diff --git a/gpu-operator/life-cycle-policy.rst b/gpu-operator/life-cycle-policy.rst index 07f370848..427ea29ec 100644 --- a/gpu-operator/life-cycle-policy.rst +++ b/gpu-operator/life-cycle-policy.rst @@ -91,21 +91,20 @@ Refer to :ref:`Upgrading the NVIDIA GPU Operator` for more information. * - NVIDIA GPU Driver - | `565.57.01 `_ | `560.35.03 `_ - | `550.127.08 `_ (recommended), - | `550.127.05 `_ (default), + | `550.127.08 `_ (default), | `535.216.03 `_ * - NVIDIA Driver Manager for Kubernetes - `v0.7.0 `__ * - NVIDIA Container Toolkit - - `1.17.0 `__ + - `1.17.3 `__ * - NVIDIA Kubernetes Device Plugin - `0.17.0 `__ * - DCGM Exporter - - `3.3.8-3.6.0 `__ + - `3.3.9-3.6.1 `__ * - Node Feature Discovery - v0.16.6 @@ -118,7 +117,7 @@ Refer to :ref:`Upgrading the NVIDIA GPU Operator` for more information. - `0.10.0 `__ * - DCGM - - `3.3.8-1 `__ + - `3.3.9-1 `__ * - Validator for NVIDIA GPU Operator - ${version} diff --git a/gpu-operator/platform-support.rst b/gpu-operator/platform-support.rst index 3aaecca2f..b0a19aa77 100644 --- a/gpu-operator/platform-support.rst +++ b/gpu-operator/platform-support.rst @@ -471,7 +471,7 @@ Support for GPUDirect RDMA Supported operating systems and NVIDIA GPU Drivers with GPUDirect RDMA. -- Ubuntu 20.04 and 22.04 LTS with Network Operator 24.7.0 +- Ubuntu 20.04 and 22.04 LTS with Network Operator 24.10.0 - Red Hat OpenShift 4.12 and higher with Network Operator 23.10.0 For information about configuring GPUDirect RDMA, refer to :doc:`gpu-operator-rdma`. @@ -482,7 +482,7 @@ Support for GPUDirect Storage Supported operating systems and NVIDIA GPU Drivers with GPUDirect Storage. -- Ubuntu 20.04 and 22.04 LTS with Network Operator 24.7.0 +- Ubuntu 20.04 and 22.04 LTS with Network Operator 24.10.0 - Red Hat OpenShift Container Platform 4.12 and higher .. note:: diff --git a/gpu-operator/release-notes.rst b/gpu-operator/release-notes.rst index 6ae8ea7a8..3747c4fe8 100644 --- a/gpu-operator/release-notes.rst +++ b/gpu-operator/release-notes.rst @@ -34,6 +34,46 @@ See the :ref:`GPU Operator Component Matrix` for a list of software components a ---- +.. _v24.9.1: + +24.9.1 +====== + +.. _v24.9.1-new-features: + +New Features +------------ + +* Added support for the NVIDIA Data Center GPU Driver versions 550.127.08 and 535.216.03. + Refer to the :ref:`GPU Operator Component Matrix` + on the platform support page. + +* Added support for the following software component versions: + + - NVIDIA Container Toolkit v1.17.3 + - NVIDIA DCGM v3.3.9-1 + - NVIDIA DCGM Exporter v3.3.9-3.6.1 + +* Added support for NVIDIA Network Operator v24.10.0. + Refer to :ref:`Support for GPUDirect RDMA` and :ref:`Support for GPUDirect Storage`. + +* Added an ``all-balanced`` MIG profile for H200 NVL which creates the following GPU instances: + + * ``1g.18gb`` :math:`\times` 2 + * ``2g.35gb`` :math:`\times` 1 + * ``3g.71gb`` :math:`\times` 1 + +.. _v24.9.1-fixed-issues: + +Fixed Issues +------------ + +* Fixed an issue where NVIDIA Container Toolkit would fail to start on Rancher RKE2, K3s, and Canonical MicroK8s. + Refer to Github `issue #1109 `__ for more details. + +* Fixed an issue where events were not being generated by the NVIDIA driver upgrade controller. + Refer to Github `issue #1101 `__ for more details. + .. _v24.9.0: 24.9.0 diff --git a/gpu-operator/versions.json b/gpu-operator/versions.json index fd6515ca9..08d33048e 100644 --- a/gpu-operator/versions.json +++ b/gpu-operator/versions.json @@ -1,7 +1,10 @@ { - "latest": "24.9.0", + "latest": "24.9.1", "versions": [ + { + "version": "24.9.1" + }, { "version": "24.9.0" }, @@ -16,9 +19,6 @@ }, { "version": "24.3.0" - }, - { - "version": "23.9.2" } ] } diff --git a/openshift/versions.json b/openshift/versions.json index 703268102..b92119424 100644 --- a/openshift/versions.json +++ b/openshift/versions.json @@ -1,7 +1,10 @@ { - "latest": "24.9.0", + "latest": "24.9.1", "versions": [ + { + "version": "24.9.1" + }, { "version": "24.9.0" }, @@ -13,9 +16,6 @@ }, { "version": "24.3.0" - }, - { - "version": "23.9.2" } ] } diff --git a/repo.toml b/repo.toml index a3cca8b18..201f4034e 100644 --- a/repo.toml +++ b/repo.toml @@ -142,8 +142,8 @@ output_format = "linkcheck" docs_root = "${root}/gpu-operator" project = "gpu-operator" name = "NVIDIA GPU Operator" -version = "24.9.0" -source_substitutions = { version = "v24.9.0", recommended = "550.127.08" } +version = "24.9.1" +source_substitutions = { version = "v24.9.1", recommended = "550.127.08" } copyright_start = 2020 sphinx_exclude_patterns = [ "life-cycle-policy.rst", @@ -201,7 +201,7 @@ output_format = "linkcheck" docs_root = "${root}/openshift" project = "gpu-operator-openshift" name = "NVIDIA GPU Operator on Red Hat OpenShift Container Platform" -version = "24.9.0" +version = "24.9.1" copyright_start = 2020 sphinx_exclude_patterns = [ "get-entitlement.rst",