feat: initial commit — Ansible roles storage-01/gpu-01 opérationnels

ansible/roles/rocm/defaults/main.yml

@@ -0,0 +1,25 @@
+---
+rocm_rhel_version: "9.4"
+rocm_amdgpu_repo: "https://repo.radeon.com/amdgpu/latest/rhel/{{ rocm_rhel_version }}/main/x86_64/"
+rocm_repo: "https://repo.radeon.com/rocm/rhel9/latest/main/"
+rocm_gpg_key: "https://repo.radeon.com/rocm/rocm.gpg.key"
+
+rocm_packages:
+  - rocminfo
+  - rocm-hip-runtime
+  - rocm-opencl-runtime
+  - rocblas
+  - hipblaslt
+
+# Packages supplémentaires requis pour compiler llama.cpp from source (rôle llama_server)
+rocm_build_packages:
+  - hipblas-devel
+  - rocblas-devel
+  - hip-devel
+  - hipcc
+  - cmake
+  - gcc-c++
+  - git
+  - patchelf
+
+hsa_override_gfx_version: "10.3.0"

ansible/roles/rocm/handlers/main.yml

@@ -0,0 +1,6 @@
+---
+- name: Reload amdgpu module
+  ansible.builtin.shell: |
+    modprobe -r amdgpu || true
+    modprobe amdgpu
+  changed_when: true

ansible/roles/rocm/tasks/main.yml

@@ -0,0 +1,60 @@
+---
+- name: Import AMD GPG key
+  ansible.builtin.rpm_key:
+    key: "{{ rocm_gpg_key }}"
+    state: present
+
+- name: Add amdgpu repository
+  ansible.builtin.yum_repository:
+    name: amdgpu
+    description: AMD GPU drivers
+    baseurl: "{{ rocm_amdgpu_repo }}"
+    enabled: true
+    gpgcheck: true
+    gpgkey: "{{ rocm_gpg_key }}"
+
+- name: Add ROCm repository
+  ansible.builtin.yum_repository:
+    name: rocm
+    description: ROCm
+    baseurl: "{{ rocm_repo }}"
+    enabled: true
+    gpgcheck: true
+    gpgkey: "{{ rocm_gpg_key }}"
+
+- name: Install kernel headers and devel (requis pour amdgpu-dkms)
+  ansible.builtin.dnf:
+    name:
+      - kernel-headers
+      - kernel-devel
+    state: present
+
+- name: Install ROCm packages
+  ansible.builtin.dnf:
+    name: "{{ rocm_packages }}"
+    state: present
+  notify: Reload amdgpu module
+
+- name: Add ansible user to video and render groups
+  ansible.builtin.user:
+    name: "{{ ansible_service_user }}"
+    groups:
+      - video
+      - render
+    append: true
+
+- name: Set HSA_OVERRIDE_GFX_VERSION system-wide
+  ansible.builtin.lineinfile:
+    path: /etc/environment
+    regexp: '^HSA_OVERRIDE_GFX_VERSION='
+    line: "HSA_OVERRIDE_GFX_VERSION={{ hsa_override_gfx_version }}"
+    create: true
+    mode: '0644'
+
+- name: Set HSA_OVERRIDE_GFX_VERSION dans profile.d (sessions interactives)
+  ansible.builtin.copy:
+    dest: /etc/profile.d/rocm.sh
+    content: |
+      export HSA_OVERRIDE_GFX_VERSION={{ hsa_override_gfx_version }}
+      export PATH=$PATH:/opt/rocm/bin
+    mode: '0644'