feat: prioritize proven GPU framework combinations

modelhub_submmit_api/main.py

@@ -68,7 +68,7 @@ def build_parser() -> argparse.ArgumentParser:
     parser.add_argument(
         "--disable-gpu-strategy",
         action="store_true",
-        help="Disable adaptive 50/30/20 GPU scheduling and keep the legacy candidate order",
+        help="Disable adaptive 70/30 proven-GPU scheduling and keep the legacy candidate order",
     )
     parser.add_argument(
         "--disable-market-intelligence",
@@ -274,22 +274,14 @@ def choose_candidate_for_gpu(
         except ValueError:
             pass
         if market_intelligence is not None:
-            discovered = market_intelligence.compatible_discovered_frameworks(
+            compatible_frameworks = market_intelligence.selectable_frameworks(
                 task_type=task_type,
                 target_gpu=target_gpu,
+                incumbent_frameworks=compatible_frameworks,
                 inspection=inspection,
             )
-            compatible_frameworks.extend(
-                framework for framework in discovered if framework not in compatible_frameworks
-            )
         if not compatible_frameworks:
             continue
-        if market_intelligence is not None:
-            compatible_frameworks = market_intelligence.rank_frameworks(
-                task_type=task_type,
-                target_gpu=target_gpu,
-                compatible_frameworks=compatible_frameworks,
-            )
 
         for framework in compatible_frameworks:
             config_params = (
@@ -451,7 +443,12 @@ def process_model_for_candidates(
             market_intelligence=market_intelligence,
         )
         if best is None:
-            skipped.append({"repoId": model.repo_id, "targetGpu": target_gpu, "reason": "no_compatible_auto_template_or_framework"})
+            reason = (
+                "no_publicly_vetted_compatible_framework"
+                if market_intelligence is not None
+                else "no_compatible_auto_template_or_framework"
+            )
+            skipped.append({"repoId": model.repo_id, "targetGpu": target_gpu, "reason": reason})
             continue
         record = candidate_to_record(best)
         if market_intelligence is not None:
@@ -706,6 +703,7 @@ def run_submission(
     target_gpus = resolve_target_gpus(args, template_selector, selected_task_types)
     if not target_gpus:
         raise RuntimeError("No auto-submittable GPUs are available for the selected task types")
+    submission_target_gpus = list(target_gpus)
 
     hf_discovery = hf_discovery or HuggingFaceDiscovery(base_url=args.hf_base_url)
     if modelhub_client is None:
@@ -809,6 +807,7 @@ def run_submission(
             "dryRun": bool(args.dry_run),
             "selectedTaskTypes": selected_task_types,
             "targetGpus": target_gpus,
+            "submissionEligibleGpus": submission_target_gpus,
             "dailyTarget": args.daily_target,
             "unlimitedDailyTarget": unlimited_daily_target,
             "submittedTodayBeforeRun": daily_snapshot["totalCount"],
@@ -893,6 +892,14 @@ def run_submission(
         except Exception:
             market_intelligence.set_local_outcome_stats(None)
         market_summary = market_intelligence.summary()
+        submission_target_gpus = market_intelligence.eligible_gpus(target_gpus)
+        market_summary["eligibleGpus"] = submission_target_gpus
+        market_summary["shadowOnlyGpus"] = [gpu for gpu in target_gpus if gpu not in submission_target_gpus]
+        print(
+            f"[market] eligible_gpus={','.join(submission_target_gpus) or 'none'} "
+            f"shadow_only={','.join(market_summary['shadowOnlyGpus']) or 'none'}",
+            flush=True,
+        )
 
     if strategy_enabled:
         strategy_manager = GPUStrategyManager(
@@ -930,7 +937,7 @@ def run_submission(
 
     scan_limit = resolve_scan_limit(
         args,
-        target_gpu_count=len(target_gpus),
+        target_gpu_count=len(submission_target_gpus),
         remaining_daily_quota=remaining_daily_quota,
         platform_available_slots=platform_available_slots,
     )
@@ -986,7 +993,7 @@ def run_submission(
             hf_discovery=hf_discovery,
             modelhub_client=modelhub_client,
             template_selector=template_selector,
-            target_gpus=target_gpus,
+            target_gpus=submission_target_gpus,
             selected_task_types=selected_task_types,
             outcome_tracker=outcome_tracker,
             submission_exclusion_store=submission_exclusion_store,
@@ -1204,6 +1211,7 @@ def run_submission(
         "dryRun": bool(args.dry_run),
         "selectedTaskTypes": selected_task_types,
         "targetGpus": target_gpus,
+        "submissionEligibleGpus": submission_target_gpus,
         "maxSubmitsPerRun": int(getattr(args, "max_submits_per_run", 0) or 0),
         "dailyTarget": args.daily_target,
         "unlimitedDailyTarget": unlimited_daily_target,