popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tests on dash

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-11 12:38:51 +03:00
parent 11bf460027
commit bb561a9665
7 changed files with 132 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.vscode/launch.json vendored
View File

@@ -7,7 +7,7 @@
"request": "launch",
"python": "${workspaceFolder}/.venv-rocm/bin/python",
"module": "meshnet_tracker.cli",
"args": ["start", "--host", "0.0.0.0", "--port", "8080"],
"args": ["start", "--host", "0.0.0.0", "--port", "8080", "--stats-db", "${workspaceFolder}/tracker-stats.sqlite", "--enable-test-runner"],
"console": "integratedTerminal",
"justMyCode": false
},

3
packages/node/meshnet_node/cli.py
View File

@@ -43,6 +43,9 @@ def _load_env_defaults() -> None:
_load_env_file(Path.cwd() / f".env.{machine}")
_load_env_file(Path.cwd() / ".env")
_load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
for path in os.environ.get("PYTHONPATH", "").split(os.pathsep):
if path and path not in sys.path:
sys.path.insert(0, path)
def _run_node(cfg: dict) -> None:

10
packages/tracker/meshnet_tracker/cli.py
View File

@@ -60,6 +60,9 @@ def _load_env_defaults() -> None:
_load_env_file(Path.cwd() / f".env.{machine}")
_load_env_file(Path.cwd() / ".env")
_load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
for path in os.environ.get("PYTHONPATH", "").split(os.pathsep):
if path and path not in sys.path:
sys.path.insert(0, path)
def _routing_config_from_args(args: argparse.Namespace) -> RoutingConfig | None:
@@ -357,6 +360,11 @@ def main() -> None:
metavar="N",
help=f"Number of rotated tracker log files to keep per level (default: {DEFAULT_LOG_BACKUP_COUNT})",
)
common.add_argument(
"--enable-test-runner",
action="store_true",
help="Enable development test-runner hooks for this tracker",
)
common.add_argument(
"--no-file-logs",
action="store_true",
@@ -373,6 +381,8 @@ def main() -> None:
subparsers.add_parser("start", help="Start the tracker server", parents=[common])
args = parser.parse_args()
if args.enable_test_runner:
os.environ["MESHNET_ENABLE_TEST_RUNNER"] = "1"
if args.command in {None, "start"}:
if not args.no_file_logs:

16
packages/tracker/meshnet_tracker/dashboard.html
View File

@@ -254,6 +254,7 @@
<label>Model
<select id="chat-model" onchange="selectChatModel(this.value)"></select>
</label>
<button type="button" id="request-model-load" style="display:none" onclick="requestSelectedModelLoad()">Load on available node</button>
<div id="chat-status" class="chat-status">select a model to start</div>
</div>
<div id="chat-history" class="chat-messages empty">
@@ -1386,6 +1387,20 @@ function selectChatModel(value) {
}
}
async function requestSelectedModelLoad() {
if (!selectedChatModel) return;
const button = $("request-model-load");
if (button) button.disabled = true;
const result = await apiCall("/v1/models/load", "POST", { model: selectedChatModel });
if (button) button.disabled = false;
if (!result.ok) {
alert(result.data.error || "model load request failed");
return;
}
const assignment = result.data.assignment || {};
$("chat-status").textContent = `load queued on ${short(assignment.node_id || "node")} for layers ${assignment.shard_start}-${assignment.shard_end}`;
}
function chatAuthToken() {
if (accountApiKeys.length) return accountApiKeys[0];
return null;
@@ -1394,6 +1409,7 @@ function chatAuthToken() {
function setAdminMode(enabled) {
isAdmin = enabled;
$("tab-admin").style.display = enabled ? "" : "none";
$("request-model-load").style.display = enabled ? "" : "none";
if (!enabled && dashboardTab === "admin") {
switchDashboardTab("overview");
} else {

51
packages/tracker/meshnet_tracker/server.py
View File

@@ -1276,6 +1276,35 @@ def _scale_demanded_models_locked(server: "_TrackerHTTPServer") -> None:
break
def _request_model_load_locked(server: "_TrackerHTTPServer", model_key: str) -> dict | None:
"""Queue an explicitly requested model on the best available joined node."""
resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
if preset is None or not preset.get("hf_repo"):
return None
required_start, required_end = _preset_layer_bounds(preset)
total_layers = required_end - required_start + 1
for host in _memory_pool_map(server)["hosts"]:
if host["spare_slots"] <= 0:
continue
host_nodes = [server.registry[item["node_id"]] for item in host["loaded"] if item["node_id"] in server.registry]
if not host_nodes:
continue
anchor = max(host_nodes, key=lambda node: node.benchmark_tokens_per_sec)
if anchor.status != "ready" or anchor.pending_new_assignment is not None:
continue
capacity = min(_node_layer_capacity(anchor, preset), total_layers)
if capacity <= 0:
continue
quantization = _node_quantization(anchor, preset)
shard_end = min(required_end, required_start + capacity - 1)
directive = _add_shard_directive(anchor, str(preset["hf_repo"]), required_start, shard_end, quantization)
anchor.pending_new_assignment = directive
anchor.pending_directives.append(directive)
_tracker_log(server, "info", "model load requested", node_id=anchor.node_id, model=resolved_name, hf_repo=preset["hf_repo"], shard=f"{required_start}-{shard_end}")
return {"node_id": anchor.node_id, "model": resolved_name, "hf_repo": preset["hf_repo"], "shard_start": required_start, "shard_end": shard_end}
return None
def _deployment_summary(nodes: list[_NodeEntry], preset: dict | None) -> dict:
if preset is None:
return {"recommended": False}
@@ -2672,6 +2701,9 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
if self.path == "/v1/benchmark/hop-penalty":
self._handle_benchmark_hop_penalty()
return
if self.path == "/v1/models/load":
self._handle_model_load_request()
return
if self.path == "/v1/calibration/toploc/run":
self._handle_toploc_calibration_run()
return
@@ -4294,6 +4326,25 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
server.gossip.merge({k: float(v) for k, v in body.items()})
self._send_json(200, {})
def _handle_model_load_request(self):
server: _TrackerHTTPServer = self.server # type: ignore[assignment]
if not self._require_role("admin"):
return
body = self._read_json_body()
if body is None:
return
model = body.get("model")
if not isinstance(model, str) or not model.strip():
self._send_json(400, {"error": "model is required"})
return
with server.lock:
self._purge_expired_nodes()
assignment = _request_model_load_locked(server, model)
if assignment is None:
self._send_json(409, {"error": "no ready joined node has an available model slot and sufficient capacity"})
return
self._send_json(202, {"status": "queued", "assignment": assignment})
def _handle_stats(self):
server: _TrackerHTTPServer = self.server # type: ignore[assignment]
if server.stats is None:

16
tests/test_dashboard.py
View File

@@ -76,6 +76,22 @@ def test_dashboard_chat_uses_streaming_fetch():
assert "renderChatModels(true)" in html
def test_dashboard_allows_admin_to_request_selected_model_load():
tracker = TrackerServer()
port = tracker.start()
try:
html = urllib.request.urlopen(
f"http://127.0.0.1:{port}/dashboard"
).read().decode()
finally:
tracker.stop()
assert 'id="request-model-load"' in html
assert "requestSelectedModelLoad" in html
assert '"/v1/models/load"' in html
assert '$("request-model-load").style.display = enabled ? "" : "none"' in html
def test_network_map_includes_node_friendly_name():
tracker = TrackerServer()
port = tracker.start()

35
tests/test_dynamic_routing.py
View File

@@ -305,6 +305,41 @@ def test_proxy_head_is_route_head_and_routing_endpoint_lists_routes():
assert sampled, "completed requests must produce route samples"
def test_admin_model_load_request_queues_directive_on_joined_node():
tracker = TrackerServer(validator_service_token="test-admin")
port = tracker.start()
try:
node = _post_json(
f"http://127.0.0.1:{port}/v1/nodes/register",
{
"endpoint": "http://127.0.0.1:9911",
"model": "stub-model",
"shard_start": 0,
"shard_end": 3,
"managed_assignment": True,
"memory_mb": 32768,
"hardware_profile": {"host_id": "available-ram-pool"},
},
)
request = urllib.request.Request(
f"http://127.0.0.1:{port}/v1/models/load",
data=json.dumps({"model": "qwen2.5-0.5b-instruct"}).encode(),
headers={"Content-Type": "application/json", "Authorization": "Bearer test-admin"},
method="POST",
)
with urllib.request.urlopen(request) as response:
result = json.loads(response.read())
heartbeat = _post_json(
f"http://127.0.0.1:{port}/v1/nodes/{node['node_id']}/heartbeat", {})
finally:
tracker.stop()
assert result["status"] == "queued"
assert result["assignment"]["node_id"] == node["node_id"]
assert heartbeat["directives"][0]["action"] == "ADD_SHARD"
assert heartbeat["directives"][0]["model"] == "Qwen/Qwen2.5-0.5B-Instruct"
def test_endpoint_key_distinguishes_same_port_different_hosts():
from meshnet_node.torch_server import _clamp_downstream_hops, _endpoint_key