feat(ansible): upgrade for CUDA, TensorRT and CUDNN (autowarefoundation#5608)

Author: amadeuszsz

amd64.env

@@ -3,7 +3,7 @@ rmw_implementation=rmw_cyclonedds_cpp
 base_image=ros:humble-ros-base-jammy
 autoware_base_image=ghcr.io/autowarefoundation/autoware-base:latest
 autoware_base_cuda_image=ghcr.io/autowarefoundation/autoware-base:cuda-latest
-cuda_version=12.3
-cudnn_version=8.9.5.29-1+cuda12.2
-tensorrt_version=8.6.1.6-1+cuda12.0
+cuda_version=12.4
+cudnn_version=8.9.7.29-1+cuda12.2
+tensorrt_version=10.8.0.43-1+cuda12.8
 pre_commit_clang_format_version=17.0.5

ansible/roles/cuda/README.md

@@ -1,6 +1,6 @@
 # cuda
 
-This role installs [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit) following [this page](https://developer.nvidia.com/cuda-12-3-0-download-archive?target_os=Linux&target_arch=x86_64&Distribution=Ubuntu&target_version=22.04&target_type=deb_network) and [this page](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#post-installation-actions).
+This role installs [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit) following [this page](https://developer.nvidia.com/cuda-12-4-0-download-archive?target_os=Linux&target_arch=x86_64&Distribution=Ubuntu&target_version=22.04&target_type=deb_network) and [this page](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#post-installation-actions).
 
 This role also registers Vulkan, OpenGL, and OpenCL GPU vendors for future use.
 
@@ -15,7 +15,7 @@ This role also registers Vulkan, OpenGL, and OpenCL GPU vendors for future use.
 
 ### Version compatibility
 
-Autoware currently uses CUDA `12.3` and from this [CUDA Application Compatibility Support Matrix](https://docs.nvidia.com/deploy/cuda-compatibility/#use-the-right-compat-package) that only the NVIDIA driver version `545` is compatible with this version of CUDA.
+Autoware currently uses CUDA `12.4` which corresponds to the NVIDIA driver version `550` and is minimum required driver version.
 
 #### 🛠️ For Advanced Users
 
@@ -42,7 +42,7 @@ sudo dpkg -i cuda-keyring_1.1-1_all.deb
 sudo apt-get update
 cuda_version_dashed=$(eval sed -e "s/[.]/-/g" <<< "${cuda_version}")
 sudo apt-get -y install cuda-toolkit-${cuda_version_dashed}
-sudo apt-get install -y cuda-drivers-545
+sudo apt-get install -y cuda-drivers-550
 ```
 
 Perform the post installation actions:

ansible/roles/tensorrt/README.md

@@ -11,34 +11,63 @@ This role installs TensorRT and cuDNN following [the official NVIDIA TensorRT In
 
 ## Manual Installation
 
+### AMD64
+
 ```bash
 # For the environment variables
 wget -O /tmp/amd64.env https://raw.githubusercontent.com/autowarefoundation/autoware/main/amd64.env && source /tmp/amd64.env
 
 sudo apt-get install -y \
 libcudnn8=${cudnn_version} \
-libnvinfer8=${tensorrt_version} \
-libnvinfer-plugin8=${tensorrt_version} \
-libnvparsers8=${tensorrt_version} \
-libnvonnxparsers8=${tensorrt_version} \
+libnvinfer10=${tensorrt_version} \
+libnvinfer-plugin10=${tensorrt_version} \
+libnvonnxparsers10=${tensorrt_version} \
 libcudnn8-dev=${cudnn_version} \
 libnvinfer-dev=${tensorrt_version} \
 libnvinfer-plugin-dev=${tensorrt_version} \
 libnvinfer-headers-dev=${tensorrt_version} \
 libnvinfer-headers-plugin-dev=${tensorrt_version} \
-libnvparsers-dev=${tensorrt_version} \
 libnvonnxparsers-dev=${tensorrt_version}
 
 sudo apt-mark hold \
 libcudnn8 \
-libnvinfer8 \
-libnvinfer-plugin8 \
-libnvparsers8 \
-libnvonnxparsers8 \
+libnvinfer10 \
+libnvinfer-plugin10 \
+libnvonnxparsers10 \
 libcudnn8-dev \
 libnvinfer-dev \
 libnvinfer-plugin-dev \
-libnvparsers-dev \
+libnvonnxparsers-dev \
+libnvinfer-headers-dev \
+libnvinfer-headers-plugin-dev
+```
+
+### ARM64
+
+```bash
+# For the environment variables
+wget -O /tmp/arm64.env https://raw.githubusercontent.com/autowarefoundation/autoware/main/arm64.env && source /tmp/arm64.env
+
+sudo apt-get install -y \
+libcudnn9-cuda-12=${cudnn_version} \
+libnvinfer10=${tensorrt_version} \
+libnvinfer-plugin10=${tensorrt_version} \
+libnvonnxparsers10=${tensorrt_version} \
+libcudnn9-dev-cuda-12=${cudnn_version} \
+libnvinfer-dev=${tensorrt_version} \
+libnvinfer-plugin-dev=${tensorrt_version} \
+libnvinfer-headers-dev=${tensorrt_version} \
+libnvinfer-headers-plugin-dev=${tensorrt_version} \
+libnvonnxparsers-dev=${tensorrt_version}
+
+sudo apt-mark hold \
+libcudnn9-cuda-12 \
+libnvinfer10 \
+libnvinfer-plugin10 \
+libnvonnxparsers10 \
+libcudnn9-dev-cuda-12 \
+libnvinfer-dev \
+libnvinfer-plugin-dev \
 libnvonnxparsers-dev \
 libnvinfer-headers-dev \
 libnvinfer-headers-plugin-dev

ansible/roles/tensorrt/tasks/main.yaml

@@ -2,11 +2,10 @@
   become: true
   ansible.builtin.apt:
     name:
-      - libcudnn8={{ cudnn_version }}
-      - libnvinfer8={{ tensorrt_version }}
-      - libnvinfer-plugin8={{ tensorrt_version }}
-      - libnvparsers8={{ tensorrt_version }}
-      - libnvonnxparsers8={{ tensorrt_version }}
+      - "{{ 'libcudnn9-cuda-12=' + cudnn_version if ansible_architecture == 'aarch64' else 'libcudnn8=' + cudnn_version }}"
+      - libnvinfer10={{ tensorrt_version }}
+      - libnvinfer-plugin10={{ tensorrt_version }}
+      - libnvonnxparsers10={{ tensorrt_version }}
     allow_change_held_packages: true
     allow_downgrade: true
     update_cache: true
@@ -15,12 +14,11 @@
   become: true
   ansible.builtin.apt:
     name:
-      - libcudnn8-dev={{ cudnn_version }}
+      - "{{ 'libcudnn9-dev-cuda-12=' + cudnn_version if ansible_architecture == 'aarch64' else 'libcudnn8-dev=' + cudnn_version }}"
       - libnvinfer-dev={{ tensorrt_version }}
       - libnvinfer-plugin-dev={{ tensorrt_version }}
       - libnvinfer-headers-dev={{ tensorrt_version }}
       - libnvinfer-headers-plugin-dev={{ tensorrt_version }}
-      - libnvparsers-dev={{ tensorrt_version }}
       - libnvonnxparsers-dev={{ tensorrt_version }}
     allow_change_held_packages: true
     allow_downgrade: true
@@ -34,23 +32,22 @@
     name: "{{ item }}"
     selection: hold
   with_items:
+    - "{{ 'libcudnn9-cuda-12' if ansible_architecture == 'aarch64' else 'libcudnn8' }}"
     - libcudnn8
-    - libnvinfer8
-    - libnvinfer-plugin8
-    - libnvparsers8
-    - libnvonnxparsers8
+    - libnvinfer10
+    - libnvinfer-plugin10
+    - libnvonnxparsers10
 
 - name: Prevent CUDA-related Dev packages from upgrading
   become: true
   ansible.builtin.dpkg_selections:
     name: "{{ item }}"
     selection: hold
   with_items:
-    - libcudnn8-dev
+    - "{{ 'libcudnn9-dev-cuda-12' if ansible_architecture == 'aarch64' else 'libcudnn8-dev' }}"
     - libnvinfer-dev
     - libnvinfer-plugin-dev
     - libnvinfer-headers-dev
     - libnvinfer-headers-plugin-dev
-    - libnvparsers-dev
     - libnvonnxparsers-dev
   when: install_devel == 'y'

arm64.env

@@ -1,3 +1,3 @@
 # Override amd64's settings
-cudnn_version=8.9.6.50-1+cuda12.2
-tensorrt_version=8.6.2.2-1+cuda12.0
+cudnn_version=9.3.0.75-1
+tensorrt_version=10.3.0.30-1+cuda12.5