feat: dynamically clean incompatible architectures
This commit is contained in:
@@ -12,10 +12,12 @@ if str(PACKAGE_DIR) in sys.path:
|
||||
sys.path.remove(str(PACKAGE_DIR))
|
||||
sys.path.insert(0, str(PACKAGE_DIR))
|
||||
|
||||
from architecture_compatibility import architecture_compatibility_key # noqa: E402
|
||||
from modelhub_client import ModelHubClient, ModelHubClientPool # noqa: E402
|
||||
from queue_cleanup import ( # noqa: E402
|
||||
OwnedTask,
|
||||
cleanup_certain_oom_tasks,
|
||||
find_architecture_incompatible_tasks,
|
||||
find_certain_oom_tasks,
|
||||
find_old_overflow_tasks,
|
||||
)
|
||||
@@ -72,9 +74,11 @@ class FakeDiscovery:
|
||||
self,
|
||||
sizes: dict[str, int | None],
|
||||
last_modified: dict[str, datetime | None] | None = None,
|
||||
configs: dict[str, dict[str, Any]] | None = None,
|
||||
) -> None:
|
||||
self.sizes = sizes
|
||||
self.last_modified = last_modified or {}
|
||||
self.configs = configs or {}
|
||||
|
||||
def list_repo_tree(self, repo_id: str) -> list[dict[str, Any]]:
|
||||
size = self.sizes[repo_id]
|
||||
@@ -85,6 +89,10 @@ class FakeDiscovery:
|
||||
def get_model_last_modified(self, repo_id: str) -> datetime | None:
|
||||
return self.last_modified.get(repo_id)
|
||||
|
||||
def get_model_config(self, repo_id: str) -> tuple[dict[str, Any], str | None]:
|
||||
config = self.configs.get(repo_id)
|
||||
return (dict(config), None) if config is not None else ({}, "config_not_found")
|
||||
|
||||
|
||||
class RecordingHttpClient:
|
||||
def __init__(self) -> None:
|
||||
@@ -103,6 +111,181 @@ class RecordingHttpClient:
|
||||
|
||||
|
||||
class QueueCleanupTests(unittest.TestCase):
|
||||
@staticmethod
|
||||
def architecture_block(
|
||||
*,
|
||||
gpu: str = "Iluvatar_bi-100",
|
||||
framework: str = "vllm",
|
||||
task_type: str = "text-generation",
|
||||
signature: str = "architectures:qwen2forcausallm",
|
||||
) -> tuple[str, dict[str, Any]]:
|
||||
key = architecture_compatibility_key(gpu, framework, task_type, signature)
|
||||
assert key is not None
|
||||
return key, {
|
||||
"targetGpu": gpu,
|
||||
"framework": framework,
|
||||
"taskType": task_type,
|
||||
"matchType": "architectures",
|
||||
"architectureSignature": signature,
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-09-11T00:00:00+00:00",
|
||||
}
|
||||
|
||||
def test_architecture_cleanup_matches_exact_context_and_protects_running(self) -> None:
|
||||
key, block = self.architecture_block()
|
||||
tasks = [
|
||||
OwnedTask(0, 1, "owner/waiting", "Iluvatar_bi-100", "waiting"),
|
||||
OwnedTask(0, 2, "owner/running", "Iluvatar_bi-100", "running"),
|
||||
OwnedTask(0, 3, "owner/other-framework", "Iluvatar_bi-100", "waiting"),
|
||||
]
|
||||
contexts = {
|
||||
"1": {
|
||||
"modelId": "owner/waiting",
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"framework": "vllm",
|
||||
"taskType": "text-generation",
|
||||
"modelProfile": {"architectures": ["Qwen2ForCausalLM"]},
|
||||
},
|
||||
"2": {
|
||||
"modelId": "owner/running",
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"framework": "vllm",
|
||||
"taskType": "text-generation",
|
||||
"modelProfile": {"architectures": ["Qwen2ForCausalLM"]},
|
||||
},
|
||||
"3": {
|
||||
"modelId": "owner/other-framework",
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"framework": "mindie",
|
||||
"taskType": "text-generation",
|
||||
"modelProfile": {"architectures": ["Qwen2ForCausalLM"]},
|
||||
},
|
||||
}
|
||||
|
||||
selected, skipped = find_architecture_incompatible_tasks(
|
||||
tasks,
|
||||
architecture_blocks={key: block},
|
||||
task_contexts=contexts,
|
||||
model_configs={},
|
||||
)
|
||||
|
||||
self.assertEqual([1], [item["taskId"] for item in selected])
|
||||
self.assertEqual(1, skipped["runningMatchedProtected"])
|
||||
self.assertEqual(1, skipped["noMatchingBlock"])
|
||||
|
||||
def test_queue_cleanup_fetches_config_and_stops_known_incompatible_waiting_task(self) -> None:
|
||||
key, block = self.architecture_block()
|
||||
client = FakeQueueClient(
|
||||
[
|
||||
{
|
||||
"taskId": 1,
|
||||
"modelId": "owner/model",
|
||||
"gpuType": "Iluvatar_bi-100",
|
||||
"status": "waiting",
|
||||
}
|
||||
]
|
||||
)
|
||||
pool = ModelHubClientPool([client], active_task_cap=100) # type: ignore[list-item]
|
||||
summary = cleanup_certain_oom_tasks(
|
||||
pool,
|
||||
FakeDiscovery(
|
||||
{"owner/model": 1 * GIB},
|
||||
configs={
|
||||
"owner/model": {
|
||||
"model_type": "qwen2",
|
||||
"architectures": ["Qwen2ForCausalLM"],
|
||||
}
|
||||
},
|
||||
), # type: ignore[arg-type]
|
||||
architecture_compatibility_blocks={key: block},
|
||||
task_compatibility_contexts={
|
||||
"1": {
|
||||
"modelId": "owner/model",
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"framework": "vllm",
|
||||
"taskType": "text-generation",
|
||||
"modelProfile": {},
|
||||
}
|
||||
},
|
||||
log=lambda _message: None,
|
||||
)
|
||||
|
||||
self.assertEqual(1, summary["architectureIncompatibleCount"])
|
||||
self.assertEqual(1, summary["cancelledCount"])
|
||||
self.assertEqual([[1]], client.stopped)
|
||||
|
||||
def test_dynamic_architecture_only_cleanup_skips_expensive_size_and_age_scans(self) -> None:
|
||||
key, block = self.architecture_block()
|
||||
client = FakeQueueClient(
|
||||
[
|
||||
{
|
||||
"taskId": 1,
|
||||
"modelId": "owner/model",
|
||||
"gpuType": "Iluvatar_bi-100",
|
||||
"status": "waiting",
|
||||
}
|
||||
]
|
||||
)
|
||||
pool = ModelHubClientPool([client], active_task_cap=100) # type: ignore[list-item]
|
||||
summary = cleanup_certain_oom_tasks(
|
||||
pool,
|
||||
FakeDiscovery({}), # type: ignore[arg-type]
|
||||
architecture_compatibility_blocks={key: block},
|
||||
task_compatibility_contexts={
|
||||
"1": {
|
||||
"modelId": "owner/model",
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"framework": "vllm",
|
||||
"taskType": "text-generation",
|
||||
"modelProfile": {"architectures": ["Qwen2ForCausalLM"]},
|
||||
}
|
||||
},
|
||||
architecture_only=True,
|
||||
log=lambda _message: None,
|
||||
)
|
||||
|
||||
self.assertTrue(summary["architectureOnly"])
|
||||
self.assertEqual(0, summary["repositorySizesComplete"])
|
||||
self.assertEqual(0, summary["modelAgeMetadataComplete"])
|
||||
self.assertEqual(1, summary["architectureIncompatibleCount"])
|
||||
self.assertEqual([[1]], client.stopped)
|
||||
|
||||
def test_architecture_cleanup_recheck_protects_task_that_started_running(self) -> None:
|
||||
key, block = self.architecture_block()
|
||||
client = FakeQueueClient(
|
||||
[
|
||||
{
|
||||
"taskId": 1,
|
||||
"modelId": "owner/model",
|
||||
"gpuType": "Iluvatar_bi-100",
|
||||
"status": "waiting",
|
||||
}
|
||||
],
|
||||
promote_on_waiting_read=2,
|
||||
)
|
||||
pool = ModelHubClientPool([client], active_task_cap=100) # type: ignore[list-item]
|
||||
summary = cleanup_certain_oom_tasks(
|
||||
pool,
|
||||
FakeDiscovery({"owner/model": 1 * GIB}), # type: ignore[arg-type]
|
||||
architecture_compatibility_blocks={key: block},
|
||||
task_compatibility_contexts={
|
||||
"1": {
|
||||
"modelId": "owner/model",
|
||||
"targetGpu": "Iluvatar_bi-100",
|
||||
"framework": "vllm",
|
||||
"taskType": "text-generation",
|
||||
"modelProfile": {"architectures": ["Qwen2ForCausalLM"]},
|
||||
}
|
||||
},
|
||||
read_concurrency=1,
|
||||
log=lambda _message: None,
|
||||
)
|
||||
|
||||
self.assertEqual(1, summary["architectureIncompatibleCount"])
|
||||
self.assertEqual(0, summary["cancelledCount"])
|
||||
self.assertEqual("task_started_running", summary["policyNoLongerAppliesTasks"][0]["policyChangeReason"])
|
||||
self.assertEqual([], client.stopped)
|
||||
|
||||
def test_old_models_use_each_accounts_own_capacity_minus_ten_threshold(self) -> None:
|
||||
now = datetime(2026, 8, 11, tzinfo=timezone.utc)
|
||||
tasks = [
|
||||
|
||||
Reference in New Issue
Block a user