routing and dashboard fixes
This commit is contained in:
@@ -355,6 +355,134 @@ def test_tracker_proxy_accepts_hf_model_alias_from_quickstart():
|
||||
assert response["choices"][0]["message"]["content"] == "56"
|
||||
|
||||
|
||||
def test_tracker_proxy_routes_split_preset_nodes_by_alias():
|
||||
"""The chat proxy must build routes from alias-matched preset nodes."""
|
||||
|
||||
class ChatHandler(http.server.BaseHTTPRequestHandler):
|
||||
def log_message(self, fmt, *args):
|
||||
pass
|
||||
|
||||
def do_POST(self):
|
||||
if self.path != "/v1/chat/completions":
|
||||
self.send_response(404)
|
||||
self.end_headers()
|
||||
return
|
||||
length = int(self.headers.get("Content-Length", 0))
|
||||
self.rfile.read(length)
|
||||
route_header = self.headers.get("X-Meshnet-Route", "[]")
|
||||
body = json.dumps({
|
||||
"choices": [{"message": {"content": route_header}}],
|
||||
"usage": {"prompt_tokens": 1, "completion_tokens": 1},
|
||||
}).encode()
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
|
||||
head = http.server.HTTPServer(("127.0.0.1", 0), ChatHandler)
|
||||
head_thread = threading.Thread(target=head.serve_forever, daemon=True)
|
||||
head_thread.start()
|
||||
tracker = TrackerServer(model_presets={
|
||||
"qwen3.6-35b-a3b": {
|
||||
"layers_start": 0,
|
||||
"layers_end": 39,
|
||||
"hf_repo": "unsloth/Qwen3.6-35B-A3B",
|
||||
"aliases": ["Qwen3.6-35B-A3B"],
|
||||
}
|
||||
})
|
||||
tracker_port = tracker.start()
|
||||
try:
|
||||
_post_json(
|
||||
f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
|
||||
{"endpoint": f"http://127.0.0.1:{head.server_address[1]}",
|
||||
"model": "qwen3.6-35b-a3b",
|
||||
"hf_repo": "unsloth/Qwen3.6-35B-A3B",
|
||||
"num_layers": 40,
|
||||
"shard_start": 0,
|
||||
"shard_end": 21,
|
||||
"tracker_mode": True,
|
||||
"hardware_profile": {},
|
||||
"score": 1.0},
|
||||
)
|
||||
_post_json(
|
||||
f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
|
||||
{"endpoint": "http://127.0.0.1:9199",
|
||||
"model": "Qwen3.6-35B-A3B",
|
||||
"hf_repo": "unsloth/Qwen3.6-35B-A3B",
|
||||
"num_layers": 40,
|
||||
"shard_start": 22,
|
||||
"shard_end": 39,
|
||||
"tracker_mode": True,
|
||||
"hardware_profile": {},
|
||||
"score": 1.0},
|
||||
)
|
||||
|
||||
response = _post_json(
|
||||
f"http://127.0.0.1:{tracker_port}/v1/chat/completions",
|
||||
{"model": "Qwen3.6-35B-A3B",
|
||||
"messages": [{"role": "user", "content": "hi"}]},
|
||||
)
|
||||
console = _get_json(f"http://127.0.0.1:{tracker_port}/v1/console")
|
||||
finally:
|
||||
tracker.stop()
|
||||
head.shutdown()
|
||||
head.server_close()
|
||||
head_thread.join(timeout=1.0)
|
||||
|
||||
route = json.loads(response["choices"][0]["message"]["content"])
|
||||
assert route == [{"endpoint": "http://127.0.0.1:9199", "start_layer": 22}]
|
||||
complete = [event for event in console["events"] if event["message"] == "proxy complete"][-1]
|
||||
assert complete["fields"]["tokens"] == 2
|
||||
assert complete["fields"]["tokens_per_sec"] >= 0
|
||||
|
||||
|
||||
def test_tracker_route_endpoint_routes_split_preset_nodes_by_alias():
|
||||
tracker = TrackerServer(model_presets={
|
||||
"qwen3.6-35b-a3b": {
|
||||
"layers_start": 0,
|
||||
"layers_end": 39,
|
||||
"hf_repo": "unsloth/Qwen3.6-35B-A3B",
|
||||
"aliases": ["Qwen3.6-35B-A3B"],
|
||||
}
|
||||
})
|
||||
tracker_port = tracker.start()
|
||||
try:
|
||||
_post_json(
|
||||
f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
|
||||
{"endpoint": "http://127.0.0.1:9101",
|
||||
"model": "qwen3.6-35b-a3b",
|
||||
"hf_repo": "unsloth/Qwen3.6-35B-A3B",
|
||||
"num_layers": 40,
|
||||
"shard_start": 0,
|
||||
"shard_end": 21,
|
||||
"tracker_mode": True,
|
||||
"hardware_profile": {},
|
||||
"score": 1.0},
|
||||
)
|
||||
_post_json(
|
||||
f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
|
||||
{"endpoint": "http://127.0.0.1:9102",
|
||||
"model": "Qwen3.6-35B-A3B",
|
||||
"hf_repo": "unsloth/Qwen3.6-35B-A3B",
|
||||
"num_layers": 40,
|
||||
"shard_start": 22,
|
||||
"shard_end": 39,
|
||||
"tracker_mode": True,
|
||||
"hardware_profile": {},
|
||||
"score": 1.0},
|
||||
)
|
||||
|
||||
response = _get_json(
|
||||
f"http://127.0.0.1:{tracker_port}/v1/route?model=Qwen3.6-35B-A3B"
|
||||
)
|
||||
finally:
|
||||
tracker.stop()
|
||||
|
||||
assert response["route"] == ["http://127.0.0.1:9101", "http://127.0.0.1:9102"]
|
||||
assert [node["start_layer"] for node in response["nodes"]] == [0, 22]
|
||||
|
||||
|
||||
def test_tracker_registration_node_id_includes_wallet_prefix_and_stable_suffix():
|
||||
tracker = TrackerServer()
|
||||
tracker_port = tracker.start()
|
||||
|
||||
Reference in New Issue
Block a user