CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fix: restore accuracy-first route admission

Browse Source
This commit is contained in:
CoolBoy
2026-09-22 15:26:42 +08:00
parent 4afce879dc
commit 6154dc738f
11 changed files with 343 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
modelhub_submmit_api/market_intelligence.py
View File

@@ -20,7 +20,8 @@ DEFAULT_THROUGHPUT_WINDOW_HOURS = 6
DEFAULT_FETCH_WORKERS = 4
DEFAULT_FRAMEWORK_MIN_SAMPLES = 300
DEFAULT_GPU_MIN_RECENT_TERMINALS = 20
DEFAULT_FRAMEWORK_MIN_WILSON = 0.05
DEFAULT_FRAMEWORK_MIN_WILSON = 0.20
DEFAULT_GPU_MIN_WILSON = 0.15
DEFAULT_COMMUNITY_WINDOW_DAYS = 30
DEFAULT_COMMUNITY_MAX_MODELS = 200
DEFAULT_COMMUNITY_HYDRATE_PER_REFRESH = 50
@@ -201,7 +202,7 @@ class MarketIntelligenceManager:
and health_factor >= 0.5
and int(item.get("recentTerminal") or 0) >= DEFAULT_GPU_MIN_RECENT_TERMINALS
and int(item.get("recentSuccess") or 0) > 0
and wilson >= DEFAULT_FRAMEWORK_MIN_WILSON
and wilson >= DEFAULT_GPU_MIN_WILSON
)
def _base_state(self, gpus: list[str], task_types: list[str], now: datetime) -> dict[str, Any]:
@@ -554,7 +555,7 @@ class MarketIntelligenceManager:
and health_factor >= 0.5
and int(stats.get("recentTerminal") or 0) >= DEFAULT_GPU_MIN_RECENT_TERMINALS
and int(stats.get("recentSuccess") or 0) > 0
and wilson >= DEFAULT_FRAMEWORK_MIN_WILSON
and wilson >= DEFAULT_GPU_MIN_WILSON
)
result[gpu] = stats
@@ -661,7 +662,26 @@ class MarketIntelligenceManager:
# Missing live data falls back to the scheduler's already-proven
# long/recent pools. Explicitly failed public gates never do.
if eligibility is False:
continue
low_sample = int(item.get("recentTerminal") or 0) < DEFAULT_GPU_MIN_RECENT_TERMINALS
has_recent_success = int(item.get("recentSuccess") or 0) > 0
recent_wilson = float(item.get("recentWilsonLowerBound") or 0.0)
healthy = float(item.get("healthFactor") or 1.0) >= 0.5
has_proven_framework = any(
bool(framework.get("officialConfigValid", False))
and int(framework.get("modelCount") or 0) >= self.framework_min_samples
and float(framework.get("wilsonLowerBound") or 0.0) >= DEFAULT_FRAMEWORK_MIN_WILSON
for by_gpu in ((self.state or {}).get("frameworkStats") or {}).values()
for framework in ((by_gpu or {}).get(gpu) or {}).values()
)
if (
item.get("canVerify") is False
or not low_sample
or not has_recent_success
or recent_wilson < DEFAULT_GPU_MIN_WILSON
or not healthy
or not has_proven_framework
):
continue
ranked.append((-float(item.get("selectionWeight") or 1.0), index, gpu))
return [gpu for _weight, _index, gpu in sorted(ranked)]
@@ -723,6 +743,7 @@ class MarketIntelligenceManager:
recent_item = (self.local_outcome_stats.get("recentCombinationStats") or {}).get(local_key) or {}
recent_success = max(0, int(recent_item.get("successCount") or 0))
recent_all_failures = max(0, int(recent_item.get("failureCount") or 0))
recent_failure = max(
0,
int(recent_item.get("attributableFailureCount", recent_item.get("failureCount") or 0)),
@@ -743,6 +764,16 @@ class MarketIntelligenceManager:
elif last_terminal_at is not None and consecutive_failures >= 5:
circuit_reason = "five_consecutive_local_failures"
circuit_until = last_terminal_at + timedelta(hours=12)
elif (
last_terminal_at is not None
and recent_success + recent_all_failures >= 5
and recent_success / (recent_success + recent_all_failures) < 0.10
):
# Runtime-empty and other unresolved failures must not create a
# permanent compatibility blacklist. Repetition is still strong
# operational evidence, so pause the route while feedback settles.
circuit_reason = "recent_terminal_success_below_10_percent"
circuit_until = last_terminal_at + timedelta(hours=12)
elif last_terminal_at is not None and recent_samples >= 20 and recent_rate is not None and recent_rate < 0.20:
circuit_reason = "recent_local_success_below_20_percent"
circuit_until = last_terminal_at + timedelta(hours=6)