fix model load/unload

This commit is contained in:
Dobromir Popov
2026-07-15 12:35:32 +02:00
parent 97e2784b37
commit 22f28bd69a
4 changed files with 111 additions and 7 deletions

View File

@@ -375,6 +375,11 @@ def test_admin_can_replace_a_served_model_and_release_it():
with urllib.request.urlopen(load) as response:
assert json.loads(response.read())["assignment"]["node_id"] == node["node_id"]
heartbeat = _post_json(f"http://127.0.0.1:{port}/v1/nodes/{node['node_id']}/heartbeat", {})
_post_json(
f"http://127.0.0.1:{port}/v1/nodes/{node['node_id']}/heartbeat",
{"completed_directives": [{"action": "DROP_SHARD", "model": "Qwen/Qwen2.5-0.5B-Instruct"}]},
)
network = _get_json(f"http://127.0.0.1:{port}/v1/network/map")
assert heartbeat["directives"][0]["action"] == "LOAD_SHARD"
release = urllib.request.Request(
f"http://127.0.0.1:{port}/v1/models/release",
@@ -386,6 +391,33 @@ def test_admin_can_replace_a_served_model_and_release_it():
tracker.stop()
assert heartbeat["directives"][0]["action"] == "DROP_SHARD"
released_node = next(item for item in network["nodes"] if item["node_id"] == node["node_id"])
assert released_node["shard_start"] is None
assert released_node["shard_end"] is None
def test_models_list_does_not_duplicate_a_preset_registered_by_hf_repo():
"""A preset and its canonical repository are one selectable model."""
tracker = TrackerServer(enable_billing=False)
port = tracker.start()
try:
_post_json(
f"http://127.0.0.1:{port}/v1/nodes/register",
{
"endpoint": "http://127.0.0.1:9913",
"model": "Qwen2.5-0.5B-Instruct",
"hf_repo": "Qwen/Qwen2.5-0.5B-Instruct",
"num_layers": 24,
"shard_start": 0,
"shard_end": 23,
},
)
models = _get_json(f"http://127.0.0.1:{port}/v1/models")["data"]
finally:
tracker.stop()
assert [model["id"] for model in models].count("qwen2.5-0.5b-instruct") == 1
assert not any(model["id"] == "Qwen/Qwen2.5-0.5B-Instruct" for model in models)
def test_endpoint_key_distinguishes_same_port_different_hosts():

View File

@@ -287,6 +287,47 @@ def test_configure_torch_threads_applies_explicit_settings(monkeypatch):
assert active == {"torch_threads": 12, "torch_interop_threads": 2}
def test_heartbeat_applies_release_without_reregistering(monkeypatch):
"""DROP_SHARD has no replacement range and must not look like an outage."""
import meshnet_node.startup as startup_mod
released = threading.Event()
requests: list[tuple[str, dict]] = []
class FakeNode:
def apply_tracker_directives(self, directives):
assert directives == [{"action": "DROP_SHARD", "model": "Qwen/Qwen2.5-0.5B-Instruct"}]
return {"action": "DROP_SHARD", "model": "Qwen/Qwen2.5-0.5B-Instruct"}
def fake_post(url, payload, timeout=10.0):
requests.append((url, dict(payload)))
released.set()
return {"directives": [{"action": "DROP_SHARD", "model": "Qwen/Qwen2.5-0.5B-Instruct"}]}
sleep_calls = 0
def one_heartbeat(_seconds):
nonlocal sleep_calls
sleep_calls += 1
if sleep_calls > 1:
raise SystemExit
monkeypatch.setattr(startup_mod, "_post_json", fake_post)
monkeypatch.setattr(startup_mod.time, "sleep", one_heartbeat)
payload = {
"model": "Qwen2.5-0.5B-Instruct",
"hf_repo": "Qwen/Qwen2.5-0.5B-Instruct",
"shard_start": 0,
"shard_end": 23,
}
startup_mod._start_heartbeat("http://tracker", "node-1", payload, interval=0, node_ref=FakeNode())
assert released.wait(1), "heartbeat did not receive the queued release"
assert len(requests) == 1, "release must not trigger a re-registration"
assert payload["shard_start"] == 0
assert payload["shard_end"] == 23
def test_benchmark_throughput_is_registered_in_payload(monkeypatch, tmp_path):
"benchmark_tokens_per_sec from the benchmark is included in the tracker registration.\n\nTags: node, performance, startup"
import meshnet_node.startup as startup_mod