feat: MI50 as a Lyra backend (OpenAI-compatible local GPU)

The MI50 box (CT202) runs an OpenAI-compatible llama.cpp server on
10.0.0.44:8080. Wire it in as a third backend:

- llm.complete gains backend="mi50" (OpenAI client pointed at MI50_BASE_URL)
- config: MI50_BASE_URL (default http://10.0.0.44:8080/v1) + MI50_MODEL
- chat.respond labels the model per backend; web _backend_for maps "mi50"
- UI backend selector adds "MI50 — local GPU"

Verified end-to-end: llm.complete(backend="mi50") returns from the live server.
See homelab-inference memory for the box topology.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lyra/web/static/index.html

@@ -123,6 +123,11 @@
               <span>Local — Ollama</span>
               <small>Free, private, runs on your home lab (LOCAL_MODEL)</small>
             </label>
+            <label class="radio-label">
+              <input type="radio" name="backend" value="mi50">
+              <span>MI50 — local GPU</span>
+              <small>Free, llama.cpp on the MI50 box (MI50_BASE_URL)</small>
+            </label>
             <label class="radio-label">
               <input type="radio" name="backend" value="cloud">
               <span>Cloud — OpenAI</span>