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

feat: make model age admission-only

Browse Source
This commit is contained in:
CoolBoy
2026-08-12 10:18:09 +08:00
parent 86088ce577
commit 91d1d3d87d
15 changed files with 438 additions and 653 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
modelhub_submmit_api/poll_runner.py
View File

@@ -74,7 +74,7 @@ def build_parser() -> argparse.ArgumentParser:
parser.add_argument(
"--recent-model-reserve-slots",
type=int,
default=int(os.getenv("MODELHUB_RECENT_MODEL_RESERVE_SLOTS", "10")),
default=int(os.getenv("MODELHUB_RECENT_MODEL_RESERVE_SLOTS", "5")),
help=argparse.SUPPRESS,
)
parser.add_argument(
@@ -83,12 +83,6 @@ def build_parser() -> argparse.ArgumentParser:
default=int(os.getenv("MODELHUB_RECENT_MODEL_DAYS", "7")),
help=argparse.SUPPRESS,
)
parser.add_argument(
"--dynamic-old-model-cleanup-reserve-slots",
type=int,
default=int(os.getenv("MODELHUB_DYNAMIC_OLD_MODEL_CLEANUP_RESERVE_SLOTS", "5")),
help=argparse.SUPPRESS,
)
parser.add_argument("--disable-candidate-preflight", action="store_true", help=argparse.SUPPRESS)
parser.add_argument("--llm-classifier-endpoint", default=os.getenv("MODELHUB_LLM_CLASSIFIER_ENDPOINT"), help=argparse.SUPPRESS)
parser.add_argument("--llm-classifier-model", default=os.getenv("MODELHUB_LLM_CLASSIFIER_MODEL"), help=argparse.SUPPRESS)
@@ -245,33 +239,11 @@ def _build_modelhub_client(base_args: argparse.Namespace) -> ModelHubClientPool:
clients,
capacity_probe_interval_cycles=max(0, int(getattr(base_args, "capacity_probe_interval_cycles", 3) or 0)),
capacity_state_path=Path(getattr(base_args, "capacity_state_path", DEFAULT_CAPACITY_STATE_PATH)),
recent_model_reserve_slots=max(0, int(getattr(base_args, "recent_model_reserve_slots", 10) or 0)),
recent_model_reserve_slots=max(0, int(getattr(base_args, "recent_model_reserve_slots", 5) or 0)),
recent_model_days=max(1, int(getattr(base_args, "recent_model_days", 7) or 7)),
)
def resolve_age_cleanup_policy(
base_args: argparse.Namespace,
*,
initial_cleanup_pending: bool,
) -> tuple[str, int]:
"""Reserve ten slots initially, then use a five-slot cleanup hysteresis."""
initial_reserve_slots = max(
0,
int(getattr(base_args, "recent_model_reserve_slots", 10) or 0),
)
dynamic_reserve_slots = min(
initial_reserve_slots,
max(
0,
int(getattr(base_args, "dynamic_old_model_cleanup_reserve_slots", 5) or 0),
),
)
if initial_cleanup_pending:
return "initial", initial_reserve_slots
return "dynamic", dynamic_reserve_slots
def _persist_architecture_blacklist(
report: dict[str, Any],
*,
@@ -554,7 +526,6 @@ def run_poll_loop(
submitted_total = 0
cycles = 0
stopped_reason = "max_cycles_reached"
initial_age_cleanup_pending = True
pending_architecture_cleanup = False
last_cleaned_architecture_blocks: set[str] = set()
@@ -645,14 +616,9 @@ def run_poll_loop(
)
if active_architecture_block_keys - last_cleaned_architecture_blocks:
pending_architecture_cleanup = True
age_cleanup_mode, age_cleanup_reserve_slots = resolve_age_cleanup_policy(
base_args,
initial_cleanup_pending=initial_age_cleanup_pending,
)
log(
f"[queue-cleanup] mode={'architecture_dynamic' if architecture_only_cleanup else age_cleanup_mode} "
f"reserve_recent_slots={age_cleanup_reserve_slots} "
f"recent_days={max(1, int(getattr(base_args, 'recent_model_days', 7) or 7))}"
"[queue-cleanup] age_cleanup=disabled_admission_only "
f"deterministic_cleanup={'architecture_only' if architecture_only_cleanup else 'full'}"
)
cleanup_summary = cleanup_certain_oom_tasks(
modelhub_client,
@@ -672,7 +638,6 @@ def run_poll_loop(
)
),
architecture_only=architecture_only_cleanup,
age_reserved_slots=age_cleanup_reserve_slots,
log=log,
)
policy_cancelled_recorded = outcome_tracker.mark_policy_cancellations(
@@ -697,9 +662,13 @@ def run_poll_loop(
"mode": (
"architecture_dynamic"
if architecture_only_cleanup
else age_cleanup_mode
else "deterministic_full"
),
"ageCleanupMode": "admission_only",
"ageReservedSlots": max(
0,
int(getattr(base_args, "recent_model_reserve_slots", 5) or 0),
),
"ageReservedSlots": age_cleanup_reserve_slots,
"ageQueueThresholds": cleanup_summary["oldModelQueueThresholds"],
"activeScanned": cleanup_summary["activeScanned"],
"certainOomCount": cleanup_summary["certainOomCount"],
@@ -715,8 +684,6 @@ def run_poll_loop(
"stopErrorCount": len(cleanup_summary["stopErrors"]),
}
)
if not architecture_only_cleanup:
initial_age_cleanup_pending = False
pending_architecture_cleanup = False
last_cleaned_architecture_blocks = active_architecture_block_keys
except Exception as exc: