llm-inference-multimodel: add Qwen2.5-14B shadow instance (port 8002, gated off — VRAM co-residency not yet confirmed)

- New llama-server-qwen systemd unit template, gated by llm_qwen_service_enabled (default false)
- Idempotent GGUF download task (bartowski Qwen2.5-14B-Instruct-Q5_K_M, stat-guarded)
- Launch flags per local-llm-64k-context-recommendation.md: ctx-size 65536, flash-attn, q8_0 KV cache, batch 2048/ubatch 512, jinja, parallel 1
- verify.yml only starts/verifies the qwen unit when llm_qwen_service_enabled=true
- README: documents live VRAM gate finding (nvidia-smi 2026-08-06: Phi-4+Mistral already ~16.6/24GB, ~7.5GB free -- insufficient for Qwen weights concurrently) and options
- Does NOT touch llama-server-aux (8000) or llama-server-toolcall (8001) service state

ansible/roles/llm-inference-multimodel/tasks/systemd.yml

@@ -41,6 +41,18 @@
   notify:
     - reload systemd
 
+- name: Deploy llama-server-qwen systemd unit (shadow, port 8002)
+  ansible.builtin.template:
+    src: llama-server-qwen.service.j2
+    dest: "/etc/systemd/system/{{ llm_qwen_service_name }}.service"
+    owner: root
+    group: root
+    mode: "0644"
+  become: true
+  register: llm_qwen_unit_deployed
+  notify:
+    - reload systemd
+
 - name: Flush handlers so daemon-reload lands before any later phase acts on unit state
   ansible.builtin.meta: flush_handlers