Merge branch 'main' into azure-infiniband

conda/environments/deployment_docs.yml

@@ -10,7 +10,8 @@ dependencies:
   - pydata-sphinx-theme>=0.15.4
   - python=3.12
   - pre-commit>=3.8.0
-  - sphinx>=8.0.2
+  # Upper bound pin on sphinx can be removed once https://github.com/mgaitan/sphinxcontrib-mermaid/issues/160 is resolved
+  - sphinx>=8.0.2,<8.1
   - sphinx-autobuild>=2024.9.19
   - sphinx-copybutton>=0.5.2
   - sphinx-design>=0.6.1

source/cloud/aws/eks.md

@@ -24,16 +24,15 @@ Now we can launch a GPU enabled EKS cluster. First launch an EKS cluster with `e
 
 ```console
 $ eksctl create cluster rapids \
-                      --version 1.24 \
+                      --version 1.29 \
                       --nodes 3 \
                       --node-type=p3.8xlarge \
                       --timeout=40m \
                       --ssh-access \
                       --ssh-public-key <public key ID> \  # Be sure to set your public key ID here
                       --region us-east-1 \
                       --zones=us-east-1c,us-east-1b,us-east-1d \
-                      --auto-kubeconfig \
-                      --install-nvidia-plugin=false
+                      --auto-kubeconfig
 ```
 
 With this command, you’ve launched an EKS cluster called `rapids`. You’ve specified that it should use nodes of type `p3.8xlarge`. We also specified that we don't want to install the NVIDIA drivers as we will do that with the NVIDIA operator.
@@ -46,30 +45,21 @@ $ aws eks --region us-east-1 update-kubeconfig --name rapids
 
 ## Install drivers
 
-Next, [install the NVIDIA drivers](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/getting-started.html) onto each node.
+As we selected a GPU node type EKS will automatically install drivers for us. We can verify this by listing the NVIDIA driver plugin Pods.
 
 ```console
-$ helm install --repo https://helm.ngc.nvidia.com/nvidia --wait --generate-name -n gpu-operator --create-namespace gpu-operator
-NAME: gpu-operator-1670843572
-NAMESPACE: gpu-operator
-STATUS: deployed
-REVISION: 1
-TEST SUITE: None
+$ kubectl get po -n kube-system -l name=nvidia-device-plugin-ds
+NAME                                   READY   STATUS    RESTARTS   AGE
+nvidia-device-plugin-daemonset-kv7t5   1/1     Running   0          52m
+nvidia-device-plugin-daemonset-rhmvx   1/1     Running   0          52m
+nvidia-device-plugin-daemonset-thjhc   1/1     Running   0          52m
 ```
 
-Verify that the NVIDIA drivers are successfully installed.
-
-```console
-$ kubectl get po -A --watch | grep nvidia
-kube-system   nvidia-driver-installer-6zwcn                                 1/1     Running   0         8m47s
-kube-system   nvidia-driver-installer-8zmmn                                 1/1     Running   0         8m47s
-kube-system   nvidia-driver-installer-mjkb8                                 1/1     Running   0         8m47s
-kube-system   nvidia-gpu-device-plugin-5ffkm                                1/1     Running   0         13m
-kube-system   nvidia-gpu-device-plugin-d599s                                1/1     Running   0         13m
-kube-system   nvidia-gpu-device-plugin-jrgjh                                1/1     Running   0         13m
+```{note}
+By default this plugin will install the latest version on the NVIDIA drivers on every Node. If you need more control over your driver installation we recommend that when creating your cluster you set `eksctl create cluster --install-nvidia-plugin=false ...` and then install drivers yourself using the [NVIDIA GPU Operator](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/getting-started.html).
 ```
 
-After your drivers are installed, you are ready to test your cluster.
+After you have confirmed your drivers are installed, you are ready to test your cluster.
 
 ```{include} ../../_includes/check-gpu-pod-works.md
 

source/conf.py

@@ -21,25 +21,25 @@
 author = "NVIDIA"
 
 # Single modifiable version for all of the docs - easier for future updates
-stable_version = "24.08"
-nightly_version = "24.10"
+stable_version = "24.10"
+nightly_version = "24.12"
 
 versions = {
     "stable": {
         "rapids_version": stable_version,
         "rapids_api_docs_version": "stable",
-        "rapids_container": f"nvcr.io/nvidia/rapidsai/base:{stable_version}-cuda12.5-py3.11",
-        "rapids_notebooks_container": f"nvcr.io/nvidia/rapidsai/notebooks:{stable_version}-cuda12.5-py3.11",
+        "rapids_container": f"nvcr.io/nvidia/rapidsai/base:{stable_version}-cuda12.5-py3.12",
+        "rapids_notebooks_container": f"nvcr.io/nvidia/rapidsai/notebooks:{stable_version}-cuda12.5-py3.12",
         "rapids_conda_channels": "-c rapidsai -c conda-forge -c nvidia",
-        "rapids_conda_packages": f"rapids={stable_version} python=3.11 cuda-version=12.5",
+        "rapids_conda_packages": f"rapids={stable_version} python=3.12 cuda-version=12.5",
     },
     "nightly": {
         "rapids_version": f"{nightly_version}-nightly",
         "rapids_api_docs_version": "nightly",
-        "rapids_container": f"rapidsai/base:{nightly_version + 'a'}-cuda12.5-py3.11",
-        "rapids_notebooks_container": f"rapidsai/notebooks:{nightly_version + 'a'}-cuda12.5-py3.11",
+        "rapids_container": f"rapidsai/base:{nightly_version + 'a'}-cuda12.5-py3.12",
+        "rapids_notebooks_container": f"rapidsai/notebooks:{nightly_version + 'a'}-cuda12.5-py3.12",
         "rapids_conda_channels": "-c rapidsai-nightly -c conda-forge -c nvidia",
-        "rapids_conda_packages": f"rapids={nightly_version} python=3.11 cuda-version=12.5",
+        "rapids_conda_packages": f"rapids={nightly_version} python=3.12 cuda-version=12.5",
     },
 }
 rapids_version = (

source/platforms/coiled.md

@@ -14,7 +14,7 @@ To get started you need to install Coiled and login.
 
 ```console
 $ conda install -c conda-forge coiled
-$ coiled setup
+$ coiled login
 ```
 
 For more information see the [Coiled Getting Started documentation](https://docs.coiled.io/user_guide/getting_started.html).
@@ -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
+client = Client(cluster)
 client
 ```