Gate GMU climb on measured improvement

src/aituner/harness.py

@@ -1590,6 +1590,7 @@ def _runtime_candidate_actions(
             study,
             anchor_flags,
             recent_diagnostics,
+            anchor_rate_per_gpu=_profile_request_rate_per_gpu(anchor),
         )
         if target is not None:
             patch = {**runtime_base_patch, "gpu-memory-utilization": target}
@@ -1629,6 +1630,8 @@ def _next_gpu_memory_utilization_target(
     study: StudySpec,
     anchor_flags: dict[str, Any],
     recent_diagnostics: list[dict[str, Any]],
+    *,
+    anchor_rate_per_gpu: float = 0.0,
 ) -> float | None:
     current_gmu = _parse_float_like(
         anchor_flags.get("gpu-memory-utilization"), default=0.9
@@ -1651,8 +1654,14 @@ def _next_gpu_memory_utilization_target(
         gmu = _parse_float_like(flag_patch.get("gpu-memory-utilization"), default=0.0)
         if gmu <= 0:
             continue
+        if abs(gmu - current_gmu) <= EPSILON:
+            continue
         if item.get("status") == "completed":
-            successful_gmus.append(gmu)
+            rate = _as_float(item.get("best_request_rate_per_gpu"))
+            if anchor_rate_per_gpu > 0 and rate <= anchor_rate_per_gpu + EPSILON:
+                failed_gmus.append(gmu)
+            else:
+                successful_gmus.append(gmu)
         elif item.get("status") == "failed":
             failed_gmus.append(gmu)
     climb_from = max(successful_gmus)
@@ -1668,6 +1677,13 @@ def _next_gpu_memory_utilization_target(
     return target
 
 
+def _profile_request_rate_per_gpu(profile: dict[str, Any]) -> float:
+    performance = profile.get("performance")
+    if isinstance(performance, dict):
+        return _as_float(performance.get("best_request_rate_per_gpu"))
+    return _as_float(profile.get("best_request_rate_per_gpu"))
+
+
 def _prefill_scheduler_candidate_actions(
     study: StudySpec,
     window_summary: dict[str, Any],