diff --git a/source/cloud/azure/azure-vm.md b/source/cloud/azure/azure-vm.md index 0b2ef953..ffcd6d04 100644 --- a/source/cloud/azure/azure-vm.md +++ b/source/cloud/azure/azure-vm.md @@ -128,7 +128,7 @@ Next, we can SSH into our VM to install RAPIDS. SSH instructions can be found by ### Useful Links -- [Using NGC with Azure](https://docs.nvidia.com/ngc/ngc-azure-setup-guide/index.html) +- [Using NGC with Azure](https://docs.nvidia.com/ngc/ngc-deploy-public-cloud/ngc-azure/index.html) ```{relatedexamples} diff --git a/source/examples/rapids-azureml-hpo/notebook.ipynb b/source/examples/rapids-azureml-hpo/notebook.ipynb index 14575363..d6f6736e 100644 --- a/source/examples/rapids-azureml-hpo/notebook.ipynb +++ b/source/examples/rapids-azureml-hpo/notebook.ipynb @@ -72,7 +72,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Initialize`MLClient`[class](https://learn.microsoft.com/en-us/python/api/azure-ai-ml/azure.ai.ml.mlclient?view=azure-python) to handle the workspace you created in the prerequisites step. \n", + "Initialize `MLClient` [class](https://learn.microsoft.com/en-us/python/api/azure-ai-ml/azure.ai.ml.mlclient?view=azure-python) to handle the workspace you created in the prerequisites step. \n", "\n", "You can manually provide the workspace details or call `MLClient.from_config(credential, path)`\n", "to create a workspace object from the details stored in `config.json`" @@ -307,7 +307,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "We'll be using a custom RAPIDS docker image to [setup the environment]((https://learn.microsoft.com/en-us/azure/machine-learning/how-to-manage-environments-v2?tabs=python#create-an-environment-from-a-docker-image). This is available in `rapidsai/rapidsai` repo on [DockerHub](https://hub.docker.com/r/rapidsai/rapidsai/).\n", + "We'll be using a custom RAPIDS docker image to [setup the environment](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-manage-environments-v2?tabs=python#create-an-environment-from-a-docker-image). This is available in `rapidsai/rapidsai` repo on [DockerHub](https://hub.docker.com/r/rapidsai/rapidsai/).\n", "\n", "Make sure you have the correct path to the docker build context as `os.getcwd()`," ] diff --git a/source/examples/rapids-optuna-hpo/notebook.ipynb b/source/examples/rapids-optuna-hpo/notebook.ipynb index 127d08ce..3f16ccf3 100644 --- a/source/examples/rapids-optuna-hpo/notebook.ipynb +++ b/source/examples/rapids-optuna-hpo/notebook.ipynb @@ -277,7 +277,7 @@ " \n", "Optuna uses [studies](https://optuna.readthedocs.io/en/stable/reference/study.html) and [trials](https://optuna.readthedocs.io/en/stable/reference/trial.html) to keep track of the HPO experiments. Put simply, a trial is a single call of the objective function while a set of trials make up a study. We will pick the best observed trial from a study to get the best parameters that were used in that run.\n", "\n", - "Here, `DaskStorage` class is used to set up a storage shared by all workers in the cluster. Learn more about what storages can be used [here](https://optuna.readthedocs.io/en/stable/tutorial/distributed.html)\n", + "Here, `DaskStorage` class is used to set up a storage shared by all workers in the cluster. Learn more about what storages can be used [here](https://optuna.readthedocs.io/en/stable/reference/storages.html)\n", "\n", "`optuna.create_study` is used to set up the study. As you can see, it specifies the study name, sampler to be used, the direction of the study, and the storage.\n", "With just a few lines of code, we have set up a distributed HPO experiment." @@ -347,7 +347,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Conluding Remarks\n", + "## Concluding Remarks\n", " \n", "This notebook shows how RAPIDS and Optuna can be used along with dask to run multi-GPU HPO jobs, and can be used as a starting point for anyone wanting to get started with the framework. We have seen how by just adding a few lines of code we were able to integrate the libraries for a muli-GPU HPO runs. This can also be scaled to multiple nodes.\n", " \n", diff --git a/source/examples/rapids-sagemaker-hpo/notebook.ipynb b/source/examples/rapids-sagemaker-hpo/notebook.ipynb index 9ab5d7b0..c615b8c0 100644 --- a/source/examples/rapids-sagemaker-hpo/notebook.ipynb +++ b/source/examples/rapids-sagemaker-hpo/notebook.ipynb @@ -43,7 +43,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "" + "![](../../_static/images/examples/rapids-sagemaker-hpo/hpo.png)" ] }, { @@ -595,7 +595,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - " " + "![](../../_static/images/examples/rapids-sagemaker-hpo/ml_workflow.png) " ] }, { @@ -707,7 +707,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "" + "![](../../_static/images/examples/rapids-sagemaker-hpo/estimator.png)" ] }, { @@ -1477,7 +1477,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "" + "![](../../_static/images/examples/rapids-sagemaker-hpo/run_hpo.png)" ] }, { @@ -2186,7 +2186,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "" + "![](../../_static/images/examples/rapids-sagemaker-hpo/results.png)" ] }, { diff --git a/source/platforms/coiled.md b/source/platforms/coiled.md index 88a3c954..f84cd3b3 100644 --- a/source/platforms/coiled.md +++ b/source/platforms/coiled.md @@ -82,7 +82,7 @@ We can also connect a Dask client to see that information for the workers too. ```python from dask.distributed import Client -client = Client(cluster) +client = Client() client ``` diff --git a/source/platforms/kubeflow.md b/source/platforms/kubeflow.md index a9f84065..5c3372ce 100644 --- a/source/platforms/kubeflow.md +++ b/source/platforms/kubeflow.md @@ -83,7 +83,7 @@ To use Dask, we need to create a scheduler and some workers that will perform ou ### Installing the Dask Kubernetes operator -To install the operator we need to create any custom resources and the operator itself, please [refer to the documentation](https://kubernetes.dask.org/en/latest/operator_installation.html) to find up-to-date installation instructions. From the terminal run the following command. +To install the operator we need to create any custom resources and the operator itself, please [refer to the documentation](https://kubernetes.dask.org/en/latest/installing.html) to find up-to-date installation instructions. From the terminal run the following command. ```console $ helm install --repo https://helm.dask.org --create-namespace -n dask-operator --generate-name dask-kubernetes-operator diff --git a/source/tools/kubernetes/dask-operator.md b/source/tools/kubernetes/dask-operator.md index 179a54cf..8997041e 100644 --- a/source/tools/kubernetes/dask-operator.md +++ b/source/tools/kubernetes/dask-operator.md @@ -1,7 +1,7 @@ # Dask Operator Many libraries in RAPIDS can leverage Dask to scale out computation onto multiple GPUs and multiple nodes. -[Dask has an operator for Kubernetes](https://kubernetes.dask.org/en/latest/operator.html) which allows you to launch Dask clusters as native Kubernetes resources. +[Dask has an operator for Kubernetes](https://kubernetes.dask.org/en/latest/) which allows you to launch Dask clusters as native Kubernetes resources. With the operator and associated Custom Resource Definitions (CRDs) you can create `DaskCluster`, `DaskWorkerGroup` and `DaskJob` resources that describe your Dask components and the operator will @@ -45,7 +45,7 @@ graph TD Your Kubernetes cluster must have GPU nodes and have [up to date NVIDIA drivers installed](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/getting-started.html). -To install the Dask operator follow the [instructions in the Dask documentation](https://kubernetes.dask.org/en/latest/operator_installation.html). +To install the Dask operator follow the [instructions in the Dask documentation](https://kubernetes.dask.org/en/latest/installing.html). ## Configuring a RAPIDS `DaskCluster` @@ -226,7 +226,7 @@ spec: ``` For the scheduler pod we are also setting the `rapidsai/base` container image, mainly to ensure our Dask versions match between -the scheduler and workers. We also disable Jupyter and ensure that the `dask-scheduler` command is configured. +the scheduler and workers. We ensure that the `dask-scheduler` command is configured. Then we configure both the Dask communication port on `8786` and the Dask dashboard on `8787` and add some probes so that Kubernetes can monitor the health of the scheduler.