Fix power governor active retention during long prompt evaluations and remove redundant proxy governor thread

scripts/ollama-proxy.py

@@ -26,54 +26,6 @@ import threading
 import re
 import subprocess
 
-# ----------------------------------------------------------------------------
-# GPU Power & Clock Governor (Automatic idle power reduction for CMP 50HX)
-# ----------------------------------------------------------------------------
-class GPUGovernor:
-    """Manages GPU clocks dynamically: drops CMP cards to low-power state when idle (saves ~90W),
-    and instantly unconstrains to full boost clocks during inference."""
-    def __init__(self, idle_timeout=30):
-        self.idle_timeout = idle_timeout
-        self.last_active = time.time()
-        self.is_low_power = False
-        self.lock = threading.Lock()
-        self._init_limits()
-        t = threading.Thread(target=self._monitor_loop, daemon=True)
-        t.start()
-
-    def _run_cmd(self, *args):
-        try:
-            subprocess.run(args, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False)
-        except Exception:
-            pass
-
-    def _init_limits(self):
-        # Ensure persistence mode and 150W safe power cap
-        self._run_cmd("nvidia-smi", "-pm", "1")
-        self._run_cmd("nvidia-smi", "-i", "1,2", "-pl", "150")
-
-    def wake(self):
-        with self.lock:
-            self.last_active = time.time()
-            if self.is_low_power:
-                self._run_cmd("nvidia-smi", "-rgc")
-                self.is_low_power = False
-
-    def touch(self):
-        with self.lock:
-            self.last_active = time.time()
-
-    def _monitor_loop(self):
-        while True:
-            time.sleep(5)
-            with self.lock:
-                if not self.is_low_power and (time.time() - self.last_active) > self.idle_timeout:
-                    # Drop CMP cards to low power idle clock
-                    self._run_cmd("nvidia-smi", "-i", "1,2", "-lgc", "600,600")
-                    self.is_low_power = True
-
-GOVERNOR = GPUGovernor(idle_timeout=30)
-
 # ----------------------------------------------------------------------------
 # Config
 # ----------------------------------------------------------------------------
@@ -125,7 +77,6 @@ def est_tokens(text):
     return max(1, (len(text) + 3) // 4)
 
 def _post(path, payload, stream=False):
-    GOVERNOR.wake()
     req = urllib.request.Request(
         BACKEND + path,
         data=json.dumps(payload).encode(),
@@ -153,7 +104,6 @@ def _backend_stream(messages, **kw):
     body.update(kw)
     with _post("/chat/completions", body) as r:
         for raw in r:
-            GOVERNOR.touch()
             line = raw.decode(errors="replace").strip()
             if not line:
                 continue