feat: let admins manage model placement
This commit is contained in:
@@ -355,6 +355,39 @@ def test_admin_model_load_request_queues_directive_on_joined_node():
|
||||
assert heartbeat["directives"][0]["model"] == "Qwen/Qwen2.5-0.5B-Instruct"
|
||||
|
||||
|
||||
def test_admin_can_replace_a_served_model_and_release_it():
|
||||
"Forced admin placement replaces a served shard; release queues DROP_SHARD."
|
||||
tracker = TrackerServer(enable_billing=False, validator_service_token="test-admin")
|
||||
port = tracker.start()
|
||||
try:
|
||||
node = _post_json(
|
||||
f"http://127.0.0.1:{port}/v1/nodes/register",
|
||||
{"endpoint": "http://127.0.0.1:9912", "model": "stub-model",
|
||||
"shard_start": 0, "shard_end": 3, "managed_assignment": True,
|
||||
"max_loaded_shards": 1, "memory_mb": 1,
|
||||
"hardware_profile": {"host_id": "full-host"}},
|
||||
)
|
||||
headers = {"Content-Type": "application/json", "Authorization": "Bearer test-admin"}
|
||||
load = urllib.request.Request(
|
||||
f"http://127.0.0.1:{port}/v1/models/load",
|
||||
data=json.dumps({"model": "qwen2.5-0.5b-instruct", "force": True}).encode(),
|
||||
headers=headers, method="POST")
|
||||
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", {})
|
||||
assert heartbeat["directives"][0]["action"] == "LOAD_SHARD"
|
||||
release = urllib.request.Request(
|
||||
f"http://127.0.0.1:{port}/v1/models/release",
|
||||
data=json.dumps({"model": "qwen2.5-0.5b-instruct"}).encode(), headers=headers, method="POST")
|
||||
with urllib.request.urlopen(release) as response:
|
||||
assert json.loads(response.read())["released"] == 1
|
||||
heartbeat = _post_json(f"http://127.0.0.1:{port}/v1/nodes/{node['node_id']}/heartbeat", {})
|
||||
finally:
|
||||
tracker.stop()
|
||||
|
||||
assert heartbeat["directives"][0]["action"] == "DROP_SHARD"
|
||||
|
||||
|
||||
def test_endpoint_key_distinguishes_same_port_different_hosts():
|
||||
"Endpoint key distinguishes same port different hosts\n\nTags: http, performance, routing, tracker"
|
||||
from meshnet_node.torch_server import _clamp_downstream_hops, _endpoint_key
|
||||
|
||||
Reference in New Issue
Block a user