Track Kimi model metadata and cache path

This commit is contained in:
Dobromir Popov
2026-07-01 12:38:31 +02:00
parent 78834e5045
commit bc760c1694
7 changed files with 231 additions and 10 deletions

View File

@@ -50,6 +50,43 @@ def test_tracker_send_json_ignores_broken_pipe_after_client_disconnect():
_TrackerHandler._send_json(DummyHandler(), 200, {"ok": True})
def test_tracker_exposes_registered_model_metadata():
tracker = TrackerServer()
port = tracker.start()
url = f"http://127.0.0.1:{port}"
try:
_post_json(
f"{url}/v1/nodes/register",
{
"endpoint": "http://127.0.0.1:7100",
"model": "Kimi-K2.7-Code",
"hf_repo": "unsloth/Kimi-K2.7-Code",
"num_layers": 61,
"shard_start": 0,
"shard_end": 60,
"hardware_profile": {},
"model_metadata": {
"total_parameters": "1T",
"activated_parameters": "32B",
"context_length": 256000,
},
},
)
models = _get_json(f"{url}/v1/models")
network_map = _get_json(f"{url}/v1/network/map")
finally:
tracker.stop()
kimi = next(model for model in models["data"] if model["id"] == "unsloth/Kimi-K2.7-Code")
assert kimi["metadata"]["total_parameters"] == "1T"
assert kimi["metadata"]["activated_parameters"] == "32B"
assert kimi["metadata"]["num_layers"] == 61
registered = network_map["nodes"][0]
assert registered["num_layers"] == 61
assert registered["model_metadata"]["context_length"] == 256000
def test_tracker_serves_health_while_proxy_request_is_in_flight():
"""Long inference proxy requests must not block heartbeats/health checks."""