fix model DL doe 4-th time
This commit is contained in:
@@ -561,13 +561,19 @@ def run_startup(
|
||||
raise ValueError("--shard-start / --shard-end require --model-id")
|
||||
|
||||
# 3a. Auto-join: query tracker for network-wide HF model assignment.
|
||||
print("Querying tracker for network assignment...", flush=True)
|
||||
assign_qs = urllib.parse.urlencode({"device": device, "vram_mb": assignment_vram_mb, "ram_mb": ram_mb})
|
||||
# Skipped when the user explicitly requested a model — the shard-assignment
|
||||
# query below (/v1/nodes/assign?model=…) is authoritative there, and a fresh
|
||||
# tracker would otherwise print a scary 503 for the model-less auto-join.
|
||||
net_assignment: dict = {}
|
||||
try:
|
||||
net_assignment = _get_json(f"{tracker_url}/v1/network/assign?{assign_qs}")
|
||||
except Exception as exc:
|
||||
print(f" (auto-join unavailable: {exc})", flush=True)
|
||||
if model and model != "stub-model":
|
||||
print(f"Model {model!r} requested explicitly — skipping network auto-join.", flush=True)
|
||||
else:
|
||||
print("Querying tracker for network assignment...", flush=True)
|
||||
assign_qs = urllib.parse.urlencode({"device": device, "vram_mb": assignment_vram_mb, "ram_mb": ram_mb})
|
||||
try:
|
||||
net_assignment = _get_json(f"{tracker_url}/v1/network/assign?{assign_qs}")
|
||||
except Exception as exc:
|
||||
print(f" (auto-join unavailable: {exc})", flush=True)
|
||||
assigned_hf_repo: str | None = net_assignment.get("hf_repo")
|
||||
_gap_found: bool = bool(net_assignment.get("gap_found", False))
|
||||
|
||||
|
||||
Reference in New Issue
Block a user