docs] (https://docs.nvidia.com/cuda/parallel-thread-execution.md): The programming guide to using PTX (Parallel Thread Execution) and ISA (Instruction Set Architecture).
- [End User License Agreement for NVIDIA Software Development Kits | NVIDIA Docs] (https://docs.nvidia.com/cuda/eula.md): End User License Agreement for NVIDIA Software Development Kits.

## NVIDIA Dynamo

- [Dynamo Python Bindings — Dynamo] (https://docs.nvidia.com/dynamo/latest/API/python_bindings.html.md)
- [Dynamo SDK — Dynamo] (https://docs.nvidia.com/dynamo/latest/API/sdk.html.md)
- [High Level Architecture — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/architecture.html.md)
- [Dynamo Disaggregation: Separating Prefill and Decode for Enhanced Performance — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/disagg_serving.html.md)
- [Dynamo Distributed Runtime — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/distributed_runtime.html.md)
- [KV Cache Routing — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/kv_cache_routing.html.md)
- [Understanding KVBM components — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/kvbm_components.html.md)
- [KV Block Manager — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/kvbm_intro.html.md)
- [Motivation behind KVBM — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/kvbm_motivation.html.md)
- [KVBM Further Reading — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/kvbm_reading.html.md)
- [Planner — Dynamo] (https://docs.nvidia.com/dynamo/latest/architecture/planner.html.md)
- [Hello World: Aggregated and Disaggregated Deployment Examples — Dynamo] (https://docs.nvidia.com/dynamo/latest/examples/disagg_skeleton.html.md)
- [Hello World Example: Basic Pipeline — Dynamo] (https://docs.nvidia.com/dynamo/latest/examples/hello_world.html.md)
- [LLM Deployment Examples — Dynamo] (https://docs.nvidia.com/dynamo/latest/examples/llm_deployment.html.md)
- [LLM Deployment Examples using TensorRT-LLM — Dynamo] (https://docs.nvidia.com/dynamo/latest/examples/trtllm.html.md)
- [Getting Started — Dynamo] (https://docs.nvidia.com/dynamo/latest/get_started.html.md)
- [Writing Python Workers in Dynamo — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/backend.html.md)
- [About the Dynamo Command Line Interface — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/cli_overview.html.md)
- [Disaggregation and Performance Tuning — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/disagg_perf_tuning.html.md)
- [Building Dynamo (dynamo build) — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_build.html.md)
- [Dynamo Cloud Kubernetes Platform (Dynamo Deploy) — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/dynamo_cloud.html.md)
- [Working with Dynamo Kubernetes Operator — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/dynamo_operator.html.md)
- [GKE Workload Identity and Artifact Registry Setup Guide — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/gke_setup.html.md)
- [Deploying Dynamo Inference Graphs to Kubernetes using Helm — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/manual_helm_deployment.html.md)
- [Minikube Setup Guide — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/minikube.html.md)
- [Model Caching with Fluid: Cloud-Native Data Orchestration and Acceleration — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/model_caching_with_fluid.html.md)
- [Deploying Dynamo Inference Graphs to Kubernetes using the Dynamo Cloud Platform — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/operator_deployment.html.md)
- [Deploying Inference Graphs to Kubernetes (dynamo deploy) — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_deploy/README.html.md)
- [Running Dynamo (dynamo run) — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_run.html.md)
- [Serving Inference Graphs (dynamo serve) — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/dynamo_serve.html.md)
- [KV Router Performance Tuning — Dynamo] (https://docs.nvidia.com/dynamo/latest/guides/kv_router_perf_tuning.html.md)
- [Welcome to NVIDIA Dynamo — Dynamo] (https://docs.nvidia.com/dynamo/latest/index.html.md)
- [Dynamo Support Matrix — Dynamo] (https://docs.nvidia.com/dynamo/latest/support_matrix.html.md)