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>

.env.example

@@ -2,6 +2,10 @@
 LOCAL_BASE_URL=http://localhost:11434
 LOCAL_MODEL=qwen2.5:7b-instruct
 
+# MI50 backend — OpenAI-compatible llama.cpp server on the home-lab GPU box.
+MI50_BASE_URL=http://10.0.0.44:8080/v1
+MI50_MODEL=local-gpu
+
 # Cloud backend (OpenAI) — higher quality, costs money.
 OPENAI_API_KEY=
 CLOUD_MODEL=gpt-4o-mini

lyra/chat.py

@@ -81,7 +81,9 @@ def build_messages(session_id: str, user_msg: str) -> list[Message]:
 def respond(session_id: str, user_msg: str, backend: Backend = "cloud") -> str:
     """Produce Lyra's reply to a single user message and persist the exchange."""
     cfg = config.load()
-    model = cfg.local_model if backend == "local" else cfg.cloud_model
+    model = {"local": cfg.local_model, "cloud": cfg.cloud_model, "mi50": cfg.mi50_model}.get(
+        backend, backend
+    )
     logbus.log(
         "info", "chat request", session=session_id, backend=backend,
         model=model, embed=cfg.embed_backend,

lyra/config.py

@@ -14,6 +14,8 @@ load_dotenv()
 class Config:
     local_base_url: str
     local_model: str
+    mi50_base_url: str  # OpenAI-compatible llama.cpp server on the MI50 box
+    mi50_model: str
     openai_api_key: str
     cloud_model: str
     embed_backend: str  # "cloud" (OpenAI) or "local" (Ollama)
@@ -27,6 +29,8 @@ def load() -> Config:
     return Config(
         local_base_url=os.getenv("LOCAL_BASE_URL", "http://localhost:11434"),
         local_model=os.getenv("LOCAL_MODEL", "qwen2.5:7b-instruct"),
+        mi50_base_url=os.getenv("MI50_BASE_URL", "http://10.0.0.44:8080/v1"),
+        mi50_model=os.getenv("MI50_MODEL", "local-gpu"),
         openai_api_key=os.getenv("OPENAI_API_KEY", ""),
         cloud_model=os.getenv("CLOUD_MODEL", "gpt-4o-mini"),
         embed_backend=os.getenv("EMBED_BACKEND", "cloud").lower(),

lyra/llm.py

@@ -14,7 +14,7 @@ class Message(TypedDict):
     content: str
 
 
-Backend = Literal["local", "cloud"]
+Backend = Literal["local", "cloud", "mi50"]
 
 
 def complete(messages: list[Message], backend: Backend = "local") -> str:
@@ -26,6 +26,12 @@ def complete(messages: list[Message], backend: Backend = "local") -> str:
         resp = client.chat.completions.create(model=cfg.cloud_model, messages=messages)
         return resp.choices[0].message.content or ""
 
+    if backend == "mi50":
+        # MI50 box runs an OpenAI-compatible llama.cpp server; key is unused.
+        client = OpenAI(api_key="not-needed", base_url=cfg.mi50_base_url)
+        resp = client.chat.completions.create(model=cfg.mi50_model, messages=messages)
+        return resp.choices[0].message.content or ""
+
     resp = httpx.post(
         f"{cfg.local_base_url}/api/chat",
         json={"model": cfg.local_model, "messages": messages, "stream": False},

lyra/web/server.py

@@ -32,7 +32,10 @@ _CLOUD = {"OPENAI", "cloud", "custom"}
 
 
 def _backend_for(label: str | None) -> Backend:
-    if label and label.upper() in {"PRIMARY", "SECONDARY", "FALLBACK", "LOCAL"}:
+    key = (label or "").lower()
+    if key == "mi50":
+        return "mi50"
+    if key in {"local", "primary", "secondary", "fallback"}:
         return "local"
     return "cloud"
 

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>