Add dual-GPU FLUX 9B image pipeline

platform/docker/profile-controller/profile_controller.py

@@ -25,6 +25,8 @@ ALLOWED = tuple(x.strip() for x in os.environ.get(
 LABEL_KEY = "com.mike-ai.llama-profile"
 IMAGE_LABEL_KEY = "com.mike-ai.image-worker"
 IMAGE_WORKER = os.environ.get("IMAGE_WORKER", "image")
+TTS_LABEL_KEY = "com.mike-ai.tts-worker"
+TTS_WORKER = os.environ.get("TTS_WORKER", "qwen3")
 LOCK = threading.Lock()
 log = logging.getLogger("profile-controller")
 
@@ -77,6 +79,15 @@ def image_container() -> dict:
     return matches[0]
 
 
+def tts_container() -> dict:
+    matches = [item for item in labelled_containers(TTS_LABEL_KEY)
+               if item.get("Labels", {}).get(TTS_LABEL_KEY) == TTS_WORKER]
+    if len(matches) != 1:
+        raise RuntimeError(
+            f"expected exactly one TTS worker {TTS_WORKER!r}, found {len(matches)}")
+    return matches[0]
+
+
 def stop_container(item: dict, timeout: int = 120) -> None:
     if item.get("State") != "running":
         return
@@ -85,6 +96,14 @@ def stop_container(item: dict, timeout: int = 120) -> None:
         raise RuntimeError(f"failed to stop container: HTTP {status}")
 
 
+def start_container(item: dict) -> None:
+    if item.get("State") == "running":
+        return
+    status, _ = docker_request("POST", f"/containers/{item['Id']}/start")
+    if status not in (204, 304):
+        raise RuntimeError(f"failed to start container: HTTP {status}")
+
+
 def stop_inference() -> dict:
     with LOCK:
         items = containers()
@@ -101,14 +120,17 @@ def set_image_worker(running: bool) -> dict:
             # The image worker may never overlap a llama profile on the 5080.
             for profile_item in containers().values():
                 stop_container(profile_item)
-            if item.get("State") != "running":
-                status, _ = docker_request("POST", f"/containers/{item['Id']}/start")
-                if status not in (204, 304):
-                    raise RuntimeError(f"failed to start image worker: HTTP {status}")
+            # The 9B beta text encoder temporarily borrows the RTX 3060 from
+            # Qwen3-TTS. The gateway retains Piper as a fallback meanwhile.
+            stop_container(tts_container(), timeout=30)
+            start_container(item)
         else:
             # CUDA/PyTorch may not react promptly to SIGTERM after an OOM.
             # Bound recovery time and let Docker issue SIGKILL afterwards.
             stop_container(item, timeout=20)
+            # TTS is restored by the following profile activation. Keeping it
+            # stopped here lets the router verify that both GPUs really
+            # released the image model before Qwen and TTS are reloaded.
         return {"image_worker": "running" if running else "stopped"}
 
 
@@ -126,6 +148,7 @@ def activate(profile: str) -> dict:
     with LOCK:
         # Defensive mutual exclusion even if a caller bypasses the router.
         stop_container(image_container())
+        start_container(tts_container())
         items = containers()
         missing = [name for name in ALLOWED if name not in items]
         if missing: