Merge branch cursor/fix-meshnet-node-param-parsing into master.
Combine shard label formatting with model/shard flag parsing and tracker registration retry. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
@@ -90,6 +90,19 @@ def _run_node(cfg: dict) -> None:
|
||||
)
|
||||
|
||||
|
||||
def _resolve_model_flags(
|
||||
model: str | None,
|
||||
model_id: str | None,
|
||||
) -> tuple[str | None, str | None]:
|
||||
"""Return (model_name, hf_repo_or_none) from --model / --model-id flags."""
|
||||
explicit = model_id or model
|
||||
if not explicit:
|
||||
return None, None
|
||||
if "/" in explicit:
|
||||
return explicit.split("/")[-1], explicit
|
||||
return explicit, None
|
||||
|
||||
|
||||
def _first_available_port(host: str, start: int = 7000, attempts: int = 100) -> int:
|
||||
"""Return the first TCP port bindable on host, starting at start."""
|
||||
bind_host = "" if host == "0.0.0.0" else host
|
||||
@@ -122,9 +135,10 @@ def _cmd_default(args) -> int:
|
||||
|
||||
# Apply CLI overrides on top of saved config
|
||||
overrides: dict = {}
|
||||
if args.model:
|
||||
overrides["model_hf_repo"] = args.model
|
||||
overrides["model_name"] = args.model.split("/")[-1]
|
||||
model_name, hf_repo = _resolve_model_flags(args.model, getattr(args, "model_id", None))
|
||||
if model_name is not None:
|
||||
overrides["model_name"] = model_name
|
||||
overrides["model_hf_repo"] = hf_repo or ""
|
||||
if args.quantization:
|
||||
overrides["quantization"] = args.quantization
|
||||
if args.download_dir:
|
||||
@@ -215,16 +229,15 @@ def _cmd_start(args) -> int:
|
||||
if args.tracker:
|
||||
cfg["tracker_url"] = args.tracker
|
||||
cfg["port"] = args.port if args.port is not None else _first_available_port(args.host)
|
||||
model = args.model or cfg.get("model_hf_repo") or cfg.get("model_name") or None
|
||||
if args.model_id is None and model and "/" in model:
|
||||
cfg["model_hf_repo"] = model
|
||||
cfg["model_name"] = model.split("/")[-1]
|
||||
else:
|
||||
cfg["model_name"] = model
|
||||
model_name, hf_repo = _resolve_model_flags(
|
||||
args.model or cfg.get("model_hf_repo") or cfg.get("model_name") or None,
|
||||
args.model_id,
|
||||
)
|
||||
if model_name is not None:
|
||||
cfg["model_name"] = model_name
|
||||
cfg["model_hf_repo"] = hf_repo or ""
|
||||
cfg["quantization"] = args.quantization
|
||||
cfg["host"] = args.host
|
||||
if args.model_id:
|
||||
cfg["model_hf_repo"] = args.model_id
|
||||
if args.shard_start is not None:
|
||||
cfg["shard_start"] = args.shard_start
|
||||
if args.shard_end is not None:
|
||||
@@ -242,7 +255,7 @@ def _cmd_start(args) -> int:
|
||||
tracker_url=cfg["tracker_url"],
|
||||
port=cfg["port"],
|
||||
model=cfg["model_name"],
|
||||
model_id=cfg.get("model_hf_repo"),
|
||||
model_id=cfg.get("model_hf_repo") or None,
|
||||
shard_start=cfg.get("shard_start"),
|
||||
shard_end=cfg.get("shard_end"),
|
||||
quantization=cfg["quantization"].replace("bf16", "bfloat16"),
|
||||
@@ -288,7 +301,8 @@ def main() -> None:
|
||||
)
|
||||
|
||||
# Flags that apply to the no-subcommand (default) path
|
||||
parser.add_argument("--model", metavar="HF_REPO", help="HuggingFace repo ID to serve")
|
||||
parser.add_argument("--model", metavar="MODEL", help="Model name or HuggingFace repo ID to serve")
|
||||
parser.add_argument("--model-id", metavar="MODEL", help="Alias for --model (catalog name or HuggingFace repo)")
|
||||
parser.add_argument("--quantization", "-q", choices=["bf16", "int8", "nf4", "bfloat16"],
|
||||
help="Quantization level")
|
||||
parser.add_argument("--download-dir", metavar="PATH", help="Model download directory")
|
||||
@@ -329,8 +343,8 @@ def main() -> None:
|
||||
start_cmd = subparsers.add_parser("start", help="Start node (legacy flags)")
|
||||
start_cmd.add_argument("--tracker")
|
||||
start_cmd.add_argument("--port", type=int)
|
||||
start_cmd.add_argument("--model")
|
||||
start_cmd.add_argument("--model-id", help="HuggingFace repo ID")
|
||||
start_cmd.add_argument("--model", help="Model name or HuggingFace repo ID")
|
||||
start_cmd.add_argument("--model-id", help="Alias for --model (catalog name or HuggingFace repo)")
|
||||
start_cmd.add_argument("--shard-start", type=int)
|
||||
start_cmd.add_argument("--shard-end", type=int)
|
||||
start_cmd.add_argument("--quantization", choices=["auto", "bfloat16", "int8", "nf4", "bf16"], default="auto")
|
||||
|
||||
@@ -346,6 +346,9 @@ def _attach_relay_bridge(node: StubNodeServer | TorchNodeServer, bridge: RelayHt
|
||||
node.stop = _stop_with_bridge # type: ignore[method-assign]
|
||||
|
||||
|
||||
_PENDING_NODE_ID = "pending"
|
||||
|
||||
|
||||
def _start_heartbeat(
|
||||
tracker_url: str,
|
||||
node_id: str,
|
||||
@@ -383,6 +386,8 @@ def _start_heartbeat(
|
||||
try:
|
||||
resp = _post_json(f"{tracker_url}/v1/nodes/register", register_payload)
|
||||
node_id = resp.get("node_id", node_id)
|
||||
if node_ref is not None:
|
||||
setattr(node_ref, "tracker_node_id", node_id)
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
@@ -434,7 +439,7 @@ def _start_heartbeat(
|
||||
def _loop() -> None:
|
||||
nonlocal node_id
|
||||
hb_url = f"{tracker_url}/v1/nodes/{node_id}/heartbeat"
|
||||
outage_streak = 0 # consecutive intervals where tracker was unreachable
|
||||
outage_streak = 1 if node_id == _PENDING_NODE_ID else 0
|
||||
|
||||
while True:
|
||||
time.sleep(interval)
|
||||
@@ -489,6 +494,34 @@ def _start_heartbeat(
|
||||
return t
|
||||
|
||||
|
||||
def _register_with_tracker(
|
||||
tracker_url: str,
|
||||
reg_payload: dict,
|
||||
node: Any,
|
||||
start_time: float,
|
||||
) -> str | None:
|
||||
"""Register with the tracker, or start background retries when it is unreachable."""
|
||||
try:
|
||||
reg_resp = _post_json(f"{tracker_url}/v1/nodes/register", reg_payload)
|
||||
tracker_node_id = str(reg_resp.get("node_id") or "?")
|
||||
setattr(node, "tracker_node_id", tracker_node_id)
|
||||
print(f" Registered with tracker — node ID: {tracker_node_id}", flush=True)
|
||||
_start_heartbeat(tracker_url, tracker_node_id, reg_payload, node_ref=node, start_time=start_time)
|
||||
return tracker_node_id
|
||||
except Exception as exc:
|
||||
setattr(node, "tracker_node_id", None)
|
||||
print(f" Warning: tracker registration failed: {exc}", flush=True)
|
||||
print(" [node] will retry registration in the background", flush=True)
|
||||
_start_heartbeat(
|
||||
tracker_url,
|
||||
_PENDING_NODE_ID,
|
||||
reg_payload,
|
||||
node_ref=node,
|
||||
start_time=start_time,
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
def _warn_virtual_network_ip(ip: str | None) -> None:
|
||||
"""Print a warning when the auto-detected advertise IP is in a known virtual-network range.
|
||||
|
||||
@@ -648,8 +681,11 @@ def run_startup(
|
||||
if probationary_line is not None:
|
||||
print(f" {probationary_line}", flush=True)
|
||||
|
||||
pinned_shard_start = shard_start
|
||||
pinned_shard_end = shard_end
|
||||
user_pinned_shard = pinned_shard_start is not None or pinned_shard_end is not None
|
||||
|
||||
if model_id: # treat "" the same as None — no explicit model given
|
||||
user_pinned_shard = shard_start is not None or shard_end is not None
|
||||
full_sources: list[dict] = []
|
||||
# Auto-detect shard range from model config if not explicitly provided
|
||||
if shard_start is None or shard_end is None:
|
||||
@@ -757,16 +793,9 @@ def run_startup(
|
||||
**registration_capabilities,
|
||||
**relay_fields,
|
||||
}
|
||||
tracker_node_id: str | None = None
|
||||
try:
|
||||
reg_resp = _post_json(f"{tracker_url}/v1/nodes/register", reg_payload)
|
||||
tracker_node_id = str(reg_resp.get("node_id") or "?")
|
||||
setattr(node, "tracker_node_id", tracker_node_id)
|
||||
print(f" Registered with tracker — node ID: {tracker_node_id}", flush=True)
|
||||
_start_heartbeat(tracker_url, tracker_node_id, reg_payload, node_ref=node, start_time=_node_start_time)
|
||||
except Exception as exc:
|
||||
setattr(node, "tracker_node_id", None)
|
||||
print(f" Warning: tracker registration failed: {exc}", flush=True)
|
||||
tracker_node_id = _register_with_tracker(
|
||||
tracker_url, reg_payload, node, _node_start_time,
|
||||
)
|
||||
|
||||
print(
|
||||
f"\n{'=' * 32}\n"
|
||||
@@ -784,8 +813,8 @@ def run_startup(
|
||||
flush=True,
|
||||
)
|
||||
return node
|
||||
if shard_start is not None or shard_end is not None:
|
||||
raise ValueError("--shard-start / --shard-end require --model-id")
|
||||
if user_pinned_shard and not model:
|
||||
raise ValueError("--shard-start / --shard-end require --model")
|
||||
|
||||
# 3a. Auto-join: query tracker for network-wide HF model assignment.
|
||||
# Skipped when the user explicitly requested a model — the shard-assignment
|
||||
@@ -892,16 +921,9 @@ def run_startup(
|
||||
**registration_capabilities,
|
||||
**relay_fields,
|
||||
}
|
||||
tracker_node_id = None
|
||||
try:
|
||||
reg_resp = _post_json(f"{tracker_url}/v1/nodes/register", auto_reg_payload)
|
||||
tracker_node_id = str(reg_resp.get("node_id") or "?")
|
||||
setattr(node, "tracker_node_id", tracker_node_id)
|
||||
print(f" Registered with tracker — node ID: {tracker_node_id}", flush=True)
|
||||
_start_heartbeat(tracker_url, tracker_node_id, auto_reg_payload, node_ref=node, start_time=_node_start_time)
|
||||
except Exception as exc:
|
||||
setattr(node, "tracker_node_id", None)
|
||||
print(f" Warning: tracker registration failed: {exc}", flush=True)
|
||||
tracker_node_id = _register_with_tracker(
|
||||
tracker_url, auto_reg_payload, node, _node_start_time,
|
||||
)
|
||||
shard_label = _format_shard_label(
|
||||
assigned_shard_start,
|
||||
assigned_shard_end,
|
||||
@@ -947,8 +969,13 @@ def run_startup(
|
||||
print(f" ERROR: Cannot reach tracker at {tracker_url}: {exc}", file=sys.stderr, flush=True)
|
||||
raise
|
||||
|
||||
shard_start: int = assignment["shard_start"]
|
||||
shard_end: int = assignment["shard_end"]
|
||||
shard_start = assignment["shard_start"]
|
||||
shard_end = assignment["shard_end"]
|
||||
if user_pinned_shard:
|
||||
if pinned_shard_start is not None:
|
||||
shard_start = pinned_shard_start
|
||||
if pinned_shard_end is not None:
|
||||
shard_end = pinned_shard_end
|
||||
assigned_model: str = assignment.get("model", model)
|
||||
hf_repo: str | None = assignment.get("hf_repo")
|
||||
peers: list[dict] = assignment.get("peers", [])
|
||||
@@ -960,10 +987,15 @@ def run_startup(
|
||||
if model_layers_end is not None
|
||||
else None
|
||||
)
|
||||
print(
|
||||
f" Shard: {_format_shard_label(shard_start, shard_end, assigned_total_layers, model_name=assigned_model)}",
|
||||
flush=True,
|
||||
shard_label = _format_shard_label(
|
||||
shard_start,
|
||||
shard_end,
|
||||
assigned_total_layers,
|
||||
model_name=assigned_model,
|
||||
)
|
||||
if user_pinned_shard:
|
||||
shard_label = f"{shard_label} (pinned)"
|
||||
print(f" Shard: {shard_label}", flush=True)
|
||||
|
||||
# 4. Download shard
|
||||
print("Downloading shard...", flush=True)
|
||||
@@ -1025,6 +1057,7 @@ def run_startup(
|
||||
"hardware_profile": hw,
|
||||
"wallet_address": address,
|
||||
"score": 1.0,
|
||||
"managed_assignment": not user_pinned_shard,
|
||||
**registration_capabilities,
|
||||
**relay_fields,
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user