Updated all CSPs to 1.28 and updated GPU operator to 23.9.x

README.md

@@ -24,6 +24,7 @@ Each CSP has its own end of life date for the versions of Kubernetes they suppor
 
 | Version | Release Date  | Kubernetes Versions                            | NVIDIA GPU Operator    | NVIDIA Data Center Driver* | End of Life |
 | :---    |    :---       | :---                                           | :---                   | :---                      | :--- |
+| 0.6.0     | January 2024 | EKS -  1.28 <br> GKE - 1.28 <br> AKS - 1.28 | 23.9.1 (Default); 23.9.0 (NV AI E)                 | 535.129.03  (EKS & GKE Default); 535.129.03 (NV AI E version for GKE & EKS)    | EKS - Nov 2024 <br> GKE - Nov 2024  <br> AKS - Nov 2024 |
 | 0.5.0     | November 2023 | EKS -  1.27 <br> GKE - 1.27 <br> AKS - 1.27 | 23.6.1 (Default); 23.3.2 (NV AI E)                 | 535.104.05  (EKS & GKE Default); 525.125.06 (NV AI E version for GKE & EKS)    | EKS - July 2024 <br> GKE - August 2024  <br> AKS - July 2024 |
 | 0.4.0     | October 2023 | EKS -  1.27 <br> GKE - 1.27 <br> AKS - 1.27 | 23.6.1 (Default); 23.3.2 (NV AI E)                 | 535.104.05  (EKS & GKE Default); 525.125.06 (NV AI E version for GKE & EKS)    | EKS - July 2024 <br> GKE - August 2024  <br> AKS - July 2024 |
 | 0.3.0     | September 2023 | EKS -  1.26 <br> GKE - 1.26 <br> AKS - 1.26 | 23.6.1 (Default); 23.3.2 (NV AI E)                 | 535.54.03  (EKS & GKE Default); 525.125.06 (NV AI E version for GKE & EKS)    | EKS - June 2024 <br> GKE - June 2024  <br> AKS - March 2024 |

aks/README.md

@@ -79,7 +79,6 @@ To create a cluster with everything needed to run the Cloud Native Service Add-o
   -  In Cloud Shell, run `az login` and re-run `terraform apply`
 
 
-
 ## Requirements
 
 | Name | Version |
@@ -131,12 +130,12 @@ No modules.
 | <a name="input_gpu_node_pool_max_count"></a> [gpu\_node\_pool\_max\_count](#input\_gpu\_node\_pool\_max\_count) | Max count of nodes in Default GPU pool | `number` | `5` | no |
 | <a name="input_gpu_node_pool_min_count"></a> [gpu\_node\_pool\_min\_count](#input\_gpu\_node\_pool\_min\_count) | Min count of number of nodes in Default GPU pool | `number` | `2` | no |
 | <a name="input_gpu_operator_namespace"></a> [gpu\_operator\_namespace](#input\_gpu\_operator\_namespace) | The namespace to deploy the NVIDIA GPU operator into | `string` | `"gpu-operator"` | no |
-| <a name="input_gpu_operator_version"></a> [gpu\_operator\_version](#input\_gpu\_operator\_version) | Version of the GPU operator to be installed | `string` | `"v23.6.1"` | no |
+| <a name="input_gpu_operator_version"></a> [gpu\_operator\_version](#input\_gpu\_operator\_version) | Version of the GPU operator to be installed | `string` | `"v23.9.1"` | no |
 | <a name="input_gpu_os_sku"></a> [gpu\_os\_sku](#input\_gpu\_os\_sku) | Specifies the OS SKU used by the agent pool. Possible values include: Ubuntu, CBLMariner, Mariner, Windows2019, Windows2022 | `string` | `"Ubuntu"` | no |
-| <a name="input_kubernetes_version"></a> [kubernetes\_version](#input\_kubernetes\_version) | Version of Kubernetes to turn on. Run 'az aks get-versions --location <location> --output table' to view all available versions | `string` | `"1.27"` | no |
+| <a name="input_kubernetes_version"></a> [kubernetes\_version](#input\_kubernetes\_version) | Version of Kubernetes to turn on. Run 'az aks get-versions --location <location> --output table' to view all available versions | `string` | `"1.28"` | no |
 | <a name="input_location"></a> [location](#input\_location) | The region to create resources in | `any` | n/a | yes |
 | <a name="input_nvaie"></a> [nvaie](#input\_nvaie) | To use the versions of GPU operator and drivers specified as part of NVIDIA AI Enterprise, set this to true. More information at https://www.nvidia.com/en-us/data-center/products/ai-enterprise | `bool` | `false` | no |
-| <a name="input_nvaie_gpu_operator_version"></a> [nvaie\_gpu\_operator\_version](#input\_nvaie\_gpu\_operator\_version) | The NVIDIA Driver version of GPU Operator. Overrides `gpu_operator_version` when `nvaie` is set to `true` | `string` | `"v23.3.2"` | no |
+| <a name="input_nvaie_gpu_operator_version"></a> [nvaie\_gpu\_operator\_version](#input\_nvaie\_gpu\_operator\_version) | The NVIDIA Driver version of GPU Operator. Overrides `gpu_operator_version` when `nvaie` is set to `true` | `string` | `"v23.9.0"` | no |
 
 ## Outputs
 

aks/terraform.tfvars

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
 # Sample tfvars file. Uncomment out values to use
@@ -19,9 +19,9 @@
 # gpu_node_pool_max_count      = 5
 # gpu_node_pool_min_count      = 2
 # gpu_operator_namespace       = "gpu-operator"
-# gpu_operator_version         = "v23.6.1"
+# gpu_operator_version         = "v23.9.1"
 # gpu_os_sku                   = "Ubuntu"
-# kubernetes_version           = "1.26.3"
+# kubernetes_version           = "1.28"
 # location                     = ""
 # nvaie                        = false
-# nvaie_gpu_operator_version   = "v23.3.2"
+# nvaie_gpu_operator_version   = "v23.9.0"

aks/variables.tf

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
 /****************************
@@ -25,7 +25,7 @@ variable "cluster_name" {
 }
 
 variable "kubernetes_version" {
-  default     = "1.27"
+  default     = "1.28"
   description = "Version of Kubernetes to turn on. Run 'az aks get-versions --location <location> --output table' to view all available versions "
 }
 
@@ -87,7 +87,7 @@ variable "gpu_os_sku" {
 GPU Operator Variables
 ****************************/
 variable "gpu_operator_version" {
-  default     = "v23.6.1"
+  default     = "v23.9.1"
   description = "Version of the GPU operator to be installed"
 }
 
@@ -105,7 +105,7 @@ variable "nvaie" {
 
 variable "nvaie_gpu_operator_version" {
   type        = string
-  default     = "v23.3.2"
+  default     = "v23.9.0"
   description = "The NVIDIA Driver version of GPU Operator. Overrides `gpu_operator_version` when `nvaie` is set to `true`"
 }
 

eks/README.md

@@ -118,7 +118,7 @@ To create a cluster with everything needed to run the Cloud Native Service Add-o
 | <a name="input_aws_profile"></a> [aws\_profile](#input\_aws\_profile) | n/a | `string` | `"development"` | no |
 | <a name="input_cidr_block"></a> [cidr\_block](#input\_cidr\_block) | CIDR for VPC | `string` | `"10.0.0.0/16"` | no |
 | <a name="input_cluster_name"></a> [cluster\_name](#input\_cluster\_name) | n/a | `string` | n/a | yes |
-| <a name="input_cluster_version"></a> [cluster\_version](#input\_cluster\_version) | Version of EKS to install on the control plane (Major and Minor version only, do not include the patch) | `string` | `"1.27"` | no |
+| <a name="input_cluster_version"></a> [cluster\_version](#input\_cluster\_version) | Version of EKS to install on the control plane (Major and Minor version only, do not include the patch) | `string` | `"1.28"` | no |
 | <a name="input_cpu_instance_type"></a> [cpu\_instance\_type](#input\_cpu\_instance\_type) | CPU EC2 worker node instance type | `string` | `"t2.xlarge"` | no |
 | <a name="input_cpu_node_pool_additional_user_data"></a> [cpu\_node\_pool\_additional\_user\_data](#input\_cpu\_node\_pool\_additional\_user\_data) | User data that is appended to the user data script after of the EKS bootstrap script on EKS-managed GPU node pool. | `string` | `""` | no |
 | <a name="input_cpu_node_pool_delete_on_termination"></a> [cpu\_node\_pool\_delete\_on\_termination](#input\_cpu\_node\_pool\_delete\_on\_termination) | Delete the VM nodes root filesystem on each node of the instance type. This is set to true by default, but can be changed when desired when using the 'local-storage provisioner' and are keeping important application data on the nodes | `bool` | `true` | no |
@@ -136,18 +136,18 @@ To create a cluster with everything needed to run the Cloud Native Service Add-o
 | <a name="input_gpu_node_pool_delete_on_termination"></a> [gpu\_node\_pool\_delete\_on\_termination](#input\_gpu\_node\_pool\_delete\_on\_termination) | Delete the VM nodes root filesystem on each node of the instance type. This is set to true by default, but can be changed when desired when using the 'local-storage provisioner' and are keeping important application data on the nodes | `bool` | `true` | no |
 | <a name="input_gpu_node_pool_root_disk_size_gb"></a> [gpu\_node\_pool\_root\_disk\_size\_gb](#input\_gpu\_node\_pool\_root\_disk\_size\_gb) | The size of the root disk on all GPU nodes in the EKS-managed GPU-only Node Pool. This is primarily for container image storage on the node | `number` | `512` | no |
 | <a name="input_gpu_node_pool_root_volume_type"></a> [gpu\_node\_pool\_root\_volume\_type](#input\_gpu\_node\_pool\_root\_volume\_type) | The type of disk to use for the GPU node pool root disk (eg. gp2, gp3). Note, this is different from the type of disk used by applications via EKS Storage classes/PVs & PVCs | `string` | `"gp2"` | no |
-| <a name="input_gpu_operator_driver_version"></a> [gpu\_operator\_driver\_version](#input\_gpu\_operator\_driver\_version) | The NVIDIA Driver version deployed with GPU Operator. Defaults to latest available. Not set when `nvaie` is set to true | `string` | `"535.104.05"` | no |
+| <a name="input_gpu_operator_driver_version"></a> [gpu\_operator\_driver\_version](#input\_gpu\_operator\_driver\_version) | The NVIDIA Driver version deployed with GPU Operator. Defaults to latest available. Not set when `nvaie` is set to true | `string` | `"535.129.03"` | no |
 | <a name="input_gpu_operator_namespace"></a> [gpu\_operator\_namespace](#input\_gpu\_operator\_namespace) | The namespace for the GPU operator deployment | `string` | `"gpu-operator"` | no |
-| <a name="input_gpu_operator_version"></a> [gpu\_operator\_version](#input\_gpu\_operator\_version) | Version of the GPU Operator to deploy. Defaults to latest available. Not set when `nvaie` is set to `true` | `string` | `"v23.6.1"` | no |
+| <a name="input_gpu_operator_version"></a> [gpu\_operator\_version](#input\_gpu\_operator\_version) | Version of the GPU Operator to deploy. Defaults to latest available. Not set when `nvaie` is set to `true` | `string` | `"v23.9.1"` | no |
 | <a name="input_max_cpu_nodes"></a> [max\_cpu\_nodes](#input\_max\_cpu\_nodes) | Maximum number of CPU nodes in the Autoscaling Group | `string` | `"2"` | no |
 | <a name="input_max_gpu_nodes"></a> [max\_gpu\_nodes](#input\_max\_gpu\_nodes) | Maximum number of GPU nodes in the Autoscaling Group | `string` | `"5"` | no |
 | <a name="input_min_cpu_nodes"></a> [min\_cpu\_nodes](#input\_min\_cpu\_nodes) | Minimum number of CPU nodes in the Autoscaling Group | `string` | `"0"` | no |
 | <a name="input_min_gpu_nodes"></a> [min\_gpu\_nodes](#input\_min\_gpu\_nodes) | Minimum number of GPU nodes in the Autoscaling Group | `string` | `"2"` | no |
 | <a name="input_nvaie"></a> [nvaie](#input\_nvaie) | To use the versions of GPU operator and drivers specified as part of NVIDIA AI Enterprise, set this to true. More information at https://www.nvidia.com/en-us/data-center/products/ai-enterprise | `bool` | `false` | no |
-| <a name="input_nvaie_gpu_operator_driver_version"></a> [nvaie\_gpu\_operator\_driver\_version](#input\_nvaie\_gpu\_operator\_driver\_version) | The NVIDIA AI Enterprise version of the NVIDIA driver to be installed with the GPU operator. Overrides `gpu_operator_driver_version` when `nvaie` is set to `true` | `string` | `"525.125.06"` | no |
-| <a name="input_nvaie_gpu_operator_version"></a> [nvaie\_gpu\_operator\_version](#input\_nvaie\_gpu\_operator\_version) | The NVIDIA Driver version of GPU Operator. Overrides `gpu_operator_version` when `nvaie` is set to `true` | `string` | `"v23.3.2"` | no |
-| <a name="input_private_subnets"></a> [private\_subnets](#input\_private\_subnets) | List of subnet ranges for the Holoscan VPC | `list(any)` | <pre>[<br>  "10.0.1.0/24",<br>  "10.0.2.0/24",<br>  "10.0.3.0/24"<br>]</pre> | no |
-| <a name="input_public_subnets"></a> [public\_subnets](#input\_public\_subnets) | List of subnet ranges for the Holoscan VPC | `list(any)` | <pre>[<br>  "10.0.4.0/24",<br>  "10.0.5.0/24",<br>  "10.0.6.0/24"<br>]</pre> | no |
+| <a name="input_nvaie_gpu_operator_driver_version"></a> [nvaie\_gpu\_operator\_driver\_version](#input\_nvaie\_gpu\_operator\_driver\_version) | The NVIDIA AI Enterprise version of the NVIDIA driver to be installed with the GPU operator. Overrides `gpu_operator_driver_version` when `nvaie` is set to `true` | `string` | `"535.129.03"` | no |
+| <a name="input_nvaie_gpu_operator_version"></a> [nvaie\_gpu\_operator\_version](#input\_nvaie\_gpu\_operator\_version) | The NVIDIA Driver version of GPU Operator. Overrides `gpu_operator_version` when `nvaie` is set to `true` | `string` | `"v23.9.0"` | no |
+| <a name="input_private_subnets"></a> [private\_subnets](#input\_private\_subnets) | List of subnet ranges for the Holoscan VPC | `list(any)` | <pre>[<br>  "10.0.0.0/19",<br>  "10.0.32.0/19",<br>  "10.0.64.0/19"<br>]</pre> | no |
+| <a name="input_public_subnets"></a> [public\_subnets](#input\_public\_subnets) | List of subnet ranges for the Holoscan VPC | `list(any)` | <pre>[<br>  "10.0.96.0/19",<br>  "10.0.128.0/19",<br>  "10.0.160.0/19"<br>]</pre> | no |
 | <a name="input_region"></a> [region](#input\_region) | AWS region to provision the Holoscan Compliant Kubernetes Cluster | `string` | `"us-west-2"` | no |
 | <a name="input_single_nat_gateway"></a> [single\_nat\_gateway](#input\_single\_nat\_gateway) | Should be true if you want to provision a single shared NAT Gateway across all of your private networks | `bool` | `false` | no |
 | <a name="input_ssh_key"></a> [ssh\_key](#input\_ssh\_key) | n/a | `string` | `""` | no |
@@ -166,4 +166,4 @@ To create a cluster with everything needed to run the Cloud Native Service Add-o
 | <a name="output_nodes"></a> [nodes](#output\_nodes) | n/a |
 | <a name="output_oidc_endpoint"></a> [oidc\_endpoint](#output\_oidc\_endpoint) | n/a |
 | <a name="output_private_subnet_ids"></a> [private\_subnet\_ids](#output\_private\_subnet\_ids) | n/a |
-| <a name="output_public_subnet_ids"></a> [public\_subnet\_ids](#output\_public\_subnet\_ids) | n/a |
+| <a name="output_public_subnet_ids"></a> [public\_subnet\_ids](#output\_public\_subnet\_ids) | n/a |

eks/examples/cnpack/aws-pca.tf

@@ -7,8 +7,8 @@ AWS Private Cert Authority Config
 
 // Create AWS Private Cert Authority
 resource "aws_acmpca_certificate_authority" "cnpack-pca" {
-  count = var.pca_enabled ? 1 : 0
-  type  = "ROOT"
+  count      = var.pca_enabled ? 1 : 0
+  type       = "ROOT"
   usage_mode = var.pca_short_lived ? "SHORT_LIVED_CERTIFICATE" : "GENERAL_PURPOSE"
   certificate_authority_configuration {
     key_algorithm     = "RSA_4096"

eks/terraform.tfvars

@@ -1,11 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
-# SPDX-License-Identifier: Apache-2.0
-
-# Sample tfvars file. Uncomment out values to use
-# Do not commit this file to Git with sensitive values
-
-
-# SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
 # Sample tfvars file. Uncomment out values to use
@@ -17,7 +10,7 @@
 # aws_profile                           = "development"
 # cidr_block                            = "10.0.0.0/16"
 # cluster_name                          = ""
-# cluster_version                       = "1.26"
+# cluster_version                       = "1.28"
 # cpu_instance_type                     = "t2.xlarge"
 # cpu_node_pool_additional_user_data    = ""
 # cpu_node_pool_delete_on_termination   = true
@@ -35,25 +28,25 @@
 # gpu_node_pool_delete_on_termination   = true
 # gpu_node_pool_root_disk_size_gb       = 512
 # gpu_node_pool_root_volume_type        = "gp2"
-# gpu_operator_driver_version           = "535.104.05"
+# gpu_operator_driver_version           = "535.129.03"
 # gpu_operator_namespace                = "gpu-operator"
-# gpu_operator_version                  = "v23.6.1"
+# gpu_operator_version                  = "v23.9.1"
 # max_cpu_nodes                         = "2"
 # max_gpu_nodes                         = "5"
 # min_cpu_nodes                         = "0"
 # min_gpu_nodes                         = "2"
 # nvaie                                 = false
-# nvaie_gpu_operator_driver_version     = "525.125.06"
-# nvaie_gpu_operator_version            = "v23.3.2"
+# nvaie_gpu_operator_driver_version     = "535.129.03"
+# nvaie_gpu_operator_version            = "v23.9.0"
 # private_subnets = [
-#   "10.0.1.0/24",
-#   "10.0.2.0/24",
-#   "10.0.3.0/24"
+#   "10.0.0.0/19",
+#   "10.0.32.0/19",
+#   "10.0.64.0/19"
 # ]
 # public_subnets = [
-#   "10.0.4.0/24",
-#   "10.0.5.0/24",
-#   "10.0.6.0/24"
+#   "10.0.96.0/19",
+#   "10.0.128.0/19",
+#   "10.0.160.0/19"
 # ]
 # region             = "us-west-2"
 # single_nat_gateway = false

eks/variables.tf

@@ -1,4 +1,4 @@
-# SPDX-FileCopyrightText: Copyright (c) 2022-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
 /************************
@@ -28,20 +28,20 @@ variable "cluster_name" {
 
 variable "cluster_version" {
   type        = string
-  default     = "1.27"
+  default     = "1.28"
   description = "Version of EKS to install on the control plane (Major and Minor version only, do not include the patch)"
 }
 /************************
   GPU Operator Variables
 *************************/
 variable "gpu_operator_version" {
-  default     = "v23.6.1"
+  default     = "v23.9.1"
   description = "Version of the GPU Operator to deploy. Defaults to latest available. Not set when `nvaie` is set to `true`"
 }
 
 variable "gpu_operator_driver_version" {
   type        = string
-  default     = "535.104.05"
+  default     = "535.129.03"
   description = "The NVIDIA Driver version deployed with GPU Operator. Defaults to latest available. Not set when `nvaie` is set to true"
 }
 
@@ -59,13 +59,13 @@ variable "nvaie" {
 
 variable "nvaie_gpu_operator_version" {
   type        = string
-  default     = "v23.3.2"
+  default     = "v23.9.0"
   description = "The NVIDIA Driver version of GPU Operator. Overrides `gpu_operator_version` when `nvaie` is set to `true`"
 }
 
 variable "nvaie_gpu_operator_driver_version" {
   type        = string
-  default     = "525.125.06"
+  default     = "535.129.03"
   description = "The NVIDIA AI Enterprise version of the NVIDIA driver to be installed with the GPU operator. Overrides `gpu_operator_driver_version` when `nvaie` is set to `true`"
 }
 /*****************************