feat(us-026): smart model assignment via demand×coverage scoring
/v1/network/assign now scores models by (demand_rpm + 1) × (coverage_deficit + 0.01) so high-traffic, under-covered models are preferred when assigning new nodes. Response includes price_per_token: 0.0 (reserved for future pricing protocol). --memory MB flag added to node CLI to override autodetected VRAM budget for shard assignment without changing hardware detection for inference. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -27,6 +27,7 @@ def _run_node(cfg: dict) -> None:
|
||||
cache_dir=Path(cfg["download_dir"]) if cfg.get("download_dir") else None,
|
||||
host=cfg.get("host", "0.0.0.0"),
|
||||
route_timeout=float(cfg.get("route_timeout", 30.0)),
|
||||
vram_mb_override=cfg.get("vram_mb_override"),
|
||||
)
|
||||
except Exception as exc:
|
||||
print(f"\nERROR: {exc}", file=sys.stderr, flush=True)
|
||||
@@ -89,6 +90,8 @@ def _cmd_default(args) -> int:
|
||||
overrides["host"] = args.host
|
||||
if args.route_timeout != 30.0:
|
||||
overrides["route_timeout"] = args.route_timeout
|
||||
if getattr(args, "memory", None) is not None:
|
||||
overrides["vram_mb_override"] = args.memory
|
||||
|
||||
if overrides:
|
||||
cfg = merge_cli_overrides(cfg, **overrides)
|
||||
@@ -177,6 +180,7 @@ def _cmd_start(args) -> int:
|
||||
host=cfg["host"],
|
||||
advertise_host=getattr(args, "advertise_host", None),
|
||||
route_timeout=getattr(args, "route_timeout", 30.0),
|
||||
vram_mb_override=getattr(args, "memory", None),
|
||||
)
|
||||
except Exception as exc:
|
||||
print(f"ERROR: {exc}", file=sys.stderr, flush=True)
|
||||
@@ -218,6 +222,8 @@ def main() -> None:
|
||||
parser.add_argument("--host", metavar="ADDR", help="Interface to bind (default 0.0.0.0)")
|
||||
parser.add_argument("--route-timeout", type=float, metavar="SEC", default=30.0,
|
||||
help="Seconds to wait for tracker route lookup (default 30)")
|
||||
parser.add_argument("--memory", type=int, metavar="MB", default=None,
|
||||
help="Override autodetected VRAM/RAM budget in MB used for shard assignment")
|
||||
parser.add_argument("--no-tui", action="store_true", help="Plain-text output (no rich dashboard)")
|
||||
parser.add_argument("--compact", action="store_true", help="Single-line status output")
|
||||
parser.add_argument("--reset-config", action="store_true", help="Re-run wizard even if config exists")
|
||||
@@ -248,6 +254,8 @@ def main() -> None:
|
||||
start_cmd.add_argument("--download-dir")
|
||||
start_cmd.add_argument("--route-timeout", type=float, default=30.0,
|
||||
help="Seconds to wait for tracker route lookup (default 30)")
|
||||
start_cmd.add_argument("--memory", type=int, default=None, metavar="MB",
|
||||
help="Override autodetected VRAM/RAM budget in MB used for shard assignment")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user