feat: add durable success-first modelhub agent

modelhub_submmit_api/outcome_tracker.py

@@ -492,6 +492,7 @@ class OutcomeTracker:
         framework_groups: dict[str, list[dict[str, Any]]] = defaultdict(list)
         combo_groups: dict[tuple[str, str, str], list[dict[str, Any]]] = defaultdict(list)
         profile_groups: dict[tuple[str, str, str, str, str], list[dict[str, Any]]] = defaultdict(list)
+        sized_profile_groups: dict[tuple[str, str, str, str, str, int], list[dict[str, Any]]] = defaultdict(list)
 
         for record in terminal:
             gpu = record.get("targetGpu") or "unknown"
@@ -505,6 +506,13 @@ class OutcomeTracker:
             if model_type:
                 quantization = str(profile.get("quantizationMethod") or "none").strip()
                 profile_groups[(gpu, fw, tt, model_type, quantization)].append(record)
+                try:
+                    load_bytes = max(1, int(profile.get("estimatedLoadBytes") or 0))
+                except (TypeError, ValueError):
+                    load_bytes = 0
+                if load_bytes > 0:
+                    size_bucket = int(load_bytes).bit_length() - 1
+                    sized_profile_groups[(gpu, fw, tt, model_type, quantization, size_bucket)].append(record)
 
         gpu_summaries = {gpu: _summarize(records) for gpu, records in gpu_groups.items()}
         framework_summaries = {fw: _summarize(records) for fw, records in framework_groups.items()}
@@ -561,6 +569,19 @@ class OutcomeTracker:
                 "lastTerminalAt": last_terminal_at.isoformat() if last_terminal_at else None,
             }
 
+        sized_profile_combination_stats: dict[str, dict[str, Any]] = {}
+        for (gpu, fw, tt, model_type, quantization, size_bucket), records in sized_profile_groups.items():
+            key = f"{gpu}|{fw}|{tt}|{model_type}|{quantization}|{size_bucket}"
+            sized_profile_combination_stats[key] = {
+                "targetGpu": gpu,
+                "framework": fw,
+                "taskType": tt,
+                "modelType": model_type,
+                "quantizationMethod": quantization,
+                "loadSizeLog2Bucket": size_bucket,
+                **_summarize(records),
+            }
+
         warnings: list[str] = []
         for gpu, summary in gpu_summaries.items():
             if summary["decisionTotal"] >= 4 and summary["decisionFailureRate"] >= 0.5:
@@ -607,6 +628,7 @@ class OutcomeTracker:
             "recentCombinationStats": recent_combination_stats,
             "profileCombinationStats": profile_combination_stats,
             "recentProfileCombinationStats": recent_profile_combination_stats,
+            "sizedProfileCombinationStats": sized_profile_combination_stats,
             "architectureCompatibilityBlocks": architecture_blocks,
             "architectureCompatibilitySummary": {
                 "activeBlockCount": len(architecture_blocks),