Files
infrastructure/llm-server/llm/ansible/roles/inference_engine/tasks/main.yml
T
spektr 026c840029 LLM-Server: M2-Vertical-Slice in Betrieb - Swift-Stack läuft, Inferenz nachgewiesen
Erster produktiver Start des llama.cpp-Testing-Stacks auf ghostnet-ki
(31.10.2026). Fix-Liste aus den Live-Läufen:
- Quadlet-Exec ohne Binärnamen (AMD-Image hat ENTRYPOINT /app/llama-server;
  GNAI-010 v0.6 dokumentiert den Befund)
- Deterministischer daemon-reload vor Unit-Zugriff (Handler allein griff nicht,
  wenn ein vorheriger Lauf die Quadlets gerendert hatte)
- Netz-Abhängigkeit Wants/After im Container-Quadlet (Netzwerk-Unit wurde
  nie mitgestartet -> network not found)
- Stopp-Bedingung für Profilwechsel korrigiert (nur aktive Units stoppen)
- Health-Tool-Kette curl/wget/bash-/dev/tcp mit Pfad-Normalisierung; curl -f
  als Gesundheitssignal (Statuszeile stand nie im stdout)
- chdir für alle runuser-Aufrufe der Health-Checks

Nachweise: Health 200 OK, /v1/models Alias korrekt, Idempotenz changed=0,
VRAM 12,6/13,0 GiB von je 16 GiB auf beiden Karten (Layer-Split 1:1),
echte Chat-Completion mit System-Fingerprint des gepinnten Builds,
Reasoning getrennt von der Antwort.

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
2026-11-01 17:32:17 +01:00

444 lines
14 KiB
YAML

---
# Deploys the inference engine (llama.cpp profile) for one environment
# (GNAI-010 sections 5, 6 and 9). Rendering and provisioning run under the
# `service` tag, model artifacts under the `models` tag of the model_store
# role. The selected unit is only started by the explicit switch/start tasks
# below and is never enabled for default.target (GNAI-010 section 5.3).
- name: Validate inference engine declarations
ansible.builtin.assert:
that:
- inference_engine_user | length > 0
- inference_engine_uid | int > 0
- inference_engine_user_home is match("^/")
- inference_engine_unit_prefix | length > 0
- inference_engine_network_name | length > 0
- inference_engine_image_ref is match("^ghcr\\.io/.+@sha256:[0-9a-f]{64}$")
- inference_engine_image_revision is match("^[0-9a-f]{40}$")
- inference_engine_profiles | length >= 2
- inference_engine_active_profile in inference_engine_profiles
- model_store_root is match("^/")
fail_msg: Inference engine declarations are incomplete or ambiguous.
tags:
- service
- name: Derive the systemd unit name of every profile
ansible.builtin.set_fact:
inference_engine_unit_names: >-
{{ inference_engine_unit_names | default({})
| combine({ item.key:
inference_engine_unit_prefix ~ '-' ~ item.value.unit_suffix }) }}
loop: "{{ inference_engine_profiles | dict2items }}"
loop_control:
label: "{{ item.key }}"
tags:
- service
- name: Require the rootless runtime utilities
ansible.builtin.stat:
path: "{{ item }}"
loop:
- /usr/sbin/runuser
- /usr/bin/podman
- /usr/bin/systemctl
- "{{ inference_engine_generator_path }}"
register: inference_engine_tools
tags:
- service
- name: Verify the rootless runtime utilities are executable
ansible.builtin.assert:
that:
- inference_engine_tools.results | selectattr('stat.exists') | list | length
== inference_engine_tools.results | length
- inference_engine_tools.results | selectattr('stat.executable', 'equalto', true) | list | length
== inference_engine_tools.results | length
fail_msg: >-
A required rootless runtime utility is missing or not executable
(runuser, podman, systemctl or the Podman system generator); run the
host baseline roles first (llm-server/host/ansible).
tags:
- service
- name: Require the KFD compute device
ansible.builtin.stat:
path: /dev/kfd
register: inference_engine_kfd
tags:
- service
- name: Discover the AMD render nodes
ansible.builtin.find:
paths: /dev/dri
patterns: renderD*
# Render nodes are character devices; the default file_type (file) would
# skip them.
file_type: any
register: inference_engine_render_node_find
tags:
- service
- name: Record the render nodes
ansible.builtin.set_fact:
inference_engine_render_nodes: >-
{{ inference_engine_render_node_find.files
| map(attribute='path') | sort }}
tags:
- service
- name: Verify KFD and exactly two render nodes
ansible.builtin.assert:
that:
- inference_engine_kfd.stat.exists
- inference_engine_render_nodes | length == 2
fail_msg: >-
Expected /dev/kfd and exactly two render nodes (2x RX 6900 XT
baseline); found {{ inference_engine_render_nodes | length }}
render node(s): {{ inference_engine_render_nodes }}.
tags:
- service
- name: Require every profile model artifact to be present
ansible.builtin.stat:
path: "{{ model_store_root }}/{{ item.value.model_directory }}/{{ item.value.model_file }}"
loop: "{{ inference_engine_profiles | dict2items }}"
loop_control:
label: "{{ item.key }}"
register: inference_engine_models
tags:
- service
- name: Verify every profile model artifact is present
ansible.builtin.assert:
that:
- inference_engine_models.results | selectattr('stat.exists', 'equalto', true) | list | length
== inference_engine_models.results | length
fail_msg: >-
Missing model artifacts under {{ model_store_root }}:
{{ inference_engine_models.results
| selectattr('stat.exists', 'equalto', false)
| map(attribute='item.key') | list | join(', ') }};
run the model_store role (--tags models) first.
# Check mode deliberately downloads nothing, so the preview continues and
# only shows the pending quadlet changes; a real run enforces presence.
when: not ansible_check_mode
tags:
- service
- name: Check whether the pinned engine image is in the workload store
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- /usr/bin/podman
- image
- exists
- "{{ inference_engine_image_ref }}"
chdir: "{{ inference_engine_user_home }}"
changed_when: false
failed_when: inference_engine_image_present.rc not in [0, 1]
check_mode: false
register: inference_engine_image_present
tags:
- service
- name: Pull the pinned engine image into the workload store
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- /usr/bin/podman
- pull
- "{{ inference_engine_image_ref }}"
chdir: "{{ inference_engine_user_home }}"
when:
- not ansible_check_mode
- inference_engine_image_present.rc != 0
tags:
- service
- name: Ensure the environment quadlet directory exists
ansible.builtin.file:
path: "{{ inference_engine_quadlet_dir }}"
state: directory
owner: root
group: root
mode: "0755"
tags:
- service
- name: Render the environment Podman network quadlet
ansible.builtin.template:
src: llama-cpp.network.j2
dest: "{{ inference_engine_quadlet_dir }}/{{ inference_engine_network_name }}.network"
owner: root
group: root
mode: "0644"
notify: Reload the workload user manager
tags:
- service
- name: Render one engine quadlet per model profile
ansible.builtin.template:
src: llama-server.container.j2
dest: "{{ inference_engine_quadlet_dir }}/{{ inference_engine_unit_names[quadlet_item.key] }}.container"
owner: root
group: root
mode: "0644"
vars:
entry:
profile_key: "{{ quadlet_item.key }}"
profile: "{{ quadlet_item.value }}"
unit_name: "{{ inference_engine_unit_names[quadlet_item.key] }}"
container_name: "{{ inference_engine_unit_names[quadlet_item.key] }}"
ctx_size: >-
{{ (inference_engine_ctx_size_override | int)
if inference_engine_ctx_size_override is not none
else quadlet_item.value.ctx_size }}
other_units: >-
{{ inference_engine_unit_names.values()
| difference([inference_engine_unit_names[quadlet_item.key]]) }}
loop: "{{ inference_engine_profiles | dict2items }}"
loop_control:
loop_var: quadlet_item
label: "{{ quadlet_item.key }}"
notify: Reload the workload user manager
tags:
- service
- name: Exercise the Quadlet generator without starting anything
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- "QUADLET_UNIT_DIRS={{ inference_engine_quadlet_dir }}"
- "{{ inference_engine_generator_path }}"
- --dryrun
chdir: "{{ inference_engine_user_home }}"
changed_when: false
when: not ansible_check_mode
tags:
- service
- name: Apply rendered quadlet changes before touching units
# The daemon-reload handler must run before unit states are read or units
# are started; otherwise systemd does not know the freshly rendered units
# and `is-active` exits with rc 4 (unknown unit).
ansible.builtin.meta: flush_handlers
tags:
- service
- name: Ensure the workload user manager knows the rendered units
# Deterministic reload: handler notifications only fire when a quadlet
# changed in the same run, but a previous run may have rendered units
# without reloading (failed run) — so reload unconditionally.
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- /usr/bin/systemctl
- --user
- daemon-reload
chdir: "{{ inference_engine_user_home }}"
changed_when: false
when: not ansible_check_mode
tags:
- service
- name: Read the current state of every engine unit
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- /usr/bin/systemctl
- --user
- is-active
- "{{ inference_engine_unit_names[item.key] }}"
chdir: "{{ inference_engine_user_home }}"
changed_when: false
failed_when: inference_engine_unit_states.rc not in [0, 3, 4]
check_mode: false
loop: "{{ inference_engine_profiles | dict2items }}"
loop_control:
label: "{{ item.key }}"
register: inference_engine_unit_states
when: not ansible_check_mode
tags:
- service
- name: Stop any other active engine unit before the switch
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- /usr/bin/systemctl
- --user
- stop
- "{{ inference_engine_unit_names[item.item.key] }}"
chdir: "{{ inference_engine_user_home }}"
when:
- not ansible_check_mode
- item.stdout | trim == 'active'
- item.item.key != inference_engine_active_profile
loop: "{{ inference_engine_unit_states.results }}"
loop_control:
label: "{{ item.item.key }}"
tags:
- service
- name: Start the selected engine unit
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- /usr/bin/systemctl
- --user
- start
- "{{ inference_engine_unit_names[inference_engine_active_profile] }}"
chdir: "{{ inference_engine_user_home }}"
when:
- not ansible_check_mode
- >-
(inference_engine_unit_states.results
| selectattr('item.key', 'equalto', inference_engine_active_profile)
| map(attribute='stdout') | join('') | trim) != 'active'
tags:
- service
- name: Detect an HTTP client inside the engine container
ansible.builtin.command:
argv:
- /usr/sbin/runuser
- --user
- "{{ inference_engine_user }}"
- --
- /usr/bin/env
- "HOME={{ inference_engine_user_home }}"
- "XDG_RUNTIME_DIR=/run/user/{{ inference_engine_uid }}"
- /usr/bin/podman
- exec
- "{{ inference_engine_unit_names[inference_engine_active_profile] }}"
- /bin/sh
- -c
- "command -v curl || command -v wget || command -v bash || true"
chdir: "{{ inference_engine_user_home }}"
changed_when: false
check_mode: false
register: inference_engine_http_client
when: not ansible_check_mode
tags:
- service
- name: Record the HTTP client for health checks
ansible.builtin.set_fact:
inference_engine_http_tool: "{{ inference_engine_http_client.stdout | split('/') | last | trim }}"
when: not ansible_check_mode
tags:
- service
- name: Require an HTTP client in the pinned engine image
ansible.builtin.assert:
that:
- inference_engine_http_tool in ['curl', 'wget', 'bash']
fail_msg: >-
The pinned engine image contains none of curl, wget or bash; health
checks cannot run (GNAI-010 section 8 requires checking the image
tool first; confirmed for this image 31.10.2026).
when: not ansible_check_mode
tags:
- service
- name: Wait for the engine health endpoint
ansible.builtin.command:
argv: >-
{{ ['/usr/sbin/runuser', '--user', inference_engine_user, '--',
'/usr/bin/env', 'HOME=' ~ inference_engine_user_home,
'XDG_RUNTIME_DIR=/run/user/' ~ inference_engine_uid,
'/usr/bin/podman', 'exec',
inference_engine_unit_names[inference_engine_active_profile],
'/bin/sh', '-c', health_cmd] }}
chdir: "{{ inference_engine_user_home }}"
vars:
health_cmd: >-
{{ inference_engine_curl_health_cmd if inference_engine_http_tool == 'curl'
else inference_engine_wget_health_cmd if inference_engine_http_tool == 'wget'
else inference_engine_bash_health_script }}
changed_when: false
check_mode: false
register: inference_engine_health
until: inference_engine_health.rc == 0
retries: 60
delay: 5
when: not ansible_check_mode
tags:
- service
- name: Verify the served model alias
ansible.builtin.command:
argv: >-
{{ ['/usr/sbin/runuser', '--user', inference_engine_user, '--',
'/usr/bin/env', 'HOME=' ~ inference_engine_user_home,
'XDG_RUNTIME_DIR=/run/user/' ~ inference_engine_uid,
'/usr/bin/podman', 'exec',
inference_engine_unit_names[inference_engine_active_profile],
'/bin/sh', '-c', models_cmd] }}
chdir: "{{ inference_engine_user_home }}"
vars:
models_cmd: >-
{{ inference_engine_curl_models_cmd if inference_engine_http_tool == 'curl'
else inference_engine_wget_models_cmd if inference_engine_http_tool == 'wget'
else inference_engine_bash_models_script }}
changed_when: false
check_mode: false
register: inference_engine_models_endpoint
when: not ansible_check_mode
tags:
- service
- name: Verify the active profile alias is served
ansible.builtin.assert:
that:
- >-
inference_engine_profiles[inference_engine_active_profile].alias
in inference_engine_models_endpoint.stdout
fail_msg: >-
The /v1/models response does not contain the expected alias
{{ inference_engine_profiles[inference_engine_active_profile].alias }}.
when: not ansible_check_mode
tags:
- service