pytorch uenv

Author: boeschf

docs/clusters/clariden.md

@@ -43,7 +43,10 @@ Users are encouraged to use containers on Clariden.
 * Jobs using containers can be easily set up and submitted using the [container engine][ref-container-engine].
 * To build images, see the [guide to building container images on Alps][ref-build-containers].
 
-Alternatively, [uenv][ref-uenv] are also available on Clariden. Currently the only uenv that is deployed on Clariden is [prgenv-gnu][ref-uenv-prgenv-gnu].
+Alternatively, [uenv][ref-uenv] are also available on Clariden. Currently deployed on Clariden:
+
+* [prgenv-gnu][ref-uenv-prgenv-gnu]
+* [pytorch][ref-uenv-pytorch]
 
 ??? example "using uenv provided for other clusters"
     You can run uenv that were built for other Alps clusters using the `@` notation.

docs/software/ml/index.md

@@ -0,0 +1,25 @@
+[](){#ref-software-ml}
+# Machine Learning Applications and Frameworks
+
+## Containerized Machine Learning Applications
+
+CSCS supports a variety of machine learning applications and frameworks on its
+systems. Typically, machine learning applications are containerized to ensure
+compatibility and ease of use across different environments.
+
+CSCS does not provide any specific machine learning container images, but users
+can create their own containers using popular base container registries, such
+as [Nvidia's NGC Catalog](https://catalog.ngc.nvidia.com/containers). These
+containers can be run on Alps, allowing users to leverage the
+high-performance computing resources available for their machine learning
+tasks.
+
+* Jobs using containers can be easily set up and submitted using the [container
+  engine][ref-container-engine].
+* To build images, see the [guide to building container images on
+  Alps][ref-build-containers].
+
+## Uenv Software Stacks
+
+CSCS provides a base [PyTorch uenv][ref-uenv-pytorch] that is available on the
+[Clariden][ref-cluster-clariden] and [Daint][ref-cluster-daint] cluster.