update release notes and support matrix

Signed-off-by: Abigail McCarthy <[email protected]>

Author: a-mccarthy

gpu-operator/life-cycle-policy.rst

@@ -101,16 +101,16 @@ Refer to :ref:`Upgrading the NVIDIA GPU Operator` for more information.
 
 
    * - NVIDIA Driver Manager for Kubernetes
-     - `v0.8.1 <https://ngc.nvidia.com/catalog/containers/nvidia:cloud-native:k8s-driver-manager>`__
+     - `v0.9.0 <https://ngc.nvidia.com/catalog/containers/nvidia:cloud-native:k8s-driver-manager>`__
 
    * - NVIDIA Container Toolkit
      - `1.18.0 <https://github.com/NVIDIA/nvidia-container-toolkit/releases>`__
 
    * - NVIDIA Kubernetes Device Plugin
-     - `0.17.4 <https://github.com/NVIDIA/k8s-device-plugin/releases>`__
+     - `0.18.0 <https://github.com/NVIDIA/k8s-device-plugin/releases>`__
 
    * - DCGM Exporter
-     - `4.4.1-4.5.2 <https://github.com/NVIDIA/dcgm-exporter/releases>`__
+     - `v4.4.1-4.6.0 <https://github.com/NVIDIA/dcgm-exporter/releases>`__
 
    * - Node Feature Discovery
      - `v0.18.1 <https://github.com/kubernetes-sigs/node-feature-discovery/releases/>`__
@@ -120,7 +120,7 @@ Refer to :ref:`Upgrading the NVIDIA GPU Operator` for more information.
      - `0.17.4 <https://github.com/NVIDIA/k8s-device-plugin/releases>`__
 
    * - NVIDIA MIG Manager for Kubernetes
-     - `0.12.3 <https://github.com/NVIDIA/mig-parted/blob/main/CHANGELOG.md>`__
+     - `0.13.0 <https://github.com/NVIDIA/mig-parted/blob/main/CHANGELOG.md>`__
 
    * - DCGM
      - `4.4.1 <https://docs.nvidia.com/datacenter/dcgm/latest/release-notes/changelog.html>`__
@@ -132,7 +132,7 @@ Refer to :ref:`Upgrading the NVIDIA GPU Operator` for more information.
      - `v1.4.0 <https://github.com/NVIDIA/kubevirt-gpu-device-plugin>`__
 
    * - NVIDIA vGPU Device Manager
-     - `v0.4.0 <https://github.com/NVIDIA/vgpu-device-manager>`__
+     - `v0.4.1 <https://github.com/NVIDIA/vgpu-device-manager>`__
 
    * - NVIDIA GDS Driver |gds|_
      - `2.26.6 <https://github.com/NVIDIA/gds-nvidia-fs/releases>`__

gpu-operator/platform-support.rst

@@ -190,6 +190,8 @@ The following NVIDIA data center GPUs are supported on x86 based platforms:
     +=========================+========================+=======+
     | NVIDIA DGX B200         | NVIDIA Blackwell       |       |
     +-------------------------+------------------------+-------+
+    | NVIDIA DGX Spark        | NVIDIA Blackwell       |       |
+    +-------------------------+------------------------+-------+
     | NVIDIA HGX B200         | NVIDIA Blackwell       |       |
     +-------------------------+------------------------+-------+
     | NVIDIA HGX B300         | NVIDIA Blackwell       |       |

gpu-operator/release-notes.rst

@@ -43,11 +43,15 @@ New Features
 
 * Updated software component versions:
 
+  - NVIDIA Driver Manager for Kubernetes v0.9.0
   - NVIDIA Container Toolkit v1.18.0
   - NVIDIA DCGM v4.4.1
-  - NVIDIA DCGM Exporter v4.4.1-4.5.2
-  - Node Feature Discovery v0.18.1
+  - NVIDIA DCGM Exporter v4.4.1-4.6.0
+  - Node Feature Discovery v0.18.2
   - NVIDIA GDS Driver v2.26.6
+  - NVIDIA Kubernetes Device Plugin v0.18.0
+  - NVIDIA MIG Manager for Kubernetes v0.13.0
+  - NVIDIA vGPU Device Manager v0.4.1
 
 * Added support for these NVIDIA Data Center GPU Driver versions:
 
@@ -68,7 +72,7 @@ New Features
     updated to ``true`` since the Operator Lifecycle Manager (OLM) does not mutate custom
     resources on operator upgrades.
 
-*  When using virtualization, on GPUs that support MIG, you now have the option to select MIG-backed vGPU instances instead of time-sliced vGPU instances.
+*  When using NVIDIA vGPU with KubeVirt / OpenShift Virtualization, on GPUs that support MIG, you now have the option to select MIG-backed vGPU instances instead of time-sliced vGPU instances.
    To select a MIG-backed vGPU profile, label the node with the name of the MIG-backed vGPU profile.
 
 * Added support for NVIDIA HGX B300 and NVIDIA HGX GB300 NVL72.
@@ -110,6 +114,17 @@ New Features
     * ``2g.70gb`` :math:`\times` 1
     * ``3g.139gb`` :math:`\times` 1 
 
+Improvements
+------------
+
+* The GPU Operator now configures containerd and cri-o using drop-in files by default.  
+   When installing on microk8s, you need to set the value of the RUNTIME_CONFIG_SOURCE parameter in the CLusterPolicy to ``file=/var/snap/microk8s/current/args/containerd.toml``. 
+
+* Hardened the GPU Operator container image by using a distroless as a base image.
+
+* Validator for NVIDIA GPU Operator is now included as part of the GPU Operator container image.
+  It is no longer a separate image.
+
 Fixed Issues
 ------------
 
@@ -118,7 +133,8 @@ Fixed Issues
 Known Issues
 ------------
 
-* TBD
+* When using cri-o as the container runtime, several of the GPU Operator pods may be stuck in the ``RunContainerError`` state during installation or upgrade of GPU Operator. 
+  The pods may be in this state for several minutes, but will recover from this state as soon as the container toolkit pod starts running.
 
 
 .. _v25.3.4: