# User Guide

This section provides practical guidance on how to get started with cuML in your
own projects to run classic ML algorithms blazingly fast on NVIDIA GPUs. You can
simply read through the examples or try them out yourself. If you want to run
code directly, have a look at the notebooks within the [notebooks](https://github.com/NVIDIA/cuml/tree/main/notebooks) as part of the cuML
GitHub repository instead.

#### NOTE
This guide describes how to use cuML’s GPU-accelerated estimators and
functions directly within your own code. See the [the next section](../cuml-accel/index.html.md) if you want to accelerate existing scikit-learn, UMAP,
and HDBSCAN code with zero code changes.

* [Training and Evaluating Machine Learning Models](../estimator_intro/index.html.md)
  * [Classification](../estimator_intro/index.html.md#Classification)
  * [Clustering](../estimator_intro/index.html.md#Clustering)
  * [Regression](../estimator_intro/index.html.md#Regression)
* [Model Serialization and Persistence](../pickling_cuml_models/index.html.md)
  * [Security Warning](../pickling_cuml_models/index.html.md#Security-Warning)
  * [Single GPU Model Serialization](../pickling_cuml_models/index.html.md#Single-GPU-Model-Serialization)
  * [Using joblib for Model Serialization](../pickling_cuml_models/index.html.md#Using-joblib-for-Model-Serialization)
  * [Distributed Model Serialization](../pickling_cuml_models/index.html.md#Distributed-Model-Serialization)
  * [Converting Between cuML and scikit-learn Models](../pickling_cuml_models/index.html.md#Converting-Between-cuML-and-scikit-learn-Models)
  * [Exporting Random Forest Models for CPU-Only Deployment](../pickling_cuml_models/index.html.md#Exporting-Random-Forest-Models-for-CPU-Only-Deployment)
  * [Exporting to ONNX](../pickling_cuml_models/index.html.md#Exporting-to-ONNX)
* [Dask Multi-GPU Guide](../dask_multigpu_guide/index.html.md)
  * [Setup and Configuration](../dask_multigpu_guide/index.html.md#Setup-and-Configuration)
  * [Example 1: K-Means Clustering](../dask_multigpu_guide/index.html.md#Example-1:-K-Means-Clustering)
  * [Example 2: Random Forest Classification](../dask_multigpu_guide/index.html.md#Example-2:-Random-Forest-Classification)
  * [Example 3: Linear Regression](../dask_multigpu_guide/index.html.md#Example-3:-Linear-Regression)
  * [Available Dask-Enabled Estimators](../dask_multigpu_guide/index.html.md#Available-Dask-Enabled-Estimators)
  * [Performance Considerations and Best Practices](../dask_multigpu_guide/index.html.md#Performance-Considerations-and-Best-Practices)
  * [Clean Up](../dask_multigpu_guide/index.html.md#Clean-Up)
  * [Additional Resources](../dask_multigpu_guide/index.html.md#Additional-Resources)
* [Advanced Topics](../advanced/index.html.md)
  * [CUDA Streams and Synchronization](../advanced/index.html.md#cuda-streams-and-synchronization)
  * [Selecting the CUDA Device](../advanced/index.html.md#selecting-the-cuda-device)
  * [Configuring the Memory Allocator](../advanced/index.html.md#configuring-the-memory-allocator)
* [Health Checks](../health_checks/index.html.md)
  * [Run standalone](../health_checks/index.html.md#run-standalone)
  * [Run via RAPIDS CLI](../health_checks/index.html.md#run-via-rapids-cli)
* [Supported Versions](../supported_versions/index.html.md)
  * [Required Runtime Dependencies](../supported_versions/index.html.md#required-runtime-dependencies)
  * [Dask Runtime Dependencies](../supported_versions/index.html.md#dask-runtime-dependencies)
  * [Optional Runtime Dependencies](../supported_versions/index.html.md#optional-runtime-dependencies)
  * [CUDA-X Dependencies](../supported_versions/index.html.md#cuda-x-dependencies)