fix model load/unload
This commit is contained in:
@@ -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():
|
||||
|
||||
Reference in New Issue
Block a user